Update langchain to 1.x to fix CVE in langchain-core (dependabot #174)

langchain-core had a high-severity path traversal vulnerability in
legacy load_prompt functions, fixed in 1.2.22. Declare langchain and
openpipe extras as conflicting since langchain-openai now requires
openai>=2.26 while openpipe caps openai<=1.97.1.

.claude-plugin/marketplace.json

@@ -0,0 +1,27 @@
+{
+  "name": "pipecat-dev-skills",
+  "owner": {
+    "name": "Pipecat"
+  },
+  "metadata": {
+    "description": "Development workflow skills for contributing to the Pipecat project",
+    "version": "1.0.0"
+  },
+  "plugins": [
+    {
+      "name": "pipecat-dev",
+      "description": "Development workflow skills for contributing to the Pipecat project",
+      "version": "1.0.0",
+      "source": "./",
+      "skills": [
+        "./.claude/skills/changelog",
+        "./.claude/skills/cleanup",
+        "./.claude/skills/code-review",
+        "./.claude/skills/docstring",
+        "./.claude/skills/pr-description",
+        "./.claude/skills/pr-submit",
+        "./.claude/skills/update-docs"
+      ]
+    }
+  ]
+}

.claude/settings.json

@@ -0,0 +1,5 @@
+{
+  "attribution": {
+    "commit": ""
+  }
+}

.claude/skills/changelog/SKILL.md

@@ -0,0 +1,61 @@
+---
+name: changelog
+description: Create changelog files for important commits in a PR
+---
+
+Create changelog files for the important commits in this PR. The PR number is provided as an argument.
+
+## Instructions
+
+1. Skip changelog for: documentation-only, internal refactoring, test-only, CI changes.
+
+2. First, check what commits are on the current branch compared to main:
+   ```
+   git log main..HEAD --oneline
+   ```
+
+3. For each significant change, create a changelog file in the `changelog/` folder using the format:
+   Allowed types: `added`, `changed`, `deprecated`, `removed`, `fixed`, `security`, `performance`, `other`
+   - `{PR_NUMBER}.added.md` - for new features
+   - `{PR_NUMBER}.added.2.md`, `{PR_NUMBER}.added.3.md` - for additional entries of the same type
+   - `{PR_NUMBER}.changed.md` - for changes to existing functionality
+   - `{PR_NUMBER}.fixed.md` - for bug fixes
+   - `{PR_NUMBER}.deprecated.md` - for deprecations
+   - `{PR_NUMBER}.removed.md` - for removed features
+   - `{PR_NUMBER}.security.md` - for security fixes
+   - `{PR_NUMBER}.performance.md` - for performance improvements
+   - `{PR_NUMBER}.other.md` - for other changes
+
+4. Each changelog file should at least contain a main single line starting with `- ` followed by a clear description of the change. No line wrapping.
+
+5. If the change is complicated, changelog files can have indented lines after the main line with additional details or code samples.
+
+6. Use ⚠️ emoji prefix for breaking changes.
+
+7. **Write changes in user-facing terms first.** Lead with what users of the framework will notice: new APIs, changed behavior, new parameters, fixed bugs they might have hit, etc. Implementation details (internal refactoring, how something is wired up under the hood) can be included as secondary context after the user-facing description, but should never be the *only* content of a changelog entry when there is a user-visible effect.
+
+   **Good** (user-facing first, implementation detail as context):
+   ```
+   - Turn completion instructions now persist correctly across full context updates when using `system_instruction`. Previously they were injected as a context system message, which caused warning spam and didn't survive context updates.
+   ```
+
+   **Bad** (implementation detail only, no user-facing framing):
+   ```
+   - Fixed turn completion instructions being injected as a context system message instead of using `system_instruction`.
+   ```
+
+   Ask yourself: "If I'm a developer building on Pipecat, what would I notice changed?" Start there.
+
+## Example
+
+For PR #3519 with a new feature and a bug fix:
+
+`changelog/3519.added.md`:
+```
+- Added `SomeNewFeature` for doing something useful.
+```
+
+`changelog/3519.fixed.md`:
+```
+- Fixed an issue where something was not working correctly in some user-visible scenario. The root cause was an internal implementation detail.
+```

.claude/skills/cleanup/SKILL.md

@@ -0,0 +1,307 @@
+# Code Cleanup Skill
+
+The **Code Cleanup Skill** reviews, refactors, and documents code changes in your current branch, ensuring alignment with **Pipecat's architecture, coding standards, and example patterns**.
+It focuses on **readability, correctness, performance, and consistency**, while avoiding breaking changes.
+
+---
+
+## Skill Overview
+
+This skill analyzes all changes introduced in your branch and performs the following actions:
+
+1. **Analyze Branch Changes**
+   - Review uncommitted changes and outgoing commits
+2. **Refactor for Readability**
+   - Improve clarity, naming, structure, and modern Python usage
+3. **Enhance Performance**
+   - Identify safe, conservative optimization opportunities
+4. **Add Documentation**
+   - Apply Pipecat-style, Google-format docstrings
+5. **Ensure Pattern Consistency**
+   - Match existing Pipecat services, pipelines, and examples
+6. **Validate Examples**
+   - Ensure examples follow foundational patterns (e.g. `07-interruptible.py`)
+
+---
+
+## Usage
+
+Invoke the skill using any of the following commands:
+
+- "Clean up my branch code"
+- "Refactor the changes in my branch"
+- "Review and improve my branch code"
+- `/cleanup`
+
+---
+
+## What This Skill Does
+
+### 1. Analyze Branch Changes
+
+The skill retrieves all uncommitted changes and outgoing commits to understand:
+
+- New files added
+- Modified files
+- Code additions and deletions
+- Overall scope and intent of changes
+
+---
+
+### 2. Code Refactoring
+
+#### Readability Improvements
+
+- Replace tuples with named classes or dataclasses
+- Improve variable, method, and class naming
+- Extract complex logic into well-named helper methods
+- Add missing type hints
+- Simplify nested or complex conditionals
+- Replace deprecated methods and features
+- Normalize formatting to match Pipecat style
+
+#### Performance Enhancements
+
+- Identify inefficient loops or repeated work
+- Suggest appropriate data structures
+- Optimize async workflows and I/O
+- Remove redundant operations
+
+> Performance changes are conservative and non-breaking.
+
+---
+
+### 3. Documentation
+
+Documentation follows **Google-style docstrings**, consistent with Pipecat conventions.
+
+#### Class Documentation
+
+```python
+class ExampleService:
+    """Brief one-line description.
+
+    Detailed explanation of the class purpose, responsibilities,
+    and important behaviors.
+
+    Supported features:
+
+    - Feature 1
+    - Feature 2
+    - Feature 3
+    """
+```
+
+#### Method Documentation
+
+```python
+def process_data(self, data: str, options: Optional[dict] = None) -> bool:
+    """Process incoming data with optional configuration.
+
+    Args:
+        data: The input data to process.
+        options: Optional configuration dictionary.
+
+    Returns:
+        True if processing succeeded, False otherwise.
+
+    Raises:
+        ValueError: If data is empty or invalid.
+    """
+```
+
+#### Pydantic Model Parameters
+
+```python
+class InputParams(BaseModel):
+    """Configuration parameters for the service.
+
+    Parameters:
+        timeout: Request timeout in seconds.
+        retry_count: Number of retry attempts.
+        enable_logging: Whether to enable debug logging.
+    """
+
+    timeout: Optional[float] = None
+    retry_count: int = 3
+    enable_logging: bool = False
+```
+
+---
+
+### 4. Pattern Consistency Checks
+
+#### Service Classes
+
+- Correct inheritance (`TTSService`, `STTService`, `LLMService`)
+- Consistent constructor signatures
+- Frame emission patterns
+- Metrics support:
+  - `can_generate_metrics()`
+  - TTFB metrics
+  - Usage metrics
+- Alignment with similar existing services
+
+#### Examples
+
+Validated against `examples/foundational/07-interruptible.py`:
+
+- Proper `create_transport()` usage
+- Correct pipeline structure
+- Task setup and observers
+- Event handler registration
+- Runner and bot entrypoint consistency
+
+---
+
+### 5. Specific Implementation Patterns
+
+#### Service Implementation
+
+```python
+class ExampleTTSService(TTSService):
+
+    def __init__(self, *, api_key: Optional[str] = None, **kwargs):
+        super().__init__(**kwargs)
+        self._api_key = api_key or os.getenv("SERVICE_API_KEY")
+
+    def can_generate_metrics(self) -> bool:
+        return True
+
+    async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
+        try:
+            await self.start_ttfb_metrics()
+            yield TTSStartedFrame()
+            # ... processing ...
+            yield TTSAudioRawFrame(...)
+        finally:
+            await self.stop_ttfb_metrics()
+```
+
+---
+
+#### Example Structure Pattern
+
+```python
+transport_params = {
+    "daily": lambda: DailyParams(...),
+    "twilio": lambda: FastAPIWebsocketParams(...),
+    "webrtc": lambda: TransportParams(...),
+}
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    stt = DeepgramSTTService(...)
+    tts = SomeTTSService(...)
+    llm = OpenAILLMService(...)
+
+    context = LLMContext(messages)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(...)
+
+    pipeline = Pipeline([...])
+    task = PipelineTask(pipeline, params=..., observers=[...])
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        await task.queue_frames([LLMRunFrame()])
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+    await runner.run(task)
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+```
+
+---
+
+## Execution Flow
+
+1. Fetch uncommitted and outgoing changes
+2. Categorize files (services, examples, tests, utilities)
+3. Analyze each file:
+   - Readability
+   - Performance
+   - Documentation
+   - Pattern consistency
+4. Generate actionable recommendations
+5. Apply Pipecat standards
+
+---
+
+## Examples
+
+### Before: Tuple Usage
+
+```python
+def get_audio_info(self) -> Tuple[int, int]:
+    return (48000, 1)
+```
+
+### After: Named Class
+
+```python
+class AudioInfo:
+    """Audio configuration information.
+
+    Parameters:
+        sample_rate: Sample rate in Hz.
+        num_channels: Number of audio channels.
+    """
+
+    sample_rate: int
+    num_channels: int
+
+def get_audio_info(self) -> AudioInfo:
+    return AudioInfo(sample_rate=48000, num_channels=1)
+```
+
+---
+
+### Before: Missing Documentation
+
+```python
+class NewTTSService(TTSService):
+    def __init__(self, api_key: str, voice: str):
+        self._api_key = api_key
+        self._voice = voice
+```
+
+### After: Fully Documented
+
+```python
+class NewTTSService(TTSService):
+    """Text-to-speech service using NewProvider API.
+
+    Streams PCM audio and emits TTSAudioRawFrame frames compatible
+    with Pipecat transports.
+
+    Supported features:
+    - Text-to-speech synthesis
+    - Streaming PCM audio
+    - Voice customization
+    - TTFB metrics
+    """
+
+    def __init__(self, *, api_key: str, voice: str, **kwargs):
+        """Initialize the NewTTSService.
+
+        Args:
+            api_key: API key for authentication.
+            voice: Voice identifier to use.
+            **kwargs: Additional arguments passed to the parent service.
+        """
+        super().__init__(**kwargs)
+        self._api_key = api_key
+        self.set_voice(voice)
+```
+
+---
+
+## Notes
+
+- Non-breaking improvements only
+- Backward compatibility preserved
+- Conservative performance changes
+- Google-style docstrings
+- Pattern checks follow recent Pipecat code

.claude/skills/code-review/SKILL.md

@@ -0,0 +1,107 @@
+---
+name: code-review
+description: Automated code review for pull requests using multiple specialized agents
+disable-model-invocation: true
+allowed-tools: Bash(gh issue view:*), Bash(gh search:*), Bash(gh issue list:*), Bash(gh pr comment:*), Bash(gh pr diff:*), Bash(gh pr view:*), Bash(gh pr list:*)
+---
+
+Provide a code review for the given pull request.
+
+**Agent assumptions (applies to all agents and subagents):**
+
+- All tools are functional and will work without error. Do not test tools or make exploratory calls. Make sure this is clear to every subagent that is launched.
+- Only call a tool if it is required to complete the task. Every tool call should have a clear purpose.
+
+To do this, follow these steps precisely:
+
+1. Launch a haiku agent to check if any of the following are true:
+   - The pull request is closed
+   - The pull request is a draft
+   - The pull request does not need code review (e.g. automated PR, trivial change that is obviously correct)
+   - Claude has already commented on this PR (check `gh pr view <PR> --comments` for comments left by claude)
+
+   If any condition is true, stop and do not proceed.
+
+Note: Still review Claude generated PR's.
+
+2. Launch a haiku agent to return a list of file paths (not their contents) for all relevant CLAUDE.md files including:
+   - The root CLAUDE.md file, if it exists
+   - Any CLAUDE.md files in directories containing files modified by the pull request
+
+3. Launch a sonnet agent to view the pull request and return a summary of the changes
+
+4. Launch 4 agents in parallel to independently review the changes. Each agent should return the list of issues, where each issue includes a description and the reason it was flagged (e.g. "CLAUDE.md adherence", "bug"). The agents should do the following:
+
+   Agents 1 + 2: CLAUDE.md compliance sonnet agents
+   Audit changes for CLAUDE.md compliance in parallel. Note: When evaluating CLAUDE.md compliance for a file, you should only consider CLAUDE.md files that share a file path with the file or parents.
+
+   Agent 3: Opus bug agent (parallel subagent with agent 4)
+   Scan for obvious bugs. Focus only on the diff itself without reading extra context. Flag only significant bugs; ignore nitpicks and likely false positives. Do not flag issues that you cannot validate without looking at context outside of the git diff.
+
+   Agent 4: Opus bug agent (parallel subagent with agent 3)
+   Look for problems that exist in the introduced code. This could be security issues, incorrect logic, etc. Only look for issues that fall within the changed code.
+
+   **CRITICAL: We only want HIGH SIGNAL issues.** Flag issues where:
+   - The code will fail to compile or parse (syntax errors, type errors, missing imports, unresolved references)
+   - The code will definitely produce wrong results regardless of inputs (clear logic errors)
+   - Clear, unambiguous CLAUDE.md violations where you can quote the exact rule being broken
+
+   Do NOT flag:
+   - Code style or quality concerns
+   - Potential issues that depend on specific inputs or state
+   - Subjective suggestions or improvements
+
+   If you are not certain an issue is real, do not flag it. False positives erode trust and waste reviewer time.
+
+   In addition to the above, each subagent should be told the PR title and description. This will help provide context regarding the author's intent.
+
+5. For each issue found in the previous step by agents 3 and 4, launch parallel subagents to validate the issue. These subagents should get the PR title and description along with a description of the issue. The agent's job is to review the issue to validate that the stated issue is truly an issue with high confidence. For example, if an issue such as "variable is not defined" was flagged, the subagent's job would be to validate that is actually true in the code. Another example would be CLAUDE.md issues. The agent should validate that the CLAUDE.md rule that was violated is scoped for this file and is actually violated. Use Opus subagents for bugs and logic issues, and sonnet agents for CLAUDE.md violations.
+
+6. Filter out any issues that were not validated in step 5. This step will give us our list of high signal issues for our review.
+
+7. If issues were found, skip to step 8 to post comments.
+
+   If NO issues were found, post a summary comment using `gh pr comment` (if `--comment` argument is provided):
+   "No issues found. Checked for bugs and CLAUDE.md compliance."
+
+8. Create a list of all comments that you plan on leaving. This is only for you to make sure you are comfortable with the comments. Do not post this list anywhere.
+
+9. Post inline comments for each issue using `gh pr review` with inline comments. For each comment:
+   - Provide a brief description of the issue
+   - For small, self-contained fixes, include a committable suggestion block
+   - For larger fixes (6+ lines, structural changes, or changes spanning multiple locations), describe the issue and suggested fix without a suggestion block
+   - Never post a committable suggestion UNLESS committing the suggestion fixes the issue entirely. If follow up steps are required, do not leave a committable suggestion.
+
+   **IMPORTANT: Only post ONE comment per unique issue. Do not post duplicate comments.**
+
+Use this list when evaluating issues in Steps 4 and 5 (these are false positives, do NOT flag):
+
+- Pre-existing issues
+- Something that appears to be a bug but is actually correct
+- Pedantic nitpicks that a senior engineer would not flag
+- Issues that a linter will catch (do not run the linter to verify)
+- General code quality concerns (e.g., lack of test coverage, general security issues) unless explicitly required in CLAUDE.md
+- Issues mentioned in CLAUDE.md but explicitly silenced in the code (e.g., via a lint ignore comment)
+
+Notes:
+
+- Use gh CLI to interact with GitHub (e.g., fetch pull requests, create comments). Do not use web fetch.
+- Create a todo list before starting.
+- You must cite and link each issue in inline comments (e.g., if referring to a CLAUDE.md, include a link to it).
+- If no issues are found, post a comment with the following format:
+
+---
+
+## Code review
+
+No issues found. Checked for bugs and CLAUDE.md compliance.
+
+---
+
+- When linking to code in inline comments, follow the following format precisely, otherwise the Markdown preview won't render correctly: `https://github.com/OWNER/REPO/blob/FULL_SHA/path/to/file.py#L10-L15`
+  - Requires full git sha
+  - You must provide the full sha. Commands like `https://github.com/owner/repo/blob/$(git rev-parse HEAD)/foo/bar` will not work, since your comment will be directly rendered in Markdown.
+  - Repo name must match the repo you're code reviewing
+  - # sign after the file name
+  - Line range format is L[start]-L[end]
+  - Provide at least 1 line of context before and after, centered on the line you are commenting about (eg. if you are commenting about lines 5-6, you should link to `L4-7`)

.claude/skills/docstring/SKILL.md

@@ -0,0 +1,256 @@
+---
+name: docstring
+description: Document a Python module and its classes using Google style
+---
+
+Document a Python module or class using Google-style docstrings following project conventions. The argument can be a class name or a module path.
+
+## Instructions
+
+1. Determine what to document based on the argument:
+
+   **If a module path is provided** (e.g. `src/pipecat/audio/vad/vad_analyzer.py`):
+   - Use that file directly
+
+   **If a class name is provided** (e.g. `VADAnalyzer`):
+   - Search for `class ClassName` in `src/pipecat/`
+   - If multiple files contain that class name, list all matches with their file paths, ask the user which one they want to document, and wait for confirmation
+
+2. Once the file is identified, read the module to understand its structure:
+   - Identify all classes, functions, and important type aliases
+   - Understand the purpose of each component
+
+4. Apply documentation in this order:
+   - Module docstring (at top, after imports)
+   - Class docstrings
+   - `__init__` methods (always document constructor parameters)
+   - Public methods (not starting with `_`)
+   - Dataclass/config classes with field descriptions
+
+5. Skip documentation for:
+   - Private methods (starting with `_`)
+   - Simple dunder methods (`__str__`, `__repr__`, `__post_init__`)
+   - Very simple pass-through properties
+   - **Already documented code** - If a class, method, or function already has a complete docstring that follows the project style, do not modify it. A docstring is complete if it has:
+     - A one-line summary
+     - Args section (if it has parameters)
+     - Returns section (if it returns something meaningful)
+   - Only add or improve documentation where it is missing or incomplete
+
+## Module Docstring Format
+
+```python
+"""[One-line description of module purpose].
+
+[Optional: Longer explanation of functionality, key classes, or use cases.]
+"""
+```
+
+Example:
+```python
+"""Neuphonic text-to-speech service implementations.
+
+This module provides WebSocket and HTTP-based integrations with Neuphonic's
+text-to-speech API for real-time audio synthesis.
+"""
+```
+
+## Class Docstring Format
+
+```python
+class ClassName:
+    """One-line summary describing what the class does.
+
+    [Longer description explaining purpose, behavior, and key features.
+    Use action-oriented language.]
+
+    [Optional: Event handlers, usage notes, or important caveats.]
+    """
+```
+
+Example:
+```python
+class FrameProcessor(BaseObject):
+    """Base class for all frame processors in the pipeline.
+
+    Frame processors are the building blocks of Pipecat pipelines, they can be
+    linked to form complex processing pipelines. They receive frames, process
+    them, and pass them to the next or previous processor in the chain.
+
+    Event handlers available:
+
+    - on_before_process_frame: Called before a frame is processed
+    - on_after_process_frame: Called after a frame is processed
+
+    Example::
+
+        @processor.event_handler("on_before_process_frame")
+        async def on_before_process_frame(processor, frame):
+            ...
+
+        @processor.event_handler("on_after_process_frame")
+        async def on_after_process_frame(processor, frame):
+            ...
+    """
+```
+
+Note: When listing event handlers, do NOT use backticks. Include an `Example::` section (with double colon for Sphinx) showing the decorator pattern and function signature for each event.
+
+## Constructor (`__init__`) Format
+
+```python
+def __init__(self, *, param1: Type, param2: Type = default, **kwargs):
+    """Initialize the [ClassName].
+
+    Args:
+        param1: Description of param1 and its purpose.
+        param2: Description of param2. Defaults to [default].
+        **kwargs: Additional arguments passed to parent class.
+    """
+```
+
+Example:
+```python
+def __init__(
+    self,
+    *,
+    api_key: str,
+    voice_id: Optional[str] = None,
+    sample_rate: Optional[int] = 22050,
+    **kwargs,
+):
+    """Initialize the Neuphonic TTS service.
+
+    Args:
+        api_key: Neuphonic API key for authentication.
+        voice_id: ID of the voice to use for synthesis.
+        sample_rate: Audio sample rate in Hz. Defaults to 22050.
+        **kwargs: Additional arguments passed to parent InterruptibleTTSService.
+    """
+```
+
+## Method Docstring Format
+
+```python
+async def method_name(self, param1: Type) -> ReturnType:
+    """One-line summary of what method does.
+
+    [Longer description if behavior isn't obvious.]
+
+    Args:
+        param1: Description of param1.
+
+    Returns:
+        Description of return value.
+
+    Raises:
+        ExceptionType: When this exception is raised.
+    """
+```
+
+Example:
+```python
+async def put(self, item: Tuple[Frame, FrameDirection, FrameCallback]):
+    """Put an item into the priority queue.
+
+    System frames (`SystemFrame`) have higher priority than any other
+    frames. If a non-frame item is provided it will have the highest priority.
+
+    Args:
+        item: The item to enqueue.
+    """
+```
+
+## Dataclass/Config Format
+
+```python
+@dataclass
+class ConfigName:
+    """One-line description of configuration.
+
+    [Explanation of when/how to use this config.]
+
+    Parameters:
+        field1: Description of field1.
+        field2: Description of field2. Defaults to [default].
+    """
+
+    field1: Type
+    field2: Type = default_value
+```
+
+Example:
+```python
+@dataclass
+class FrameProcessorSetup:
+    """Configuration parameters for frame processor initialization.
+
+    Parameters:
+        clock: The clock instance for timing operations.
+        task_manager: The task manager for handling async operations.
+        observer: Optional observer for monitoring frame processing events.
+    """
+
+    clock: BaseClock
+    task_manager: BaseTaskManager
+    observer: Optional[BaseObserver] = None
+```
+
+## Enum Documentation Format
+
+```python
+class EnumName(Enum):
+    """One-line description of the enum purpose.
+
+    [Longer description of how the enum is used.]
+
+    Parameters:
+        VALUE1: Description of VALUE1.
+        VALUE2: Description of VALUE2.
+    """
+
+    VALUE1 = 1
+    VALUE2 = 2
+```
+
+## Writing Style Guidelines
+
+- **Concise and professional** - No casual language or filler words
+- **Action-oriented** - Start with verbs: "Processes...", "Manages...", "Converts..."
+- **Purpose before implementation** - Explain WHY before HOW
+- **Clear parameter descriptions** - Include type hints, defaults, and purpose
+- **No redundant type info** - Type hints are in the signature, don't repeat in description
+- **Use backticks for code references** - Wrap class names, method names, event names, parameter names, and code snippets in backticks
+
+Good: "Neuphonic API key for authentication."
+Bad: "str: The API key (string) that is used for authenticating with Neuphonic."
+
+Good: "Triggers `on_speech_started` when the `VADAnalyzer` detects speech."
+Bad: "Triggers on_speech_started when the VADAnalyzer detects speech."
+
+## Deprecation Notice Format
+
+When documenting deprecated code:
+
+```python
+"""[Description].
+
+.. deprecated:: X.X.X
+    `ClassName` is deprecated and will be removed in a future version.
+    Use `NewClassName` instead.
+"""
+```
+
+## Checklist
+
+Before finishing, verify:
+
+- [ ] Module has a docstring at the top (after copyright header and imports)
+- [ ] All public classes have docstrings
+- [ ] All `__init__` methods document their parameters
+- [ ] All public methods have docstrings with Args/Returns/Raises as needed
+- [ ] Dataclasses use "Parameters:" section for field descriptions
+- [ ] Enums document each value in "Parameters:" section
+- [ ] Writing is concise and action-oriented
+- [ ] No documentation added to private methods (starting with `_`)
+- [ ] Existing complete docstrings were left unchanged

.claude/skills/pr-description/SKILL.md

@@ -0,0 +1,128 @@
+---
+name: pr-description
+description: Update a GitHub PR description with a summary of changes
+---
+
+Update a GitHub pull request description based on the changes in the PR.
+
+## Arguments
+
+```
+/pr-description <PR_NUMBER> [--fixes <ISSUE_NUMBERS>]
+```
+
+- `PR_NUMBER` (required): The pull request number to update
+- `--fixes` (optional): Comma-separated issue numbers that this PR fixes (e.g., `--fixes 123,456`)
+
+Examples:
+- `/pr-description 3534`
+- `/pr-description 3534 --fixes 123`
+- `/pr-description 3534 --fixes 123,456,789`
+
+## Instructions
+
+1. First, gather information about the PR:
+   - Use GitHub plugin to get PR details (title, current description, base branch)
+   - Use local git to get commits: `git log main..HEAD --oneline`
+   - Use local git to get the diff: `git diff main..HEAD`
+   - Parse any `--fixes` argument for issue numbers
+
+2. Check the existing PR description:
+   - If it already has a complete, accurate description that reflects the changes, do nothing
+   - If it's missing sections, incomplete, or outdated compared to the actual changes, proceed to update
+   - If it only has the template placeholder text, generate a full description
+
+3. Analyze the changes:
+   - Understand the purpose of each commit
+   - Identify any breaking changes (API changes, removed features, behavior changes)
+   - Look for new features, bug fixes, refactoring, or documentation changes
+   - Collect issue numbers from:
+     - The `--fixes` argument (if provided)
+     - Commit messages (patterns like "Fixes #123", "Closes #456", "Resolves #789")
+
+4. Generate or update the PR description with these sections:
+
+## PR Description Format
+
+### Summary (always include)
+
+Brief bullet points describing what changed and why. Focus on the *purpose* and *impact*, not implementation details.
+
+```markdown
+## Summary
+
+- Added X to enable Y
+- Fixed bug where Z would happen
+- Refactored W for better maintainability
+```
+
+### Breaking Changes (include only if applicable)
+
+Document any changes that affect existing users or APIs.
+
+```markdown
+## Breaking Changes
+
+- `ClassName.method()` now requires a `param` argument
+- Removed deprecated `old_function()` - use `new_function()` instead
+```
+
+### Testing (include when non-obvious)
+
+How to verify the changes work. Skip for trivial changes.
+
+```markdown
+## Testing
+
+- Run `uv run pytest tests/test_feature.py` to verify the fix
+- Example usage: `uv run examples/new_feature.py`
+```
+
+### Fixes (include if issues are provided or found in commits)
+
+List issues this PR fixes. GitHub will automatically close these issues when the PR is merged.
+
+```markdown
+## Fixes
+
+- Fixes #123
+- Fixes #456
+```
+
+Note: Use "Fixes #X" format (not "Closes" or "Resolves") for consistency. Each issue should be on its own line with "Fixes" to ensure GitHub auto-closes them.
+
+## Guidelines
+
+- **Be concise** - Reviewers should understand the PR in 30 seconds
+- **Focus on why** - The diff shows *what* changed, explain *why*
+- **Skip empty sections** - Only include sections that have content
+- **Use bullet points** - Easier to scan than paragraphs
+- **Don't duplicate the diff** - Avoid listing every file or line changed
+
+## Example Output
+
+```markdown
+## Summary
+
+- Added `/docstring` skill for documenting Python modules with Google-style docstrings
+- Skill finds classes by name and handles conflicts when multiple matches exist
+- Skips already-documented code to avoid unnecessary changes
+
+## Testing
+
+/docstring ClassName
+
+## Fixes
+
+- Fixes #123
+```
+
+## Checklist
+
+Before updating the PR:
+
+- [ ] Verified existing description needs updating (not already complete)
+- [ ] Summary accurately reflects the changes
+- [ ] Breaking changes are clearly documented (if any)
+- [ ] No unnecessary sections included
+- [ ] Description is concise and scannable

.claude/skills/pr-submit/SKILL.md

@@ -0,0 +1,28 @@
+---
+name: pr-submit
+description: Create and submit a GitHub PR from the current branch
+---
+
+Submit the current changes as a GitHub pull request.
+
+## Instructions
+
+1. Check the current state of the repository:
+   - Run `git status` to see staged, unstaged, and untracked changes
+   - Run `git diff` to see current changes
+   - Run `git log --oneline -10` to see recent commits
+
+2. If there are uncommitted changes relevant to the PR:
+   - Ask the user if they want a specific prefix for the branch name (e.g., `alice/`, `fix/`, `feat/`)
+   - Create a new branch based on the current branch
+   - Commit the changes using multiple commits if the changes are unrelated
+
+3. Push the branch and create the PR:
+   - Push with `-u` flag to set upstream tracking
+   - Create the PR using `gh pr create`
+
+4. After the PR is created:
+   - Run `/changelog <pr_number>` to generate changelog files, then commit and push them
+   - Run `/pr-description <pr_number>` to update the PR description
+
+5. Return the PR URL to the user.

.claude/skills/update-docs/SKILL.md

@@ -0,0 +1,306 @@
+---
+name: update-docs
+description: Update documentation pages to match source code changes on the current branch
+---
+
+Update documentation pages to reflect source code changes on the current branch. Analyzes the diff against main, maps changed source files to their corresponding doc pages, and makes targeted edits.
+
+## Arguments
+
+```
+/update-docs [DOCS_PATH]
+```
+
+- `DOCS_PATH` (optional): Path to the docs repository root. If not provided, ask the user.
+
+Examples:
+- `/update-docs /Users/me/src/docs`
+- `/update-docs`
+
+## Instructions
+
+### Step 1: Resolve docs path
+
+If `DOCS_PATH` was provided as an argument, use it. Otherwise, ask the user for the path to their docs repository.
+
+Verify the path exists and contains `server/services/` subdirectory.
+
+### Step 2: Create docs branch
+
+Get the current pipecat branch name:
+```bash
+git rev-parse --abbrev-ref HEAD
+```
+
+In the docs repo, create a new branch off main with a matching name:
+```bash
+cd DOCS_PATH && git checkout main && git pull && git checkout -b {branch-name}-docs
+```
+
+For example, if the pipecat branch is `feat/new-service`, the docs branch becomes `feat/new-service-docs`.
+
+All doc edits in subsequent steps are made on this branch.
+
+### Step 3: Detect changed source files
+
+Run:
+```bash
+git diff main..HEAD --name-only
+```
+
+Filter to files that could affect documentation:
+- `src/pipecat/services/**/*.py` (service implementations)
+- `src/pipecat/transports/**/*.py` (transport implementations)
+- `src/pipecat/serializers/**/*.py` (serializer implementations)
+- `src/pipecat/processors/**/*.py` (processor implementations)
+- `src/pipecat/audio/**/*.py` (audio utilities)
+- `src/pipecat/turns/**/*.py` (turn management)
+- `src/pipecat/observers/**/*.py` (observers)
+- `src/pipecat/pipeline/**/*.py` (pipeline core)
+
+Ignore `__init__.py`, `__pycache__`, test files, and files that only contain type re-exports.
+
+### Step 4: Map source files to doc pages
+
+For each changed source file, find the corresponding doc page. Read the mapping file at `.claude/skills/update-docs/SOURCE_DOC_MAPPING.md` and apply its tiered lookup: tier 1 (known exceptions) → tier 2 (pattern matching) → tier 3 (search fallback). **First match wins.**
+
+### Step 5: Analyze each source-doc pair
+
+For each mapped pair:
+
+1. **Read the full source file** to understand current state
+2. **Read the diff** for that file: `git diff main..HEAD -- <source_file>`
+3. **Read the current doc page** in full
+
+Identify what changed by comparing source to docs:
+
+- **Constructor parameters**: Compare `__init__` signature to the Configuration section's `<ParamField>` entries
+- **InputParams fields**: Compare `InputParams(BaseModel)` class fields to the InputParams table
+- **Event handlers**: Compare `_register_event_handler` calls and event handler definitions to Event Handlers section
+- **Class names / imports**: Check if Usage examples reference correct names
+- **Behavioral changes**: Check if Notes section needs updating
+
+### Step 6: Make targeted edits
+
+For each doc page that needs updates, edit **only the sections that need changes**. Preserve all other content exactly as-is.
+
+#### Rules
+
+- **Never remove content** unless the corresponding source code was removed
+- **Never rewrite sections** that are already accurate
+- **Match existing formatting** — if the page uses `<ParamField>` tags, use them; if it uses tables, use tables
+- **Keep descriptions concise** — match the tone and length of surrounding content
+- **Preserve CardGroup, links, and examples** unless they reference removed functionality
+- **Don't touch frontmatter** unless the class was renamed
+
+#### Section-specific guidance
+
+**Configuration** (constructor params):
+- Use `<ParamField path="name" type="type" default="value">` format if the page already uses it
+- Add new params in logical order (required first, then optional)
+- Remove params that no longer exist in source
+- Update types/defaults that changed
+
+**InputParams** (runtime settings):
+- Use markdown table format: `| Parameter | Type | Default | Description |`
+- Match the field names and types from the `InputParams(BaseModel)` class
+- Include the default values from the source
+
+**Usage** (code examples):
+- Update import paths, class names, and parameter names
+- Only modify examples if they would break or be misleading with the new API
+- Don't rewrite working examples just to add new optional params
+
+**Notes**:
+- Add notes for new behavioral gotchas or breaking changes
+- Remove notes about limitations that were fixed
+- Keep existing notes that are still accurate
+
+**Event Handlers**:
+- Update the event table and example code
+- Add new events, remove deleted ones
+- Update handler signatures if they changed
+
+**Overview / Key Features / Prerequisites**:
+- Only update if the PR fundamentally changes what the service does (new capability, removed capability, renamed class)
+- Most PRs will NOT need changes to these sections
+
+### Step 7: Update guides
+
+Guides at `DOCS_PATH/guides/` reference specific class names, parameters, imports, and code patterns. After completing reference doc edits, check if any guides need updates too.
+
+For each changed source file, collect the class names, renamed parameters, and changed imports from the diff. Search the guides directory:
+```bash
+grep -rl "ClassName\|old_param_name" DOCS_PATH/guides/
+```
+
+For each guide that references changed code:
+1. Read the full guide
+2. Update class names, parameter names, import paths, and code examples that are now incorrect
+3. **Don't rewrite prose** — only fix the specific references that changed
+4. Leave guides alone if they reference the service generally but don't use any changed APIs
+
+Guide directories:
+- `guides/learn/` — conceptual tutorials (pipeline, LLM, STT, TTS, etc.)
+- `guides/fundamentals/` — practical how-tos (metrics, recording, transcripts, etc.)
+- `guides/features/` — feature-specific guides (Gemini Live, OpenAI audio, WhatsApp, etc.)
+- `guides/telephony/` — telephony integration guides (Twilio, Plivo, Telnyx, etc.)
+
+### Step 8: Identify doc gaps
+
+After processing all mapped pairs, check for two kinds of gaps:
+
+**Missing pages**: Source files that had no doc page mapping (neither tier 1, 2, nor 3) and are not marked as "(skip)". For each, tell the user:
+- The source file path
+- The main class(es) it defines
+- Whether a new doc page should be created
+
+**Missing sections**: Mapped doc pages that are missing standard sections compared to the source. For example, a transport page with no Configuration section, or a service page with no InputParams table when the source defines `InputParams(BaseModel)`. Flag these and offer to add the missing sections.
+
+If the user wants a new page, do all three of the following:
+
+#### 8a: Create the doc page
+
+Create the new `.mdx` file using this template structure:
+```
+---
+title: "Service Name"
+description: "Brief description"
+---
+
+## Overview
+
+[Description from class docstring or source analysis]
+
+<CardGroup cols={2}>
+  [Cards for API reference and examples if available]
+</CardGroup>
+
+## Installation
+
+```bash
+pip install "pipecat-ai[package-name]"
+```
+
+## Prerequisites
+
+[Environment variables and account setup]
+
+## Configuration
+
+[ParamField entries for constructor params]
+
+## InputParams
+
+[Table of InputParams fields, if the service has them]
+
+## Usage
+
+### Basic Setup
+
+```python
+[Minimal working example]
+```
+
+## Notes
+
+[Important caveats]
+
+## Event Handlers
+
+[Event table and example code]
+```
+
+#### 8b: Add to docs.json
+
+Add the new page path to `DOCS_PATH/docs.json` in the correct navigation group. The path format is `server/services/{category}/{provider}` (without the `.mdx` extension).
+
+Find the matching group in the navigation structure:
+- **STT** → `"group": "Speech-to-Text"` under Services
+- **TTS** → `"group": "Text-to-Speech"` under Services
+- **LLM** → `"group": "LLM"` under Services
+- **S2S** → `"group": "Speech-to-Speech"` under Services
+- **Transport** → `"group": "Transport"` under Services
+- **Serializer** → `"group": "Serializers"` under Services
+- **Image generation** → `"group": "Image Generation"` under Services
+- **Video** → `"group": "Video"` under Services
+- **Memory** → `"group": "Memory"` under Services
+- **Vision** → `"group": "Vision"` under Services
+- **Analytics** → `"group": "Analytics & Monitoring"` under Services
+
+Insert the new entry **alphabetically** within the group's `pages` array. For example, adding a new STT service "foo":
+```json
+{
+  "group": "Speech-to-Text",
+  "pages": [
+    "server/services/stt/assemblyai",
+    "server/services/stt/aws",
+    ...
+    "server/services/stt/foo",
+    ...
+  ]
+}
+```
+
+#### 8c: Add to supported-services.mdx
+
+Add a new row to the correct category table in `DOCS_PATH/server/services/supported-services.mdx`.
+
+Use this format:
+```
+| [DisplayName](/server/services/{category}/{provider}) | `pip install "pipecat-ai[package]"` |
+```
+
+To determine the correct values:
+- **DisplayName**: Use the service's human-readable name (e.g., "ElevenLabs", "AWS Polly", "Google Gemini")
+- **package**: Look at the service's `pyproject.toml` extras or the import pattern in the source code. For example, if the service is in `src/pipecat/services/foo/`, the package is typically `foo`.
+- If no pip dependencies are required, use `No dependencies required` instead.
+
+Insert the new row **alphabetically** within the table. Match the column alignment of the existing rows.
+
+### Step 9: Output summary
+
+After all edits are complete, print a summary:
+
+```
+## Documentation Updates
+
+### Updated reference pages
+- `server/services/stt/deepgram.mdx` — Updated Configuration (added `new_param`), InputParams (updated `language` default)
+- `server/services/tts/elevenlabs.mdx` — Updated Event Handlers (added `on_connected`)
+
+### Updated guides
+- `guides/learn/speech-to-text.mdx` — Updated code example (renamed `old_param` → `new_param`)
+
+### New service pages
+- `server/services/tts/newprovider.mdx` — Created page, added to docs.json (Text-to-Speech), added to supported-services.mdx
+
+### Unmapped source files
+- `src/pipecat/services/newprovider/tts.py` — NewProviderTTSService (no doc page exists)
+
+### Skipped files
+- `src/pipecat/services/ai_service.py` — internal base class
+```
+
+## Guidelines
+
+- **Be conservative** — only change what the diff warrants. Don't "improve" docs beyond what changed in source.
+- **Read before editing** — always read the full doc page before making changes so you understand the existing structure.
+- **Preserve voice** — match the writing style of the existing doc page, don't impose a different tone.
+- **One PR at a time** — this skill operates on the current branch's diff against main. Don't look at other branches.
+- **Parallel analysis** — when multiple source files map to different doc pages, analyze and edit them in parallel for efficiency.
+- **Shared source files** — files like `services/google/google.py` are shared bases. Check which services import from them and update all affected doc pages.
+
+## Checklist
+
+Before finishing, verify:
+
+- [ ] All changed source files were checked against the mapping table
+- [ ] Each doc page edit matches the actual source code change (not guessed)
+- [ ] No content was removed unless the corresponding source was removed
+- [ ] New parameters have accurate types and defaults from source
+- [ ] Formatting matches the existing page style
+- [ ] Guides referencing changed APIs were checked and updated
+- [ ] New service pages were added to `docs.json` in the correct group, alphabetically
+- [ ] New service pages were added to `supported-services.mdx` in the correct table, alphabetically
+- [ ] Unmapped files were reported to the user

.claude/skills/update-docs/SOURCE_DOC_MAPPING.md

@@ -0,0 +1,79 @@
+# Source-to-Doc Mapping
+
+Maps pipecat source files to their documentation pages. Source paths are relative to `src/pipecat/`. Doc paths are relative to `DOCS_PATH`.
+
+## Name mismatches
+
+These source paths don't follow the standard `services/{provider}/{type}.py` → `server/services/{type}/{provider}.mdx` pattern.
+
+| Source path | Doc page |
+|---|---|
+| `services/google/llm.py` | `server/services/llm/gemini.mdx` |
+| `services/google/llm_vertex.py` | `server/services/llm/google-vertex.mdx` |
+| `services/google/google.py` | (shared base — check which services use it) |
+| `services/google/gemini_live/**` | `server/services/s2s/gemini-live.mdx` |
+| `services/google/gemini_live/llm_vertex.py` | `server/services/s2s/gemini-live-vertex.mdx` |
+| `services/aws_nova_sonic/**` | `server/services/s2s/aws.mdx` |
+| `services/ultravox/**` | `server/services/s2s/ultravox.mdx` |
+| `services/grok/realtime/**` | `server/services/s2s/grok.mdx` |
+| `services/openai/realtime/**` | `server/services/s2s/openai.mdx` |
+| `processors/frameworks/rtvi.py` | `server/frameworks/rtvi/rtvi-processor.mdx` and `server/frameworks/rtvi/rtvi-observer.mdx` |
+| `processors/transcript_processor.py` | `server/utilities/transcript-processor.mdx` |
+| `processors/user_idle_processor.py` | `server/utilities/user-idle-processor.mdx` |
+| `processors/idle_frame_processor.py` | `server/pipeline/pipeline-idle-detection.mdx` |
+| `pipeline/task.py` | `server/pipeline/pipeline-task.mdx` |
+| `pipeline/runner.py` | `server/utilities/runner/guide.mdx` |
+| `transports/base_transport.py` | `server/services/transport/transport-params.mdx` |
+
+## Skip list
+
+These files should never trigger doc updates.
+
+| Pattern | Reason |
+|---|---|
+| `services/ai_service.py` | Internal base class |
+| `services/stt_service.py` | Internal base class |
+| `services/tts_service.py` | Internal base class |
+| `services/llm_service.py` | Internal base class |
+| `services/websocket_service.py` | Internal base class |
+| `services/openai_realtime_beta/**` | Deprecated |
+| `services/openai_realtime/**` | Deprecated |
+| `services/gemini_multimodal_live/**` | Deprecated |
+| `services/aws/agent_core.py` | Internal |
+| `services/aws/sagemaker/**` | No doc page |
+| `transports/base_input.py` | Internal base class |
+| `transports/base_output.py` | Internal base class |
+| `transports/websocket/client.py` | No doc page |
+| `serializers/base_serializer.py` | Internal base class |
+| `serializers/protobuf.py` | Internal |
+| `processors/audio/**` | Internal |
+| `pipeline/pipeline.py` | Core architecture, not a service doc |
+
+## Pattern matching
+
+For files not in the tables above, apply these patterns. Convert underscores to hyphens in provider names for doc filenames.
+
+| Source pattern | Doc pattern |
+|---|---|
+| `services/{provider}/stt*.py` | `server/services/stt/{provider}.mdx` |
+| `services/{provider}/tts*.py` | `server/services/tts/{provider}.mdx` |
+| `services/{provider}/llm*.py` | `server/services/llm/{provider}.mdx` |
+| `services/{provider}/image*.py` | `server/services/image-generation/{provider}.mdx` |
+| `services/{provider}/video*.py` | `server/services/video/{provider}.mdx` |
+| `services/{provider}/realtime/**` | `server/services/s2s/{provider}.mdx` |
+| `transports/{name}/**` | `server/services/transport/{name}.mdx` |
+| `serializers/{name}.py` | `server/services/serializers/{name}.mdx` |
+| `observers/**` | `server/utilities/observers/` (match by class name) |
+| `audio/vad/**` | `server/utilities/audio/` (match by class name) |
+| `audio/filters/**` | `server/utilities/audio/` (match by class name) |
+| `audio/mixers/**` | `server/utilities/audio/` (match by class name) |
+| `processors/filters/**` | `server/utilities/filters/` (match by class name) |
+
+If the doc file doesn't exist at the resolved path, the file is **unmapped**.
+
+## Search fallback
+
+For files that don't match any table or pattern above:
+1. Extract the main class name(s) from the source file
+2. Search the docs directory for that class name: `grep -r "ClassName" DOCS_PATH/server/`
+3. If found in a doc page, use that as the mapping

.github/workflows/build.yaml

@@ -21,20 +21,20 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      
+
       - name: Install uv
         uses: astral-sh/setup-uv@v3
         with:
           version: "latest"
-      
+
       - name: Set up Python
-        run: uv python install 3.10
-      
+        run: uv python install 3.12
+
       - name: Install development dependencies
         run: uv sync --group dev
-      
+
       - name: Build project
         run: uv build
-      
+
       - name: Install project in editable mode
-        run: uv pip install --editable .
+        run: uv pip install --editable .

.github/workflows/coverage.yaml

@@ -29,11 +29,22 @@ jobs:
 
       - name: Install system packages
         run: |
+          sudo apt-get update
           sudo apt-get install -y portaudio19-dev
 
       - name: Install dependencies
         run: |
-          uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
+          uv sync --group dev \
+            --extra anthropic \
+            --extra aws \
+            --extra deepgram \
+            --extra google \
+            --extra langchain \
+            --extra livekit \
+            --extra piper \
+            --extra sagemaker \
+            --extra tracing \
+            --extra websocket
 
       - name: Run tests with coverage
         run: |

.github/workflows/format.yaml

@@ -22,22 +22,22 @@ jobs:
     steps:
       - name: Checkout repo
         uses: actions/checkout@v4
-      
+
       - name: Install uv
         uses: astral-sh/setup-uv@v3
         with:
           version: "latest"
-      
+
       - name: Set up Python
-        run: uv python install 3.10
-      
+        run: uv python install 3.12
+
       - name: Install development dependencies
         run: uv sync --group dev
-      
+
       - name: Ruff formatter
         id: ruff-format
         run: uv run ruff format --diff
-      
+
       - name: Ruff linter (all rules)
         id: ruff-check
-        run: uv run ruff check
+        run: uv run ruff check

.github/workflows/generate-changelog.yml

@@ -0,0 +1,174 @@
+name: Generate Changelog for Release
+
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: "Release version (e.g., 0.0.97)"
+        required: true
+        type: string
+      date:
+        description: "Release date (YYYY-MM-DD format, defaults to today)"
+        required: false
+        type: string
+        default: ""
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  generate-changelog:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Install dependencies
+        run: |
+          uv sync --group dev
+
+      - name: Set release date
+        id: set_date
+        run: |
+          if [ -z "${{ inputs.date }}" ]; then
+            RELEASE_DATE=$(date +%Y-%m-%d)
+            echo "Using today's date: $RELEASE_DATE"
+          else
+            RELEASE_DATE="${{ inputs.date }}"
+            echo "Using provided date: $RELEASE_DATE"
+          fi
+          echo "release_date=$RELEASE_DATE" >> $GITHUB_OUTPUT
+
+      - name: Validate inputs
+        run: |
+          # Validate version format (basic check)
+          if ! [[ "${{ inputs.version }}" =~ ^[0-9]+\.[0-9]+\.[0-9]+.*$ ]]; then
+            echo "Error: Version must be in format X.Y.Z (e.g., 0.0.97)"
+            exit 1
+          fi
+
+          # Validate date format if provided
+          if [ -n "${{ inputs.date }}" ]; then
+            if ! date -d "${{ inputs.date }}" >/dev/null 2>&1; then
+              # Try macOS date format
+              if ! date -j -f "%Y-%m-%d" "${{ inputs.date }}" >/dev/null 2>&1; then
+                echo "Error: Date must be in YYYY-MM-DD format (e.g., 2025-12-04)"
+                exit 1
+              fi
+            fi
+          fi
+
+      - name: Check for changelog fragments
+        id: check_fragments
+        run: |
+          FRAGMENT_COUNT=$(find changelog -name "*.md" ! -name "_template.md.j2" | wc -l | tr -d ' ')
+          echo "fragment_count=$FRAGMENT_COUNT" >> $GITHUB_OUTPUT
+
+          if [ "$FRAGMENT_COUNT" -eq "0" ]; then
+            echo "❌ Error: No changelog fragments found in changelog/"
+            echo ""
+            echo "Cannot create a release without changelog entries."
+            echo "Add changelog fragments to the changelog/ directory (e.g., 1234.added.md) and try again."
+            exit 1
+          fi
+
+          # Validate fragment types
+          VALID_TYPES="added changed deprecated removed fixed performance security other"
+          INVALID_FRAGMENTS=""
+
+          for file in changelog/*.md; do
+            # Skip template
+            if [[ "$file" == "changelog/_template.md.j2" ]]; then
+              continue
+            fi
+            
+            # Extract type from filename (e.g., 1234.added.md -> added)
+            filename=$(basename "$file")
+            # Handle both 1234.added.md and 1234.added.2.md patterns
+            type=$(echo "$filename" | sed -E 's/^[0-9]+\.([a-z]+)(\.[0-9]+)?\.md$/\1/')
+            
+            # Check if type is valid
+            if ! echo "$VALID_TYPES" | grep -wq "$type"; then
+              INVALID_FRAGMENTS="$INVALID_FRAGMENTS\n  - $filename (type: '$type')"
+            fi
+          done
+
+          if [ -n "$INVALID_FRAGMENTS" ]; then
+            echo "❌ Error: Invalid changelog fragment types found:"
+            echo -e "$INVALID_FRAGMENTS"
+            echo ""
+            echo "Valid types are: $VALID_TYPES"
+            echo "Example: 1234.added.md, 5678.fixed.md"
+            exit 1
+          fi
+
+          echo "✓ Found $FRAGMENT_COUNT changelog fragment(s)"
+          echo "has_fragments=true" >> $GITHUB_OUTPUT
+
+      - name: Preview changelog
+        run: |
+          echo "## Preview of changelog for version ${{ inputs.version }}"
+          echo ""
+          uv run towncrier build --draft --version "${{ inputs.version }}" --date "${{ steps.set_date.outputs.release_date }}"
+
+      - name: Build changelog
+        run: |
+          uv run towncrier build --version "${{ inputs.version }}" --date "${{ steps.set_date.outputs.release_date }}" --yes
+
+      - name: Create Pull Request
+        uses: peter-evans/create-pull-request@v7
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: "Update changelog for version ${{ inputs.version }}"
+          title: "Release ${{ inputs.version }} - Changelog Update"
+          body: |
+            ## Changelog Update for Release ${{ inputs.version }}
+
+            This PR updates the CHANGELOG.md with all changes for version **${{ inputs.version }}**.
+
+            ### Summary
+            - **Version:** ${{ inputs.version }}
+            - **Date:** ${{ steps.set_date.outputs.release_date }}
+            - **Fragments processed:** ${{ steps.check_fragments.outputs.fragment_count }}
+
+            ### What this PR does
+            - ✅ Adds new release section to CHANGELOG.md
+            - ✅ Removes processed changelog fragments
+            - ✅ Ready to merge for release
+
+            ### Next Steps
+            1. Review the changelog entries below
+            2. Make any necessary edits to CHANGELOG.md if needed
+            3. Merge this PR
+            4. Continue with your release process
+
+            ---
+
+            <details>
+            <summary>📋 Preview of changes</summary>
+
+            The changelog has been updated with entries from the following fragments:
+
+            ```bash
+            ${{ steps.check_fragments.outputs.fragment_count }} fragments processed
+            ```
+
+            </details>
+          branch: changelog-${{ inputs.version }}
+          delete-branch: true
+          labels: |
+            changelog
+            release

.github/workflows/python-compatibility.yaml

@@ -14,7 +14,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ['3.10.18', '3.11.13', '3.12.11', '3.13.5']
+        python-version: ['3.10.19', '3.11.14', '3.12.12', '3.13.12']
 
     name: Python ${{ matrix.python-version }}
     steps:
@@ -40,21 +40,10 @@ jobs:
           uv python install ${{ matrix.python-version }}
           uv python pin ${{ matrix.python-version }}
 
-      - name: Test uv sync with all extras (Python < 3.13)
-        if: "!startsWith(matrix.python-version, '3.13.')"
+      - name: Test uv sync with all extras
         run: |
           uv sync --group dev --all-extras --no-extra krisp
 
-      - name: Test uv sync without PyTorch extras (Python 3.13+)
-        if: startsWith(matrix.python-version, '3.13.')
-        run: |
-          uv sync --group dev --all-extras \
-            --no-extra krisp \
-            --no-extra ultravox \
-            --no-extra local-smart-turn \
-            --no-extra moondream \
-            --no-extra mlx-whisper
-
       - name: Verify installation
         run: |
           uv run python --version

.github/workflows/tests.yaml

@@ -33,11 +33,22 @@ jobs:
 
       - name: Install system packages
         run: |
+          sudo apt-get update
           sudo apt-get install -y portaudio19-dev
 
       - name: Install dependencies
         run: |
-          uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
+          uv sync --group dev \
+            --extra anthropic \
+            --extra aws \
+            --extra deepgram \
+            --extra google \
+            --extra langchain \
+            --extra livekit \
+            --extra piper \
+            --extra sagemaker \
+            --extra tracing \
+            --extra websocket
 
       - name: Test with pytest
         run: |

.github/workflows/update-docs.yml

@@ -0,0 +1,147 @@
+name: Update Documentation on PR Merge
+
+on:
+  pull_request_target:
+    types: [closed]
+    branches: [main]
+    paths:
+      - "src/pipecat/services/**"
+      - "src/pipecat/transports/**"
+      - "src/pipecat/serializers/**"
+      - "src/pipecat/processors/**"
+      - "src/pipecat/audio/**"
+      - "src/pipecat/turns/**"
+      - "src/pipecat/observers/**"
+      - "src/pipecat/pipeline/**"
+  workflow_dispatch:
+    inputs:
+      pr_number:
+        description: "PR number to generate docs for"
+        required: true
+        type: string
+
+jobs:
+  update-docs:
+    if: >-
+      github.event_name == 'workflow_dispatch' ||
+      github.event.pull_request.merged == true
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    permissions:
+      contents: read
+      pull-requests: read
+      id-token: write
+    steps:
+      - name: Checkout pipecat
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Checkout docs
+        uses: actions/checkout@v4
+        with:
+          repository: pipecat-ai/docs
+          token: ${{ secrets.DOCS_SYNC_TOKEN }}
+          path: _docs
+
+      - name: Resolve PR number
+        id: pr
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            echo "number=${{ inputs.pr_number }}" >> "$GITHUB_OUTPUT"
+          else
+            echo "number=${{ github.event.pull_request.number }}" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Update documentation
+        uses: anthropics/claude-code-action@v1
+        env:
+          DOCS_SYNC_TOKEN: ${{ secrets.DOCS_SYNC_TOKEN }}
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          prompt: |
+            You are updating documentation for the pipecat-ai/docs repository based on
+            changes merged in PR #${{ steps.pr.outputs.number }} of pipecat-ai/pipecat.
+
+            ## Setup
+
+            1. Read the skill instructions at `.claude/skills/update-docs/SKILL.md`
+            2. Read the source-to-doc mapping at `.claude/skills/update-docs/SOURCE_DOC_MAPPING.md`
+            3. The docs repository is checked out at `./_docs/`
+
+            ## Get the diff
+
+            Run `gh pr diff ${{ steps.pr.outputs.number }}` to see what changed in the PR.
+            Also run `gh pr diff ${{ steps.pr.outputs.number }} --name-only` to get the list of changed files.
+            Filter to source files matching the directories listed in SKILL.md Step 3.
+
+            If no relevant source files were changed, exit with "No documentation changes needed."
+
+            ## Follow the skill instructions
+
+            Apply the SKILL.md workflow (Steps 3-9) with these adaptations for automation:
+
+            ### Docs path
+            Use `./_docs/` — it's already checked out. Do not ask for a path.
+
+            ### Branch management
+            - Branch name: `docs/pr-${{ steps.pr.outputs.number }}`
+            - Work inside `./_docs/` for all doc edits and git operations
+            - Check if the branch already exists on the remote:
+              ```bash
+              cd _docs && git fetch origin docs/pr-${{ steps.pr.outputs.number }} 2>/dev/null
+              ```
+              - If it exists: check it out (supports workflow re-runs)
+              - If not: create it from main
+
+            ### Git config
+            Before committing in `_docs`, set:
+            ```bash
+            git config user.name "github-actions[bot]"
+            git config user.email "github-actions[bot]@users.noreply.github.com"
+            ```
+
+            ### No interactive questions
+            Do not ask questions. If you encounter gaps (unmapped files, missing sections,
+            ambiguous changes), note them in the PR body under "## Gaps identified".
+
+            ### Creating the docs PR
+            After committing all changes in `_docs`, push and create a PR:
+            ```bash
+            cd _docs
+            git push -u origin docs/pr-${{ steps.pr.outputs.number }}
+            GH_TOKEN=$DOCS_SYNC_TOKEN gh pr create \
+              --repo pipecat-ai/docs \
+              --label auto-docs \
+              --title "docs: update for pipecat PR #${{ steps.pr.outputs.number }}" \
+              --body "$(cat <<'BODY'
+            Automated documentation update for [pipecat PR #${{ steps.pr.outputs.number }}](https://github.com/pipecat-ai/pipecat/pull/${{ steps.pr.outputs.number }}).
+
+            ## Changes
+            <summarize each doc page updated and what changed>
+
+            ## Gaps identified
+            <any unmapped files, missing doc pages, or missing sections — or "None">
+            BODY
+            )"
+            ```
+
+            ### Re-run handling
+            If `gh pr create` fails because a PR from that branch already exists,
+            push the updated commits and use `gh pr edit` to update the body instead.
+
+            ### No-op
+            If after analyzing the diff you determine no documentation changes are needed
+            (e.g., only skip-listed files changed, or changes don't affect public API docs),
+            exit cleanly without creating a branch or PR. Output "No documentation changes needed."
+
+            ## Important rules
+            - Only modify files inside `./_docs/` — never modify pipecat source code
+            - Follow the conservative editing rules from SKILL.md Step 6
+            - Read each doc page fully before editing (SKILL.md Guidelines)
+            - Use `GH_TOKEN=$DOCS_SYNC_TOKEN` for all `gh` commands targeting pipecat-ai/docs
+          claude_args: |
+            --model claude-sonnet-4-5-20250929
+            --max-turns 30
+            --allowedTools "Read,Write,Edit,Glob,Grep,Bash"

.gitignore

@@ -4,7 +4,14 @@ __pycache__/
 *~
 venv
 .venv
-/.idea
+.idea
+.gradle
+.next
+next-env.d.ts
+local.properties
+*.log
+*.lock
+smart_turn_audio_log
 #*#
 
 # Distribution / Packaging
@@ -27,7 +34,7 @@ share/python-wheels/
 *.egg
 MANIFEST
 .DS_Store
-.env
+.env*
 fly.toml
 
 # Examples
@@ -51,4 +58,7 @@ docs/api/_build/
 docs/api/api
 
 # uv
-.python-version
+.python-version
+
+# Pipecat
+whisker_setup.py

.readthedocs.yaml

@@ -11,7 +11,7 @@ build:
   jobs:
     post_install:
       - pip install uv
-      - UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra ultravox --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
+      - UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
 
 sphinx:
   configuration: docs/api/conf.py

CLAUDE.md

@@ -0,0 +1,157 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+Pipecat is an open-source Python framework for building real-time voice and multimodal conversational AI agents. It orchestrates audio/video, AI services, transports, and conversation pipelines using a frame-based architecture.
+
+## Common Commands
+
+```bash
+# Setup development environment
+uv sync --group dev --all-extras --no-extra gstreamer --no-extra krisp
+
+# Install pre-commit hooks
+uv run pre-commit install
+
+# Run all tests
+uv run pytest
+
+# Run a single test file
+uv run pytest tests/test_name.py
+
+# Run a specific test
+uv run pytest tests/test_name.py::test_function_name
+
+# Preview changelog
+uv run towncrier build --draft --version Unreleased
+
+# Lint and format check
+uv run ruff check
+uv run ruff format --check
+
+# Update dependencies (after editing pyproject.toml)
+uv lock && uv sync
+```
+
+## Architecture
+
+### Frame-Based Pipeline Processing
+
+All data flows as **Frame** objects through a pipeline of **FrameProcessors**:
+
+```
+[Processor1] → [Processor2] → ... → [ProcessorN]
+```
+
+**Key components:**
+
+- **Frames** (`src/pipecat/frames/frames.py`): Data units (audio, text, video) and control signals. Flow DOWNSTREAM (input→output) or UPSTREAM (acknowledgments/errors).
+
+- **FrameProcessor** (`src/pipecat/processors/frame_processor.py`): Base processing unit. Each processor receives frames, processes them, and pushes results downstream.
+
+- **Pipeline** (`src/pipecat/pipeline/pipeline.py`): Chains processors together.
+
+- **ParallelPipeline** (`src/pipecat/pipeline/parallel_pipeline.py`): Runs multiple pipelines in parallel.
+
+- **Transports** (`src/pipecat/transports/`): Transports are frame processors used for external I/O layer (Daily WebRTC, LiveKit WebRTC, WebSocket, Local). Abstract interface via `BaseTransport`, `BaseInputTransport` and `BaseOutputTransport`.
+
+- **Pipeline Task (`src/pipecat/pipeline/task.py`)**: Runs and manages a pipeline. Pipeline tasks send the first frame, `StartFrame`, to the pipeline in order for processors to know they can start processing and pushing frames. Pipeline tasks internally create a pipeline with two additional processors, a source processor before the user-defined pipeline and a sink processor at the end. Those are used for multiple things: error handling, pipeline task level events, heartbeat monitoring, etc.
+
+- **Pipeline Runner (`src/pipecat/pipeline/runner.py`)**: High-level entry point for executing pipeline tasks. Handles signal management (SIGINT/SIGTERM) for graceful shutdown and optional garbage collection. Run a single pipeline task with `await runner.run(task)` or multiple concurrently with `await asyncio.gather(runner.run(task1), runner.run(task2))`.
+
+- **Services** (`src/pipecat/services/`): 60+ AI provider integrations (STT, TTS, LLM, etc.). Extend base classes: `AIService`, `LLMService`, `STTService`, `TTSService`, `VisionService`.
+
+- **Serializers** (`src/pipecat/serializers/`): Convert frames to/from wire formats for WebSocket transports. `FrameSerializer` base class defines `serialize()` and `deserialize()`. Telephony serializers (Twilio, Plivo, Vonage, Telnyx, Exotel, Genesys) handle provider-specific protocols and audio encoding (e.g., μ-law).
+
+- **RTVI** (`src/pipecat/processors/frameworks/rtvi.py`): Real-Time Voice Interface protocol bridging clients and the pipeline. `RTVIProcessor` handles incoming client messages (text input, audio, function call results). `RTVIObserver` converts pipeline frames to outgoing messages: user/bot speaking events, transcriptions, LLM/TTS lifecycle, function calls, metrics, and audio levels.
+
+- **Observers** (`src/pipecat/observers/`): Monitor frame flow without modifying the pipeline. Passed to `PipelineTask` via the `observers` parameter. Implement `on_process_frame()` and `on_push_frame()` callbacks.
+
+### Important Patterns
+
+- **Context Aggregation**: `LLMContext` accumulates messages for LLM calls; `UserResponse` aggregates user input
+
+- **Turn Management**: Turn management is done through `LLMUserAggregator` and
+  `LLMAssistantAggregator`, created with `LLMContextAggregatorPair`
+
+- **User turn strategies**: Detection of when the user starts and stops speaking is done via user turn start/stop strategies. They push `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` respectively.
+
+- **Interruptions**: Interruptions are usually triggered by a user turn start strategy (e.g. `VADUserTurnStartStrategy`) but they can be triggered by other processors as well, in which case the user turn start strategies don't need to. An `InterruptionFrame` carries an optional `asyncio.Event` that is set when the frame reaches the pipeline sink. If a processor stops an `InterruptionFrame` from propagating downstream (i.e., doesn't push it), it **must** call `frame.complete()` to avoid stalling `push_interruption_task_frame_and_wait()` callers.
+
+- **Uninterruptible Frames**: These are frames that will not be removed from internal queues even if there's an interruption. For example, `EndFrame` and `StopFrame`.
+
+- **Events**: Most classes in Pipecat have `BaseObject` as the very base class. `BaseObject` has support for events. Events can run in the background in an async task (default) or synchronously (`sync=True`) if we want immediate action. Synchronous event handlers need to execute fast.
+
+- **Async Task Management**: Always use `self.create_task(coroutine, name)` instead of raw `asyncio.create_task()`. The `TaskManager` automatically tracks tasks and cleans them up on processor shutdown. Use `await self.cancel_task(task, timeout)` for cancellation.
+
+- **Error Handling**: Use `await self.push_error(msg, exception, fatal)` to push errors upstream. Services should use `fatal=False` (the default) so application code can handle errors and take action (e.g. switch to another service).
+
+### Key Directories
+
+| Directory                  | Purpose                                            |
+| -------------------------- | -------------------------------------------------- |
+| `src/pipecat/frames/`      | Frame definitions (100+ types)                     |
+| `src/pipecat/processors/`  | FrameProcessor base + aggregators, filters, audio  |
+| `src/pipecat/pipeline/`    | Pipeline orchestration                             |
+| `src/pipecat/services/`    | AI service integrations (60+ providers)            |
+| `src/pipecat/transports/`  | Transport layer (Daily, LiveKit, WebSocket, Local) |
+| `src/pipecat/serializers/` | Frame serialization for WebSocket protocols        |
+| `src/pipecat/observers/`   | Pipeline observers for monitoring frame flow       |
+| `src/pipecat/audio/`       | VAD, filters, mixers, turn detection, DTMF         |
+| `src/pipecat/turns/`       | User turn management                               |
+
+## Code Style
+
+- **Docstrings**: Google-style. Classes describe purpose; `__init__` has `Args:` section; dataclasses use `Parameters:` section.
+- **Linting**: Ruff (line length 100). Pre-commit hooks enforce formatting.
+- **Type hints**: Required for complex async code.
+- **Dataclass vs Pydantic**: Use `@dataclass` for frames and internal pipeline data (high-frequency, no validation needed). Use Pydantic `BaseModel` for configuration, parameters, metrics, and external API data (benefits from validation and serialization). Specifically:
+  - `@dataclass`: Frame types, context aggregator pairs, internal data containers
+  - `BaseModel`: Service `InputParams`, transport/VAD/turn params, metrics data, API request/response models, serializer params
+
+### Docstring Example
+
+```python
+class MyService(LLMService):
+    """Description of what the service does.
+
+    More detailed description.
+
+    Event handlers available:
+
+    - on_connected: Called when we are connected
+
+    Example::
+
+        @service.event_handler("on_connected")
+        async def on_connected(service, frame):
+            ...
+    """
+
+    def __init__(self, param1: str, **kwargs):
+        """Initialize the service.
+
+        Args:
+            param1: Description of param1.
+            **kwargs: Additional arguments passed to parent.
+        """
+        super().__init__(**kwargs)
+```
+
+## Service Implementation
+
+When adding a new service:
+
+1. Extend the appropriate base class (`STTService`, `TTSService`, `LLMService`, etc.)
+2. Implement required abstract methods
+3. Handle necessary frames
+4. By default, all frames should be pushed in the direction they came
+5. Push `ErrorFrame` on failures
+6. Add metrics tracking via `MetricsData` if relevant
+7. Follow the pattern of existing services in `src/pipecat/services/`
+
+## Testing
+
+Test utilities live in `src/pipecat/tests/utils.py`. Use `run_test()` to send frames through a pipeline and assert expected output frames in each direction. Use `SleepFrame(sleep=N)` to add delays between frames.

COMMUNITY_INTEGRATIONS.md

@@ -25,7 +25,6 @@ Your repository must contain these components:
 - **Source code** - Complete implementation following Pipecat patterns
 - **Foundational example** - Single file example showing basic usage (see [Pipecat examples](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational))
 - **README.md** - Must include:
-
   - Introduction and explanation of your integration
   - Installation instructions
   - Usage instructions with Pipecat Pipeline
@@ -66,12 +65,25 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel
 
 #### Websocket-based Services
 
+**Base class:** `WebsocketSTTService`
+
+**Use for:** Services where you manage the websocket connection directly. Combines `STTService` with `WebsocketService` for automatic reconnection and keepalive support.
+
+**Examples:**
+
+- [CartesiaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/cartesia/stt.py)
+- [ElevenLabsRealtimeSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/elevenlabs/stt.py)
+
+#### SDK-based Streaming Services
+
 **Base class:** `STTService`
 
+**Use for:** Streaming services where the provider's Python SDK manages the connection internally.
+
 **Examples:**
 
 - [DeepgramSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/deepgram/stt.py)
-- [SpeechmaticsSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/speechmatics/stt.py)
+- [GoogleSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/stt.py)
 
 #### File-based Services
 
@@ -79,7 +91,7 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel
 
 **Examples:**
 
-- [RivaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/riva/stt.py)
+- [NvidiaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/nvidia/stt.py)
 - [FalSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/fal/stt.py)
 
 #### Key requirements:
@@ -109,56 +121,59 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel
 
 #### Key requirements:
 
+- **`_process_context(self, context: LLMContext)`** — The main method that processes an LLM context and generates a response. Each LLM service overrides `process_frame` to extract context from `LLMContextFrame` and calls `_process_context`.
+
+- **`adapter_class`** — Class attribute pointing to a `BaseLLMAdapter` subclass. Defaults to `OpenAILLMAdapter`. Non-OpenAI services must implement their own adapter (see `src/pipecat/adapters/base_llm_adapter.py`) with methods:
+  - `get_llm_invocation_params(context)` — Extract provider-specific params from universal context
+  - `to_provider_tools_format(tools_schema)` — Convert standard tools to provider format
+  - `get_messages_for_logging(context)` — Format messages for logging
+  - Reference adapters: `src/pipecat/adapters/services/` (anthropic, gemini, bedrock, etc.)
+
 - **Frame sequence:** Output must follow this frame sequence pattern:
+  - `LLMFullResponseStartFrame` — Signals the start of an LLM response
+  - `LLMTextFrame` — Contains LLM content, typically streamed as tokens
+  - `LLMFullResponseEndFrame` — Signals the end of an LLM response
 
-  - `LLMFullResponseStartFrame` - Signals the start of an LLM response
-  - `LLMTextFrame` - Contains LLM content, typically streamed as tokens
-  - `LLMFullResponseEndFrame` - Signals the end of an LLM response
+- **Thought frames (reasoning models):** If the model supports extended thinking / chain-of-thought, emit thought frames alongside the response:
+  - `LLMThoughtStartFrame` — Signals the start of a thought
+  - `LLMThoughtTextFrame` — Contains thought content, streamed as tokens
+  - `LLMThoughtEndFrame` — Signals the end of a thought
 
-- **Context aggregation:** Implement context aggregation to collect user and assistant content:
-  - Aggregators come in pairs with a `user()` instance and `assistant()` instance
-  - Context must adhere to the `LLMContext` universal format
-  - Aggregators should handle adding messages, function calls, and images to the context
+- **Context aggregation** is handled by the framework via `LLMContext` + `LLMContextAggregatorPair`. The LLM service just processes context it receives — no need to implement aggregators.
 
 ### TTS (Text-to-Speech) Services
 
-#### AudioContextWordTTSService
+#### WebsocketTTSService
 
-**Use for:** Websocket-based services supporting word/timestamp alignment
+**Use for:** Websocket-based streaming services (with or without word timestamps)
 
-**Example:**
+**Examples:**
 
 - [CartesiaTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/cartesia/tts.py)
+- [ElevenLabsTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/elevenlabs/tts.py)
 
 #### InterruptibleTTSService
 
-**Use for:** Websocket-based services without word/timestamp alignment, requiring disconnection on interruption
+**Use for:** Websocket-based services without word timestamps that reconnect on interruption (e.g. don't support a context ID or interruption message)
 
 **Example:**
 
 - [SarvamTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/sarvam/tts.py)
 
-#### WordTTSService
-
-**Use for:** HTTP-based services supporting word/timestamp alignment
-
-**Example:**
-
-- [ElevenLabsHttpTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/elevenlabs/tts.py)
-
 #### TTSService
 
-**Use for:** HTTP-based services without word/timestamp alignment
+**Use for:** HTTP-based services (word timestamps are supported in the base class)
 
-**Example:**
+**Examples:**
 
 - [GoogleHttpTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/tts.py)
+- [OpenAITTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/openai/tts.py)
 
 #### Key requirements:
 
-- For websocket services, use asyncio WebSocket implementation (required for v13+ support)
+- For websocket services, use asyncio WebSocket implementation
 - Handle idle service timeouts with keepalives
-- TTSServices push both audio (`TTSRawAudioFrame`) and text (`TTSTextFrame`) frames
+- TTS services push both audio (`TTSAudioRawFrame`) and text (`TTSTextFrame`) frames
 
 ### Telephony Serializers
 
@@ -202,9 +217,9 @@ Vision services process images and provide analysis such as descriptions, object
 
 #### Key requirements:
 
-- Must implement `run_vision` method that takes an `LLMContext` and returns an `AsyncGenerator[Frame, None]`
-- The method processes the latest image in the context and yields frames with analysis results
-- Typically yields `TextFrame` objects containing descriptions or answers
+- Must implement `run_vision` method that takes a `UserImageRawFrame` and returns an `AsyncGenerator[Frame, None]`
+- The method processes the image frame and yields frames with analysis results
+- Must yield the frame sequence: `VisionFullResponseStartFrame`, `VisionTextFrame`, `VisionFullResponseEndFrame`
 
 ## Implementation Guidelines
 
@@ -233,24 +248,137 @@ def can_generate_metrics(self) -> bool:
     return True
 ```
 
-### Dynamic Settings Updates
+### Service Settings
 
-STT, LLM, and TTS services support `ServiceUpdateSettingsFrame` for dynamic configuration changes. The base STTService has an `_update_settings()` method that handles settings, and the private `_settings` `Dict` is used to store settings and provide access to the subclass.
+Every AI service (STT, LLM, TTS, image generation, etc.) exposes a **Settings dataclass** that serves two roles:
+
+1. **Store mode** — the service's `self._settings` holds the current value of every runtime-updatable field.
+2. **Delta mode** — an update frame (e.g. `TTSUpdateSettingsFrame`) specifies only the fields that should change; unspecified fields remain `NOT_GIVEN`.
+
+#### Defining your Settings class
+
+Extend `STTSettings`, `TTSSettings`, `LLMSettings`, or `ImageGenSettings` (or, if your service directly subclasses `AIService`, `ServiceSettings`). The base classes already provide common fields (e.g. `model`, `voice`, `language`). You only need to add **service-specific knobs that should be runtime-updatable**:
 
 ```python
-async def set_language(self, language: Language):
-    """Set the recognition language and reconnect.
+from dataclasses import dataclass, field
 
-    Args:
-        language: The language to use for speech recognition.
+from pipecat.services.settings import TTSSettings, NOT_GIVEN
+
+@dataclass
+class MyTTSSettings(TTSSettings):
+    """Settings for MyTTS service.
+
+    Parameters:
+        speaking_rate: Speed multiplier (0.5–2.0).
     """
-    logger.info(f"Switching STT language to: [{language}]")
-    self._settings["language"] = language
-    await self._disconnect()
-    await self._connect()
+
+    speaking_rate: float | None = field(default_factory=lambda: NOT_GIVEN)
 ```
 
-Note that, in this example, Deepgram requires the websocket connection be disconnected and reconnected to reinitialize the service with the new value. Consider if your service requires reconnection.
+**What goes in Settings vs. `__init__` params:**
+
+| Belongs in Settings                                      | Stays as `__init__` params                |
+| -------------------------------------------------------- | ----------------------------------------- |
+| Model name, voice, language                              | API keys, auth tokens                     |
+| Service-specific tuning knobs (rate, pitch, temperature) | Base URLs, endpoint overrides             |
+| Anything users may want to change mid-session            | Audio encoding, sample format             |
+|                                                          | Connection parameters (timeouts, retries) |
+
+The rule of thumb: if a caller might send an update frame to change it at runtime, it belongs in Settings. Everything else is init-only config stored as `self._xxx`.
+
+#### Wiring settings into `__init__`
+
+Accept an **optional** `settings` parameter. Build a `default_settings` object with all fields set to real values, then merge any caller overrides with `apply_update`.
+
+Add a `Settings` **class attribute** that points to your settings dataclass. This lets callers access the settings class through the service itself (e.g. `MyTTSService.Settings(...)`) without a separate import:
+
+```python
+from typing import Optional
+
+class MyTTSService(TTSService):
+    Settings = MyTTSSettings
+    _settings: Settings
+
+    def __init__(
+        self,
+        *,
+        api_key: str,
+        settings: Optional[Settings] = None,
+        **kwargs,
+    ):
+        # 1. Defaults — every field has a real value (store mode).
+        default_settings = self.Settings(
+            model="my-model-v1",
+            voice="default-voice",
+            language="en",
+            speaking_rate=1.0,
+        )
+
+        # 2. Merge caller overrides (only given fields win).
+        if settings is not None:
+            default_settings.apply_update(settings)
+
+        # 3. Pass the fully-populated settings to the base class.
+        super().__init__(settings=default_settings, **kwargs)
+
+        # 4. Init-only config stored separately.
+        self._api_key = api_key
+```
+
+This pattern lets callers override only what they care about:
+
+```python
+# Uses all defaults
+svc = MyTTSService(api_key="sk-xxx")
+
+# Overrides just the voice — access Settings through the service class
+svc = MyTTSService(
+    api_key="sk-xxx",
+    settings=MyTTSService.Settings(voice="custom-voice"),
+)
+```
+
+#### Reacting to runtime changes
+
+AI services support runtime configuration changes via `*UpdateSettingsFrame`s (e.g. `STTUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `LLMUpdateSettingsFrame`).
+
+To react to runtime setting changes, override `_update_settings`. The base implementation applies the delta to `self._settings` and returns a `dict` mapping each changed field name to its **pre-update** value. Your override should call `super()` first, then act on the changed fields. A common implementation might look like:
+
+```python
+async def _update_settings(self, update: TTSSettings) -> dict[str, Any]:
+    """Apply a settings update, reconfiguring the connection if needed."""
+    changed = await super()._update_settings(update)
+
+    if not changed:
+        return changed
+
+    await self._disconnect()
+    await self._connect()
+
+    return changed
+```
+
+The dict keys work like a set for membership tests (`"language" in changed`) and truthiness (`if changed`). Use `changed.keys() - {"language"}` for set difference, or `changed["language"]` to inspect the previous value of a field.
+
+Note that, in this example, the service requires a reconnect to apply the new language. Consider, for each setting, whether your service requires reconnection or can apply changes in-place.
+
+If your service can't yet apply certain settings at runtime, call `self._warn_unhandled_updated_settings(changed)` with any unhandled field names so users get a clear log message:
+
+```python
+async def _update_settings(self, update: TTSSettings) -> dict[str, Any]:
+    changed = await super()._update_settings(update)
+
+    if not changed:
+        return changed
+
+    if "language" in changed:
+        await self._update_language()
+    else:
+        # TODO: this should be temporary - handle changes to other settings soon!
+        self._warn_unhandled_updated_settings(changed.keys() - {"language"})
+
+    return changed
+```
 
 ### Sample Rate Handling
 
@@ -260,7 +388,7 @@ Sample rates are set via PipelineParams and passed to each frame processor at in
 async def start(self, frame: StartFrame):
     """Start the service."""
     await super().start(frame)
-    self._settings["output_format"]["sample_rate"] = self.sample_rate
+    self._settings.output_sample_rate = self.sample_rate
     await self._connect()
 ```
 
@@ -270,7 +398,7 @@ Note that `self.sample_rate` is a `@property` set in the TTSService base class,
 
 Use Pipecat's tracing decorators:
 
-- **STT:** `@traced_stt` - decorate a function that handles `transcript`, `is_final`, `language` as args
+- **STT:** `@traced_stt` - decorate `_handle_transcription(self, transcript, is_final, language)` (the standard method name convention)
 - **LLM:** `@traced_llm` - decorate the `_process_context()` method
 - **TTS:** `@traced_tts` - decorate the `run_tts()` method
 
@@ -292,17 +420,15 @@ For REST-based communication, use aiohttp. Pipecat includes this as a required d
 - Wrap API calls in appropriate try/catch blocks
 - Handle rate limits and network failures gracefully
 - Provide meaningful error messages
-- When errors occur, raise exceptions AND push `ErrorFrame`s to notify the pipeline:
+- When errors occur, raise exceptions AND push errors to notify the pipeline:
 
 ```python
-from pipecat.frames.frames import ErrorFrame
-
 try:
     # Your API call
     result = await self._make_api_call()
 except Exception as e:
-    # Push error frame to pipeline
-    await self.push_error(ErrorFrame(error=f"{self} error: {e}"))
+    # Push error upstream to notify the pipeline
+    await self.push_error(f"{self} error: {e}", exception=e)
     # Raise or handle as appropriate
     raise
 ```

CONTRIBUTING.md

@@ -17,24 +17,120 @@ We welcome contributions of all kinds! Your help is appreciated. Follow these st
    git checkout -b your-branch-name
    ```
 4. **Make your changes**: Edit or add files as necessary.
-5. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
-6. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
+5. **Add a changelog entry**: Create a changelog fragment file (see [Changelog Entries](#changelog-entries) below).
+6. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
+7. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
 
 ```bash
 git commit -m "Description of your changes"
 ```
 
-7. **Push your changes**: Push your branch to your forked repository.
+8. **Push your changes**: Push your branch to your forked repository.
 
 ```bash
 git push origin your-branch-name
 ```
 
-8. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
+9. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
    > Important: Describe the changes you've made clearly!
 
 Our maintainers will review your PR, and once everything is good, your contributions will be merged!
 
+## Changelog Entries
+
+Every pull request that makes a user-facing change should include a changelog entry. We use a changelog fragment system to avoid merge conflicts.
+
+### Creating a Changelog Fragment
+
+1. Create a new file in the `changelog/` directory with this naming pattern:
+
+   ```
+   <PR_number>.<type>.md
+   ```
+
+2. Choose the appropriate type:
+   - `added.md` - New features
+   - `changed.md` - Changes in existing functionality
+   - `deprecated.md` - Soon-to-be removed features
+   - `removed.md` - Removed features
+   - `fixed.md` - Bug fixes
+   - `performance.md` - Performance improvements
+   - `security.md` - Security fixes
+   - `other.md` - Other changes (documentation, dependencies, etc.)
+
+3. Write your changelog entry as a Markdown bullet point. Include the `-` at the start:
+
+**Example files:**
+
+`changelog/1234.added.md`:
+
+```markdown
+- Added support for Anthropic Claude 3.5 Sonnet with improved streaming performance.
+```
+
+`changelog/5678.fixed.md`:
+
+```markdown
+- Fixed an issue where audio frames were dropped during high-load scenarios.
+```
+
+**For entries with nested bullets:**
+
+`changelog/1234.changed.md`:
+
+```markdown
+- Updated service configuration:
+  - Changed default timeout to 30 seconds
+  - Added retry logic for failed connections
+```
+
+### Multiple Changes in One PR
+
+**Different types of changes:** Create separate fragment files for each type:
+
+```
+changelog/1234.added.md
+changelog/1234.fixed.md
+```
+
+**Multiple changes of the same type:** Create numbered fragment files:
+
+```
+changelog/1234.changed.md
+changelog/1234.changed.2.md
+```
+
+**Related changes:** Use nested bullets in a single fragment:
+
+```markdown
+- Updated service configuration:
+  - Changed default timeout to 30 seconds
+  - Added retry logic for failed connections
+```
+
+**Rule of thumb:** One logical change per fragment file. If changes are unrelated, use separate files.
+
+### Preview Your Changes
+
+To see what your changelog entry will look like:
+
+```bash
+towncrier build --draft --version Unreleased
+```
+
+This won't modify any files, just show you a preview.
+
+### When to Skip Changelog Entries
+
+You can skip adding a changelog entry for:
+
+- Documentation-only changes
+- Internal refactoring with no user-facing impact
+- Test-only changes
+- CI/build configuration changes
+
+If you're unsure whether your change needs a changelog entry, ask in your PR!
+
 ## Dependency Management
 
 This project uses [uv](https://docs.astral.sh/uv/) for dependency management. The `uv.lock` file is committed to ensure reproducible builds.

LICENSE

@@ -1,6 +1,6 @@
 BSD 2-Clause License
 
-Copyright (c) 2024–2025, Daily
+Copyright (c) 2024–2026, Daily
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:

README.md

@@ -3,7 +3,6 @@
 </div></h1>
 
 [![PyPI](https://img.shields.io/pypi/v/pipecat-ai)](https://pypi.org/project/pipecat-ai) ![Tests](https://github.com/pipecat-ai/pipecat/actions/workflows/tests.yaml/badge.svg) [![codecov](https://codecov.io/gh/pipecat-ai/pipecat/graph/badge.svg?token=LNVUIVO4Y9)](https://codecov.io/gh/pipecat-ai/pipecat) [![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.pipecat.ai) [![Discord](https://img.shields.io/discord/1239284677165056021)](https://discord.gg/pipecat) [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/pipecat-ai/pipecat)
-[![](https://getmanta.ai/api/badges?text=Manta%20Graph&link=manta)](https://getmanta.ai/pipecat)
 
 # 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
 
@@ -56,6 +55,20 @@ Looking for help debugging your pipeline and processors? Check out [Whisker](htt
 
 Love terminal applications? Check out [Tail](https://github.com/pipecat-ai/tail), a terminal dashboard for Pipecat.
 
+### 🤖 Claude Code Skills
+
+Use [Pipecat Skills](https://github.com/pipecat-ai/skills) with [Claude Code](https://claude.ai/code) to scaffold projects, deploy to Pipecat Cloud, and more. Install the marketplace with:
+
+```
+claude plugin marketplace add pipecat-ai/skills
+```
+
+and install any of the available plugins.
+
+### 🧩 Community Integrations
+
+Build and share your own Pipecat service integrations! Browse existing [community integrations](https://docs.pipecat.ai/server/services/community-integrations) or check out our [guide](COMMUNITY_INTEGRATIONS.md) to create your own.
+
 ### 📺️ Pipecat TV Channel
 
 Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.youtube.com/playlist?list=PLzU2zoMTQIHjqC3v4q2XVSR3hGSzwKFwH) channel.
@@ -72,19 +85,20 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
 
 ## 🧩 Available services
 
-| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
-| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                        |
-| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                                                                                                                                                              |
-| Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
-| Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
-| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Serializers         | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
-| Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
-| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
-| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [Nebius](https://docs.pipecat.ai/server/services/llm/nebius), [Novita](https://docs.pipecat.ai/server/services/llm/novita), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nvidia), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/llm/sarvam), [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                                                                                                                                                                                                                                                                                         |
+| Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [Resemble](https://docs.pipecat.ai/server/services/tts/resemble), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Smallest](https://docs.pipecat.ai/server/services/tts/smallest), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [xAI](https://docs.pipecat.ai/server/services/tts/xai), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
+| Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox),                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
+| Serializers         | [Exotel](https://docs.pipecat.ai/server/utilities/serializers/exotel), [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx), [Vonage](https://docs.pipecat.ai/server/utilities/serializers/vonage)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |
+| Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [LemonSlice](https://docs.pipecat.ai/server/services/video/lemonslice), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/google-imagen), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+| Community           | [Browse community integrations →](https://docs.pipecat.ai/server/services/community-integrations)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 
@@ -154,7 +168,6 @@ You can get started with Pipecat running on your local machine, then move your a
      --no-extra gstreamer \
      --no-extra krisp \
      --no-extra local \
-     --no-extra ultravox # (ultravox not fully supported on macOS)
    ```
 
 3. Install the git pre-commit hooks:
@@ -165,6 +178,15 @@ You can get started with Pipecat running on your local machine, then move your a
 
 > **Note**: Some extras (local, gstreamer) require system dependencies. See documentation if you encounter build errors.
 
+### Claude Code Skills
+
+Install development workflow skills for contributing to Pipecat with [Claude Code](https://claude.ai/code):
+
+```
+claude plugin marketplace add pipecat-ai/pipecat
+claude plugin install pipecat-dev@pipecat-dev-skills
+```
+
 ### Running tests
 
 To run all tests, from the root directory:

changelog/_template.md.j2

@@ -0,0 +1,16 @@
+{% for section, _ in sections.items() %}
+{% if sections[section] %}
+{% for category, val in definitions.items() if category in sections[section]%}
+### {{ definitions[category]['name'] }}
+
+{% for text, values in sections[section][category].items() %}
+{{ text }}
+(PR {{ values|join(', ') }})
+
+{% endfor %}
+{% endfor %}
+{% else %}
+No significant changes.
+
+{% endif %}
+{% endfor %}

docs/api/README.md

@@ -42,7 +42,7 @@ This script:
 
 - Creates a fresh virtual environment
 - Installs all dependencies as specified in requirements files
-- Handles conflicting dependencies (like grpcio versions for Riva and PlayHT)
+- Handles conflicting dependencies (like grpcio versions for Riva)
 - Builds the documentation in an isolated environment
 - Provides detailed logging of the build process
 
@@ -74,7 +74,6 @@ start _build/html/index.html
 ├── index.rst       # Main documentation entry point
 ├── requirements-base.txt    # Base documentation dependencies
 ├── requirements-riva.txt    # Riva-specific dependencies
-├── requirements-playht.txt  # PlayHT-specific dependencies
 ├── build-docs.sh   # Local build script
 └── rtd-test.py     # ReadTheDocs test build script
 ```

docs/api/build-docs.sh

@@ -2,7 +2,7 @@
 
 # Build docs using uv
 echo "Installing dependencies with uv..."
-uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra ultravox --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
+uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
 
 # Check if sphinx-build is available
 if ! uv run sphinx-build --version &> /dev/null; then
@@ -24,4 +24,4 @@ if [ $? -eq 0 ]; then
 else
     echo "Documentation build failed!" >&2
     exit 1
-fi
+fi

docs/api/conf.py

@@ -61,9 +61,6 @@ autodoc_mock_imports = [
     # OpenCV - sometimes has import issues during docs build
     "cv2",
     # Heavy ML packages excluded from ReadTheDocs
-    # ultravox dependencies
-    "vllm",
-    "vllm.engine.arg_utils",
     # local-smart-turn dependencies
     "coremltools",
     "coremltools.models",
@@ -94,6 +91,25 @@ autodoc_mock_imports = [
     # MLX dependencies (Apple Silicon specific)
     "mlx",
     "mlx_whisper",  # Note: might need underscore format too
+    # Pydantic v2 compatibility issues in third-party SDKs
+    "hume",
+    "hume.tts",
+    "hume.tts.types",
+    "cartesia",
+    "camb",
+    "sarvamai",
+    "openpipe",
+    "openai.types.beta.realtime",
+    "langchain_core",
+    "langchain_core.messages",
+    # FastAPI - Pydantic v2 compatibility issues during Sphinx autodoc
+    "fastapi",
+    "fastapi.applications",
+    "fastapi.routing",
+    "fastapi.params",
+    "fastapi.middleware",
+    "fastapi.responses",
+    "uvicorn",
 ]
 
 # HTML output settings
@@ -119,7 +135,6 @@ def import_core_modules():
         "pipecat.observers",
         "pipecat.runner",
         "pipecat.serializers",
-        "pipecat.sync",
         "pipecat.transcriptions",
         "pipecat.utils",
     ]

docs/api/index.rst

@@ -30,7 +30,6 @@ Quick Links
    Runner <api/pipecat.runner>
    Serializers <api/pipecat.serializers>
    Services <api/pipecat.services>
-   Sync <api/pipecat.sync>
    Transcriptions <api/pipecat.transcriptions>
    Transports <api/pipecat.transports>
-   Utils <api/pipecat.utils>
+   Utils <api/pipecat.utils>

env.example

@@ -31,6 +31,9 @@ AZURE_DALLE_API_KEY=...
 AZURE_DALLE_ENDPOINT=https://...
 AZURE_DALLE_MODEL=...
 
+# Camb.ai
+CAMB_API_KEY=...
+
 # Cartesia
 CARTESIA_API_KEY=...
 CARTESIA_VOICE_ID=...
@@ -40,10 +43,12 @@ CEREBRAS_API_KEY=...
 
 # Daily
 DAILY_API_KEY=...
-DAILY_SAMPLE_ROOM_URL=https://...
+DAILY_ROOM_URL=https://...
 
 # Deepgram
 DEEPGRAM_API_KEY=...
+SAGEMAKER_STT_ENDPOINT_NAME=...
+SAGEMAKER_TTS_ENDPOINT_NAME=...
 
 # DeepSeek
 DEEPSEEK_API_KEY=...
@@ -72,14 +77,15 @@ GOOGLE_CLOUD_PROJECT_ID=...
 GOOGLE_CLOUD_LOCATION=...
 GOOGLE_TEST_CREDENTIALS=...
 
-# Grok
-GROK_API_KEY=...
+# Gradium
+GRAPDIUM_API_KEY=...
 
 # Groq
 GROQ_API_KEY=...
 
 # Heygen
 HEYGEN_API_KEY=...
+HEYGEN_LIVE_AVATAR_API_KEY=...
 
 # Hume
 HUME_API_KEY=...
@@ -92,7 +98,13 @@ INWORLD_API_KEY=...
 KRISP_MODEL_PATH=...
 
 # Krisp Viva
-KRISP_VIVA_MODEL_PATH=...
+KRISP_VIVA_API_KEY=...
+KRISP_VIVA_FILTER_MODEL_PATH=...
+KRISP_VIVA_TURN_MODEL_PATH=...
+
+# LemonSlice
+LEMONSLICE_API_KEY=...
+LEMONSLICE_AGENT_ID=...
 
 # LiveKit
 LIVEKIT_API_KEY=...
@@ -109,9 +121,15 @@ MINIMAX_GROUP_ID=...
 # Mistral
 MISTRAL_API_KEY=...
 
+# Nebius
+NEBIUS_API_KEY=...
+
 # Neuphonic
 NEUPHONIC_API_KEY=...
 
+# Novita
+NOVITA_API_KEY=...
+
 # NVIDIA
 NVIDIA_API_KEY=...
 
@@ -133,10 +151,6 @@ KOALA_ACCESS_KEY=...
 # Piper
 PIPER_BASE_URL=...
 
-# PlayHT
-PLAYHT_USER_ID=...
-PLAYHT_API_KEY=...
-
 # Plivo
 PLIVO_AUTH_ID=...
 PLIVO_AUTH_TOKEN=...
@@ -144,6 +158,10 @@ PLIVO_AUTH_TOKEN=...
 # Qwen
 QWEN_API_KEY=...
 
+# Resemble AI
+RESEMBLE_API_KEY=
+RESEMBLE_VOICE_UUID=
+
 # Rime
 RIME_API_KEY=...
 RIME_VOICE_ID=...
@@ -161,6 +179,9 @@ SENTRY_DSN=...
 SIMLI_API_KEY=...
 SIMLI_FACE_ID=...
 
+# Smallest
+SMALLEST_API_KEY=...
+
 # Smart turn
 LOCAL_SMART_TURN_MODEL_PATH=...
 FAL_SMART_TURN_API_KEY=...
@@ -186,8 +207,14 @@ TOGETHER_API_KEY=...
 TWILIO_ACCOUNT_SID=...
 TWILIO_AUTH_TOKEN=...
 
+# Ultravox Realtime
+ULTRAVOX_API_KEY=...
+
 # WhatsApp
 WHATSAPP_TOKEN=...
 WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=...
 WHATSAPP_PHONE_NUMBER_ID=...
-WHATSAPP_APP_SECRET=...
+WHATSAPP_APP_SECRET=...
+
+# xAI / Grok
+XAI_API_KEY=...

examples/foundational/01-say-one-thing-piper.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -16,7 +16,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.piper.tts import PiperTTSService
+from pipecat.services.piper.tts import PiperHttpTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -24,9 +24,8 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(audio_out_enabled=True),
     "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
@@ -39,8 +38,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     # Create an HTTP session
     async with aiohttp.ClientSession() as session:
-        tts = PiperTTSService(
-            base_url=os.getenv("PIPER_BASE_URL"), aiohttp_session=session, sample_rate=24000
+        tts = PiperHttpTTSService(
+            base_url=os.getenv("PIPER_BASE_URL"),
+            aiohttp_session=session,
+            sample_rate=24000,
         )
 
         task = PipelineTask(

examples/foundational/01-say-one-thing-rime.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -23,9 +23,8 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(audio_out_enabled=True),
     "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
@@ -40,8 +39,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async with aiohttp.ClientSession() as session:
         tts = RimeHttpTTSService(
             api_key=os.getenv("RIME_API_KEY", ""),
-            voice_id="rex",
             aiohttp_session=session,
+            settings=RimeHttpTTSService.Settings(
+                voice="rex",
+            ),
         )
 
         task = PipelineTask(

examples/foundational/01-say-one-thing.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -23,9 +23,8 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(audio_out_enabled=True),
     "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
@@ -38,7 +37,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
     task = PipelineTask(

examples/foundational/01a-local-audio.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -29,7 +29,9 @@ async def main():
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
     pipeline = Pipeline([tts, transport.output()])

examples/foundational/01b-livekit-audio.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -37,7 +37,9 @@ async def main():
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
     runner = PipelineRunner()

examples/foundational/01c-nvidia-riva-tts.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -15,7 +15,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.riva.tts import FastPitchTTSService
+from pipecat.services.nvidia.tts import NvidiaTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -23,9 +23,8 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(audio_out_enabled=True),
     "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
@@ -36,7 +35,7 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+    tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
 
     task = PipelineTask(
         Pipeline([tts, transport.output()]),

examples/foundational/02-llm-say-one-thing.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -25,9 +25,8 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(audio_out_enabled=True),
     "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
@@ -40,17 +39,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
-
-    messages = [
-        {
-            "role": "system",
-            "content": "You are an LLM in a WebRTC session, and this is a 'hello world' demo. Say hello to the world.",
-        }
-    ]
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
     task = PipelineTask(
         Pipeline([llm, tts, transport.output()]),
@@ -60,7 +59,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     # Register an event handler so we can play the audio when the client joins
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
-        await task.queue_frames([LLMContextFrame(LLMContext(messages)), EndFrame()])
+        context = LLMContext()
+        context.add_message({"role": "developer", "content": "Say hello to the world."})
+        await task.queue_frames([LLMContextFrame(context), EndFrame()])
 
     runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
 

examples/foundational/03-still-frame.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -23,9 +23,8 @@ from pipecat.transports.daily.transport import DailyParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         video_out_enabled=True,
@@ -46,7 +45,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     # Create an HTTP session
     async with aiohttp.ClientSession() as session:
         imagegen = FalImageGenService(
-            params=FalImageGenService.InputParams(image_size="square_hd"),
+            settings=FalImageGenService.Settings(
+                image_size="square_hd",
+            ),
             aiohttp_session=session,
             key=os.getenv("FAL_KEY"),
         )

examples/foundational/03a-local-still-frame.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -37,7 +37,9 @@ async def main():
         )
 
         imagegen = FalImageGenService(
-            params=FalImageGenService.InputParams(image_size="square_hd"),
+            settings=FalImageGenService.Settings(
+                image_size="square_hd",
+            ),
             aiohttp_session=session,
             key=os.getenv("FAL_KEY"),
         )

examples/foundational/03b-still-frame-imagen.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -22,9 +22,8 @@ from pipecat.transports.daily.transport import DailyParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         video_out_enabled=True,

examples/foundational/04-transports-small-webrtc.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -17,16 +17,16 @@ from fastapi.responses import RedirectResponse
 from loguru import logger
 from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
@@ -60,8 +60,6 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
         params=TransportParams(
             audio_in_enabled=True,
             audio_out_enabled=True,
-            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         ),
     )
 
@@ -69,30 +67,33 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -108,7 +109,9 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/04a-transports-daily.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -12,16 +12,16 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.daily import configure
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
@@ -45,36 +45,37 @@ async def main():
                 audio_in_enabled=True,
                 audio_out_enabled=True,
                 transcription_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-                turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
             ),
         )
 
         tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            settings=CartesiaTTSService.Settings(
+                voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            ),
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            settings=OpenAILLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(context)
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -90,7 +91,9 @@ async def main():
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_participant_left")

examples/foundational/04b-transports-livekit.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -12,10 +12,7 @@ import sys
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import (
     InterruptionFrame,
     TranscriptionFrame,
@@ -27,7 +24,10 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.livekit import configure
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -50,42 +50,40 @@ async def main():
         params=LiveKitParams(
             audio_in_enabled=True,
             audio_out_enabled=True,
-            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         ),
     )
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. "
-            "Your goal is to demonstrate your capabilities in a succinct way. "
-            "Your output will be converted to audio so don't include special characters in your answers. "
-            "Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

examples/foundational/05-sync-speech-and-image.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -16,14 +16,14 @@ from pipecat.frames.frames import (
     Frame,
     LLMContextFrame,
     LLMFullResponseStartFrame,
+    OutputImageRawFrame,
     TextFrame,
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
+from pipecat.pipeline.sync_parallel_pipeline import FrameOrder, SyncParallelPipeline
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.aggregators.sentence import SentenceAggregator
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
@@ -31,6 +31,7 @@ from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaHttpTTSService
 from pipecat.services.fal.image import FalImageGenService
 from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.tts_service import TextAggregationMode
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 
@@ -45,6 +46,18 @@ class MonthFrame(DataFrame):
         return f"{self.name}(month: {self.month})"
 
 
+class MarkImageForPlaybackSync(FrameProcessor):
+    """Marks output image frames to be synchronized with audio playback."""
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, OutputImageRawFrame):
+            frame.sync_with_audio = True
+
+        await self.push_frame(frame, direction)
+
+
 class MonthPrepender(FrameProcessor):
     def __init__(self):
         super().__init__()
@@ -66,9 +79,8 @@ class MonthPrepender(FrameProcessor):
             await self.push_frame(frame, direction)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_out_enabled=True,
@@ -100,11 +112,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = CartesiaHttpTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            settings=CartesiaHttpTTSService.Settings(
+                voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            ),
+            # No need to aggregate by sentences (the default), as we already know we're getting full sentences
+            # (Otherwise the service will unnecessarily wait for follow-up input to confirm the sentence is complete,
+            #  which, sadly, actually breaks the synchronization mechanism)
+            text_aggregation_mode=TextAggregationMode.TOKEN,
         )
 
         imagegen = FalImageGenService(
-            params=FalImageGenService.InputParams(image_size="square_hd"),
+            settings=FalImageGenService.Settings(
+                image_size="square_hd",
+            ),
             aiohttp_session=session,
             key=os.getenv("FAL_KEY"),
         )
@@ -117,17 +137,26 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         # that, each pipeline runs concurrently and `SyncParallelPipeline` will
         # wait for the input frame to be processed.
         #
+        # We use `FrameOrder.PIPELINE` so that each synchronized batch of output
+        # frames is pushed in the order the pipelines are listed: image first,
+        # then audio. This ensures the transport receives the image before the
+        # audio frames it should accompany.
+        #
         # Note that `SyncParallelPipeline` requires the last processor in each
         # of the pipelines to be synchronous. In this case, we use
-        # `CartesiaHttpTTSService` and `FalImageGenService` which make HTTP
+        # `FalImageGenService` and `CartesiaHttpTTSService` which make HTTP
         # requests and wait for the response.
         pipeline = Pipeline(
             [
                 llm,  # LLM
                 sentence_aggregator,  # Aggregates LLM output into full sentences
                 SyncParallelPipeline(  # Run pipelines in parallel aggregating the result
+                    [
+                        imagegen,  # Generate image
+                        MarkImageForPlaybackSync(),  # Mark image as needing sync w/audio during playback
+                    ],
                     [month_prepender, tts],  # Create "Month: sentence" and output audio
-                    [imagegen],  # Generate image
+                    frame_order=FrameOrder.PIPELINE,
                 ),
                 transport.output(),  # Transport output
             ]
@@ -150,7 +179,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ]:
             messages = [
                 {
-                    "role": "system",
+                    "role": "user",
                     "content": f"Describe a nature photograph suitable for use in a calendar, for the month of {month}. Include only the image description with no preamble. Limit the description to one sentence, please.",
                 }
             ]

examples/foundational/05a-local-sync-speech-and-image.py

@@ -1,199 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-import tkinter as tk
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-
-from pipecat.frames.frames import (
-    Frame,
-    LLMContextFrame,
-    OutputAudioRawFrame,
-    TextFrame,
-    TTSAudioRawFrame,
-    URLImageRawFrame,
-)
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
-from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
-from pipecat.processors.aggregators.sentence import SentenceAggregator
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.services.cartesia.tts import CartesiaHttpTTSService
-from pipecat.services.fal.image import FalImageGenService
-from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        tk_root = tk.Tk()
-        tk_root.title("Calendar")
-
-        runner = PipelineRunner()
-
-        async def get_month_data(month):
-            messages = [
-                {
-                    "role": "system",
-                    "content": f"Describe a nature photograph suitable for use in a calendar, for the month of {month}. Include only the image description with no preamble. Limit the description to one sentence, please.",
-                }
-            ]
-
-            class ImageDescription(FrameProcessor):
-                def __init__(self):
-                    super().__init__()
-                    self.text = ""
-
-                async def process_frame(self, frame: Frame, direction: FrameDirection):
-                    await super().process_frame(frame, direction)
-
-                    if isinstance(frame, TextFrame):
-                        self.text = frame.text
-                    await self.push_frame(frame, direction)
-
-            class AudioGrabber(FrameProcessor):
-                def __init__(self):
-                    super().__init__()
-                    self.audio = bytearray()
-                    self.frame = None
-
-                async def process_frame(self, frame: Frame, direction: FrameDirection):
-                    await super().process_frame(frame, direction)
-
-                    if isinstance(frame, TTSAudioRawFrame):
-                        self.audio.extend(frame.audio)
-                        self.frame = OutputAudioRawFrame(
-                            bytes(self.audio), frame.sample_rate, frame.num_channels
-                        )
-                    await self.push_frame(frame, direction)
-
-            class ImageGrabber(FrameProcessor):
-                def __init__(self):
-                    super().__init__()
-                    self.frame = None
-
-                async def process_frame(self, frame: Frame, direction: FrameDirection):
-                    await super().process_frame(frame, direction)
-
-                    if isinstance(frame, URLImageRawFrame):
-                        self.frame = frame
-                    await self.push_frame(frame, direction)
-
-            llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
-
-            tts = CartesiaHttpTTSService(
-                api_key=os.getenv("CARTESIA_API_KEY"),
-                voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-            )
-
-            imagegen = FalImageGenService(
-                params=FalImageGenService.InputParams(image_size="square_hd"),
-                aiohttp_session=session,
-                key=os.getenv("FAL_KEY"),
-            )
-
-            sentence_aggregator = SentenceAggregator()
-
-            description = ImageDescription()
-
-            audio_grabber = AudioGrabber()
-
-            image_grabber = ImageGrabber()
-
-            # With `SyncParallelPipeline` we synchronize audio and images by
-            # pushing them basically in order (e.g. I1 A1 A1 A1 I2 A2 A2 A2 A2
-            # I3 A3). To do that, each pipeline runs concurrently and
-            # `SyncParallelPipeline` will wait for the input frame to be
-            # processed.
-            #
-            # Note that `SyncParallelPipeline` requires the last processor in
-            # each of the pipelines to be synchronous. In this case, we use
-            # `CartesiaHttpTTSService` and `FalImageGenService` which make HTTP
-            # requests and wait for the response.
-            pipeline = Pipeline(
-                [
-                    llm,  # LLM
-                    sentence_aggregator,  # Aggregates LLM output into full sentences
-                    description,  # Store sentence
-                    SyncParallelPipeline(
-                        [tts, audio_grabber],  # Generate and store audio for the given sentence
-                        [imagegen, image_grabber],  # Generate and storeimage for the given sentence
-                    ),
-                ]
-            )
-
-            task = PipelineTask(pipeline)
-            await task.queue_frame(LLMContextFrame(LLMContext(messages)))
-            await task.stop_when_done()
-
-            await runner.run(task)
-
-            return {
-                "month": month,
-                "text": description.text,
-                "image": image_grabber.frame,
-                "audio": audio_grabber.frame,
-            }
-
-        transport = TkLocalTransport(
-            tk_root,
-            TkTransportParams(
-                audio_out_enabled=True,
-                video_out_enabled=True,
-                video_out_width=1024,
-                video_out_height=1024,
-            ),
-        )
-
-        pipeline = Pipeline([transport.output()])
-
-        task = PipelineTask(pipeline)
-
-        # We only specify a few months as we create tasks all at once and we
-        # might get rate limited otherwise.
-        months: list[str] = [
-            "January",
-            "February",
-        ]
-
-        # We create one task per month. This will be executed concurrently.
-        month_tasks = [asyncio.create_task(get_month_data(month)) for month in months]
-
-        # Now we wait for each month task in the order they're completed. The
-        # benefit is we'll have as little delay as possible before the first
-        # month, and likely no delay between months, but the months won't
-        # display in order.
-        async def show_images(month_tasks):
-            for month_data_task in asyncio.as_completed(month_tasks):
-                data = await month_data_task
-                await task.queue_frames([data["image"], data["audio"]])
-
-            await runner.stop_when_done()
-
-        async def run_tk():
-            while not task.has_finished():
-                tk_root.update()
-                tk_root.update_idletasks()
-                await asyncio.sleep(0.1)
-
-        await asyncio.gather(runner.run(task), show_images(month_tasks), run_tk())
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

examples/foundational/06-listen-and-respond.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -9,10 +9,7 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import Frame, LLMRunFrame, MetricsFrame
 from pipecat.metrics.metrics import (
     LLMUsageMetricsData,
@@ -24,7 +21,10 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -58,27 +58,20 @@ class MetricsLogger(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -90,33 +83,36 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
     ml = MetricsLogger()
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),
             stt,
-            context_aggregator.user(),
+            user_aggregator,
             llm,
             tts,
             ml,
             transport.output(),
-            context_aggregator.assistant(),
+            assistant_aggregator,
         ]
     )
 
@@ -133,7 +129,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/06a-image-sync.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,10 +10,7 @@ from dotenv import load_dotenv
 from loguru import logger
 from PIL import Image
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import (
     BotStartedSpeakingFrame,
     BotStoppedSpeakingFrame,
@@ -25,7 +22,10 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -73,9 +73,8 @@ class ImageSyncAggregator(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
@@ -83,8 +82,6 @@ transport_params = {
         video_out_enabled=True,
         video_out_width=1024,
         video_out_height=1024,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
@@ -92,8 +89,6 @@ transport_params = {
         video_out_enabled=True,
         video_out_width=1024,
         video_out_height=1024,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -105,20 +100,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     image_sync_aggregator = ImageSyncAggregator(
         os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
@@ -129,12 +127,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),
             stt,
-            context_aggregator.user(),
+            user_aggregator,
             llm,
             tts,
             image_sync_aggregator,
             transport.output(),
-            context_aggregator.assistant(),
+            assistant_aggregator,
         ]
     )
 

examples/foundational/07-interruptible-cartesia-http.py

@@ -1,24 +1,25 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import os
 
+import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.stt import CartesiaSTTService
@@ -31,27 +32,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -59,61 +53,68 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
+    async with aiohttp.ClientSession() as session:
+        stt = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
 
-    tts = CartesiaHttpTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-    )
+        tts = CartesiaHttpTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            aiohttp_session=session,
+            settings=CartesiaHttpTTSService.Settings(
+                voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            ),
+        )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            settings=OpenAILLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,
+                user_aggregator,  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                assistant_aggregator,  # Assistant spoken responses
+            ]
+        )
 
-    pipeline = Pipeline(
-        [
-            transport.input(),  # Transport user input
-            stt,
-            context_aggregator.user(),  # User responses
-            llm,  # LLM
-            tts,  # TTS
-            transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
-        ]
-    )
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
 
-    task = PipelineTask(
-        pipeline,
-        params=PipelineParams(
-            enable_metrics=True,
-            enable_usage_metrics=True,
-        ),
-        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
-    )
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info(f"Client connected")
+            # Kick off the conversation.
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
+            await task.queue_frames([LLMRunFrame()])
 
-    @transport.event_handler("on_client_connected")
-    async def on_client_connected(transport, client):
-        logger.info(f"Client connected")
-        # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([LLMRunFrame()])
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+            await task.cancel()
 
-    @transport.event_handler("on_client_disconnected")
-    async def on_client_disconnected(transport, client):
-        logger.info(f"Client disconnected")
-        await task.cancel()
+        runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
 
-    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
-
-    await runner.run(task)
+        await runner.run(task)
 
 
 async def bot(runner_args: RunnerArguments):

examples/foundational/07-interruptible-openai-responses.py

@@ -1,66 +1,49 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-
 import os
 
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.ultravox.stt import UltravoxSTTService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.openai.responses.llm import OpenAIResponsesLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# NOTE: This example requires GPU resources to run efficiently.
-# The Ultravox model is compute-intensive and performs best with GPU acceleration.
-# This can be deployed on cloud GPU providers like Cerebrium.ai for optimal performance.
-
-
-# Want to initialize the ultravox processor since it takes time to load the model and dont
-# want to load it every time the pipeline is run
-ultravox_processor = UltravoxSTTService(
-    model_name="fixie-ai/ultravox-v0_5-llama-3_1-8b",
-    hf_token=os.getenv("HF_TOKEN"),
-)
-
-
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -68,17 +51,37 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
     tts = CartesiaTTSService(
-        api_key=os.environ.get("CARTESIA_API_KEY"),
-        voice_id="97f4b8fb-f2fe-444b-bb9a-c109783a857a",
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
+    )
+
+    llm = OpenAIResponsesLLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAIResponsesLLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
+
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
     )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
-            ultravox_processor,
+            stt,
+            user_aggregator,  # User responses
+            llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -94,6 +97,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
+        # Kick off the conversation.
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/07-interruptible.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -9,16 +9,16 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
@@ -30,27 +30,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -62,30 +55,33 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -102,7 +98,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07a-interruptible-speechmatics-vad.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -15,13 +15,12 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response import (
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
     LLMUserAggregatorParams,
 )
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.openai.base_llm import BaseOpenAILLMService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
 from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
@@ -29,12 +28,12 @@ from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.user_turn_strategies import ExternalUserTurnStrategies
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
@@ -76,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     4. Text-to-Speech (TTS)
        - Low latency streaming audio synthesis
-       - Multiple voice options available including `sarah`, `theo`, and `megan`
+       - Multiple voice options available including `sarah`, `theo`, `megan` and `jack`
 
     5. Configuration Options
        - `operating_point` parameter defaults to `ENHANCED` for optimal accuracy
@@ -93,12 +92,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async with aiohttp.ClientSession() as session:
         stt = SpeechmaticsSTTService(
             api_key=os.getenv("SPEECHMATICS_API_KEY"),
-            params=SpeechmaticsSTTService.InputParams(
+            settings=SpeechmaticsSTTService.Settings(
                 language=Language.EN,
-                enable_vad=True,
-                enable_diarization=True,
-                focus_speakers=["S1"],
-                end_of_utterance_silence_trigger=0.5,
+                turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
+                # focus_speakers=["S1"],
                 speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
                 speaker_passive_format="<PASSIVE><{speaker_id}>{text}</{speaker_id}></PASSIVE>",
             ),
@@ -106,46 +103,35 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = SpeechmaticsTTSService(
             api_key=os.getenv("SPEECHMATICS_API_KEY"),
-            voice_id="sarah",
+            settings=SpeechmaticsTTSService.Settings(
+                voice="sarah",
+            ),
             aiohttp_session=session,
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            params=BaseOpenAILLMService.InputParams(temperature=0.75),
+            settings=OpenAILLMService.Settings(
+                temperature=0.75,
+                system_instruction="You are a helpful British assistant called Sarah in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",
+            ),
         )
 
-        messages = [
-            {
-                "role": "system",
-                "content": (
-                    "You are a helpful British assistant called Sarah. "
-                    "Your goal is to demonstrate your capabilities in a succinct way. "
-                    "Your output will be converted to audio so don't include special characters in your answers. "
-                    "Always include punctuation in your responses. "
-                    "Give very short replies - do not give longer replies unless strictly necessary. "
-                    "Respond to what the user said in a concise, funny, creative and helpful way. "
-                    "Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. "
-                    "Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to. "
-                ),
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
-            user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
+            user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
         )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -162,7 +148,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         async def on_client_connected(transport, client):
             logger.info(f"Client connected")
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Say a short hello to the user."})
+            context.add_message({"role": "developer", "content": "Say a short hello to the user."})
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

examples/foundational/07a-interruptible-speechmatics.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,22 +10,18 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response import (
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
     LLMUserAggregatorParams,
 )
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.openai.base_llm import BaseOpenAILLMService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
 from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
@@ -36,27 +32,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -75,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     TTS Features:
     - Low latency streaming audio synthesis
-    - Multiple voice options available including `sarah`, `theo`, and `megan`
+    - Multiple voice options available including `sarah`, `theo`, `megan` and `jack`
 
     For more information:
     - STT: https://docs.speechmatics.com/rt-api-ref
@@ -86,55 +75,43 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async with aiohttp.ClientSession() as session:
         stt = SpeechmaticsSTTService(
             api_key=os.getenv("SPEECHMATICS_API_KEY"),
-            params=SpeechmaticsSTTService.InputParams(
+            settings=SpeechmaticsSTTService.Settings(
                 language=Language.EN,
-                enable_diarization=True,
-                end_of_utterance_silence_trigger=0.5,
                 speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
             ),
         )
 
         tts = SpeechmaticsTTSService(
             api_key=os.getenv("SPEECHMATICS_API_KEY"),
-            voice_id="sarah",
+            settings=SpeechmaticsTTSService.Settings(
+                voice="sarah",
+            ),
             aiohttp_session=session,
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            params=BaseOpenAILLMService.InputParams(temperature=0.75),
+            settings=OpenAILLMService.Settings(
+                temperature=0.75,
+                system_instruction="You are a helpful British assistant called Sarah in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",
+            ),
         )
 
-        messages = [
-            {
-                "role": "system",
-                "content": (
-                    "You are a helpful British assistant called Sarah. "
-                    "Your goal is to demonstrate your capabilities in a succinct way. "
-                    "Your output will be converted to audio so don't include special characters in your answers. "
-                    "Always include punctuation in your responses. "
-                    "Give very short replies - do not give longer replies unless strictly necessary. "
-                    "Respond to what the user said in a concise, funny, creative and helpful way. "
-                    "Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
-                ),
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
-            user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
         )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,  # STT
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -151,7 +128,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         async def on_client_connected(transport, client):
             logger.info(f"Client connected")
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Say a short hello to the user."})
+            context.add_message({"role": "developer", "content": "Say a short hello to the user."})
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

examples/foundational/07b-interruptible-langchain.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -15,16 +15,16 @@ from langchain_core.runnables.history import RunnableWithMessageHistory
 from langchain_openai import ChatOpenAI
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMMessagesUpdateFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.processors.frameworks.langchain import LangchainProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -46,27 +46,20 @@ def get_session_history(session_id: str) -> BaseChatMessageHistory:
     return message_store[session_id]
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -78,15 +71,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
     prompt = ChatPromptTemplate.from_messages(
         [
             (
                 "system",
-                "Be nice and helpful. Answer very briefly and without special characters like `#` or `*`. "
-                "Your response will be synthesized to voice and those characters will create unnatural sounds.",
+                "You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
             ),
             MessagesPlaceholder("chat_history"),
             ("human", "{input}"),
@@ -102,17 +96,20 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     lc = LangchainProcessor(history_chain)
 
     context = LLMContext()
-    context_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             lc,  # Langchain
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

examples/foundational/07c-interruptible-deepgram-flux-sagemaker.py

@@ -0,0 +1,151 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
+from pipecat.services.deepgram.flux.sagemaker.stt import DeepgramFluxSageMakerSTTService
+from pipecat.services.deepgram.sagemaker.tts import DeepgramSageMakerTTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.user_turn_strategies import ExternalUserTurnStrategies
+
+load_dotenv(override=True)
+
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    # Initialize Deepgram Flux SageMaker STT Service
+    # This requires:
+    # - AWS credentials configured (via environment variables or AWS CLI)
+    # - A deployed SageMaker endpoint with Deepgram Flux model
+    stt = DeepgramFluxSageMakerSTTService(
+        endpoint_name=os.getenv("SAGEMAKER_STT_ENDPOINT_NAME"),
+        region=os.getenv("AWS_REGION"),
+        settings=DeepgramFluxSageMakerSTTService.Settings(
+            min_confidence=0.3,
+        ),
+    )
+
+    # Initialize Deepgram SageMaker TTS Service
+    # This requires:
+    # - AWS credentials configured (via environment variables or AWS CLI)
+    # - A deployed SageMaker endpoint with Deepgram TTS model
+    tts = DeepgramSageMakerTTSService(
+        endpoint_name=os.getenv("SAGEMAKER_TTS_ENDPOINT_NAME"),
+        region=os.getenv("AWS_REGION"),
+        settings=DeepgramSageMakerTTSService.Settings(
+            voice="aura-2-andromeda-en",
+        ),
+    )
+
+    llm = AWSBedrockLLMService(
+        aws_region=os.getenv("AWS_REGION"),
+        settings=AWSBedrockLLMSettings(
+            model="us.amazon.nova-pro-v1:0",
+            temperature=0.8,
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
+
+    context = LLMContext()
+    # Use ExternalUserTurnStrategies since Flux handles turn detection natively
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=ExternalUserTurnStrategies(),
+            vad_analyzer=SileroVADAnalyzer(),
+        ),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            user_aggregator,  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            assistant_aggregator,  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    @stt.event_handler("on_update")
+    async def on_deepgram_flux_update(stt, transcript):
+        logger.debug(f"On deepgram flux update: {transcript}")
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07c-interruptible-deepgram-flux.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,6 +10,7 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -17,6 +18,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_response_universal import (
     LLMContext,
     LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -26,13 +28,13 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.user_turn_strategies import ExternalUserTurnStrategies
 
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
@@ -52,31 +54,45 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = DeepgramFluxSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = DeepgramFluxSTTService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        settings=DeepgramFluxSTTService.Settings(
+            min_confidence=0.3,
+        ),
+    )
 
-    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
+    tts = DeepgramTTSService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        settings=DeepgramTTSService.Settings(
+            voice="aura-2-andromeda-en",
+        ),
+    )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=ExternalUserTurnStrategies(),
+            vad_analyzer=SileroVADAnalyzer(),
+        ),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -93,7 +109,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07c-interruptible-deepgram-http.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,16 +11,16 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -33,27 +33,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -66,31 +59,34 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = DeepgramHttpTTSService(
             api_key=os.getenv("DEEPGRAM_API_KEY"),
-            voice="aura-2-andromeda-en",
+            settings=DeepgramHttpTTSService.Settings(
+                voice="aura-2-andromeda-en",
+            ),
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            settings=OpenAILLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(context)
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,  # STT
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -107,7 +103,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         async def on_client_connected(transport, client):
             logger.info(f"Client connected")
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

examples/foundational/07c-interruptible-deepgram-sagemaker.py

@@ -0,0 +1,141 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
+from pipecat.services.deepgram.sagemaker.stt import DeepgramSageMakerSTTService
+from pipecat.services.deepgram.sagemaker.tts import DeepgramSageMakerTTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    # Initialize Deepgram SageMaker STT Service
+    # This requires:
+    # - AWS credentials configured (via environment variables or AWS CLI)
+    # - A deployed SageMaker endpoint with Deepgram model
+    stt = DeepgramSageMakerSTTService(
+        endpoint_name=os.getenv("SAGEMAKER_STT_ENDPOINT_NAME"),
+        region=os.getenv("AWS_REGION"),
+    )
+
+    # Initialize Deepgram SageMaker TTS Service
+    # This requires:
+    # - AWS credentials configured (via environment variables or AWS CLI)
+    # - A deployed SageMaker endpoint with Deepgram TTS model
+    tts = DeepgramSageMakerTTSService(
+        endpoint_name=os.getenv("SAGEMAKER_TTS_ENDPOINT_NAME"),
+        region=os.getenv("AWS_REGION"),
+        settings=DeepgramSageMakerTTSService.Settings(
+            voice="aura-2-andromeda-en",
+        ),
+    )
+
+    llm = AWSBedrockLLMService(
+        aws_region=os.getenv("AWS_REGION"),
+        settings=AWSBedrockLLMSettings(
+            model="us.amazon.nova-pro-v1:0",
+            temperature=0.8,
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
+
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            user_aggregator,  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            assistant_aggregator,  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07c-interruptible-deepgram-vad.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -7,21 +7,18 @@
 
 import os
 
-from deepgram import LiveOptions
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.frames.frames import (
-    InterruptionFrame,
-    LLMRunFrame,
-    UserStartedSpeakingFrame,
-    UserStoppedSpeakingFrame,
-)
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -30,13 +27,13 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.user_turn_strategies import ExternalUserTurnStrategies
 
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
@@ -58,32 +55,41 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(
         api_key=os.getenv("DEEPGRAM_API_KEY"),
-        live_options=LiveOptions(vad_events=True, utterance_end_ms="1000"),
+        settings=DeepgramSTTService.Settings(
+            vad_events=True,
+            utterance_end_ms="1000",
+        ),
     )
 
-    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
+    tts = DeepgramTTSService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        settings=DeepgramTTSService.Settings(
+            voice="aura-2-andromeda-en",
+        ),
+    )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -96,19 +102,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
-    @stt.event_handler("on_speech_started")
-    async def on_speech_started(stt, *args, **kwargs):
-        await task.queue_frames([InterruptionFrame(), UserStartedSpeakingFrame()])
-
-    @stt.event_handler("on_utterance_end")
-    async def on_utterance_end(stt, *args, **kwargs):
-        await task.queue_frames([UserStoppedSpeakingFrame()])
-
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07c-interruptible-deepgram.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,16 +10,16 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -32,27 +32,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -62,29 +55,35 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
+    tts = DeepgramTTSService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        settings=DeepgramTTSService.Settings(
+            voice="aura-2-andromeda-en",
+        ),
+    )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -101,7 +100,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07d-interruptible-elevenlabs-http.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,16 +11,16 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.elevenlabs.stt import ElevenLabsSTTService
@@ -33,27 +33,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -70,31 +63,34 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = ElevenLabsHttpTTSService(
             api_key=os.getenv("ELEVENLABS_API_KEY", ""),
-            voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
             aiohttp_session=session,
+            settings=ElevenLabsHttpTTSService.Settings(
+                voice=os.getenv("ELEVENLABS_VOICE_ID", ""),
+            ),
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            settings=OpenAILLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(context)
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -111,7 +107,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         async def on_client_connected(transport, client):
             logger.info(f"Client connected")
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

examples/foundational/07d-interruptible-elevenlabs.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,19 +10,19 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.elevenlabs.stt import ElevenLabsRealtimeSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -32,27 +32,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -60,34 +53,37 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = ElevenLabsRealtimeSTTService(api_key=os.getenv("ELEVENLABS_API_KEY"))
 
     tts = ElevenLabsTTSService(
         api_key=os.getenv("ELEVENLABS_API_KEY", ""),
-        voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
+        settings=ElevenLabsTTSService.Settings(
+            voice=os.getenv("ELEVENLABS_VOICE_ID", ""),
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -104,7 +100,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07e-interruptible-xai.py

@@ -1,58 +1,50 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-
 import os
 
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
-from pipecat.services.inworld.tts import InworldTTSService
-from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.xai.llm import GrokLLMService
+from pipecat.services.xai.tts import XAIHttpTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -60,43 +52,39 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    # Create an HTTP session
     async with aiohttp.ClientSession() as session:
         stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        # Inworld TTS Service - Unified streaming and non-streaming
-        # Set streaming=True for real-time audio, streaming=False for complete audio generation
-        streaming = True  # Toggle this to switch between modes
-
-        tts = InworldTTSService(
-            api_key=os.getenv("INWORLD_API_KEY", ""),
+        tts = XAIHttpTTSService(
+            api_key=os.getenv("XAI_API_KEY"),
             aiohttp_session=session,
-            voice_id="Ashley",
-            model="inworld-tts-1",
-            streaming=streaming,  # True: real-time chunks, False: complete audio then playback
+            settings=XAIHttpTTSService.Settings(
+                voice="eve",
+            ),
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = GrokLLMService(
+            api_key=os.getenv("XAI_API_KEY"),
+            settings=GrokLLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are very knowledgable about dogs. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(context)
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
+                stt,
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -113,7 +101,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         async def on_client_connected(transport, client):
             logger.info(f"Client connected")
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

examples/foundational/07f-interruptible-azure-http.py

@@ -0,0 +1,129 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.azure.llm import AzureLLMService
+from pipecat.services.azure.stt import AzureSTTService
+from pipecat.services.azure.tts import AzureHttpTTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = AzureSTTService(
+        api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+        region=os.getenv("AZURE_SPEECH_REGION"),
+    )
+
+    tts = AzureHttpTTSService(
+        api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+        region=os.getenv("AZURE_SPEECH_REGION"),
+    )
+
+    llm = AzureLLMService(
+        api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+        endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+        settings=AzureLLMService.Settings(
+            model=os.getenv("AZURE_CHATGPT_MODEL"),
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
+
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            user_aggregator,  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            assistant_aggregator,  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07f-interruptible-azure.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,16 +10,16 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.azure.llm import AzureLLMService
@@ -31,27 +31,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -72,28 +65,27 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = AzureLLMService(
         api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
         endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
-        model=os.getenv("AZURE_CHATGPT_MODEL"),
+        settings=AzureLLMService.Settings(
+            model=os.getenv("AZURE_CHATGPT_MODEL"),
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
     )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -110,7 +102,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07g-interruptible-openai-http.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,48 +10,41 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.nim.llm import NimLLMService
-from pipecat.services.riva.stt import RivaSTTService
-from pipecat.services.riva.tts import RivaTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.openai.stt import OpenAISTTService
+from pipecat.services.openai.tts import OpenAITTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -59,37 +52,50 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = RivaSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
+    stt = OpenAISTTService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAISTTService.Settings(
+            model="gpt-4o-transcribe",
+            prompt="Expect words related to dogs, such as breed names.",
+        ),
+    )
 
-    llm = NimLLMService(api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct")
+    tts = OpenAITTSService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAITTSService.Settings(
+            voice="ballad",
+        ),
+    )
 
-    tts = RivaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are very knowledgable about dogs. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
     task = PipelineTask(
         pipeline,
         params=PipelineParams(
+            audio_out_sample_rate=24000,
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
@@ -100,7 +106,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07g-interruptible-openai.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,48 +10,42 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.services.openai.stt import OpenAISTTService
+from pipecat.services.openai.stt import OpenAIRealtimeSTTService
 from pipecat.services.openai.tts import OpenAITTSService
+from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -59,35 +53,44 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = OpenAISTTService(
+    stt = OpenAIRealtimeSTTService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        model="gpt-4o-transcribe",
-        prompt="Expect words related to dogs, such as breed names.",
+        settings=OpenAIRealtimeSTTService.Settings(
+            model="gpt-4o-transcribe",
+            prompt="Expect words related to dogs, such as breed names.",
+            language=Language.EN,
+        ),
     )
 
-    tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
+    tts = OpenAITTSService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAITTSService.Settings(
+            voice="ballad",
+        ),
+    )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are very knowledgable about dogs. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are very knowledgable about dogs. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -105,7 +108,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07h-interruptible-openpipe.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,16 +11,16 @@ import time
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
@@ -32,27 +32,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -64,7 +57,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
     timestamp = int(time.time())
@@ -72,27 +67,26 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("OPENAI_API_KEY"),
         openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
         tags={"conversation_id": f"pipecat-{timestamp}"},
+        settings=OpenPipeLLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
     )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -109,7 +103,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07i-interruptible-xtts.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,16 +11,16 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -32,27 +32,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -66,31 +59,34 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = XTTSService(
             aiohttp_session=session,
-            voice_id="Claribel Dervla",
+            settings=XTTSService.Settings(
+                voice="Claribel Dervla",
+            ),
             base_url="http://localhost:8000",
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            settings=OpenAILLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(context)
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -107,7 +103,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         async def on_client_connected(transport, client):
             logger.info(f"Client connected")
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

examples/foundational/07j-interruptible-gladia-vad.py

@@ -0,0 +1,140 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.gladia.config import LanguageConfig
+from pipecat.services.gladia.stt import GladiaSTTService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.user_turn_strategies import ExternalUserTurnStrategies
+
+load_dotenv(override=True)
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = GladiaSTTService(
+        api_key=os.getenv("GLADIA_API_KEY", ""),
+        region=os.getenv("GLADIA_REGION"),
+        settings=GladiaSTTService.Settings(
+            language_config=LanguageConfig(
+                languages=[Language.EN],
+            ),
+            enable_vad=True,
+        ),
+    )
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY", ""),
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
+    )
+
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY", ""),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
+
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=ExternalUserTurnStrategies(),
+            vad_analyzer=SileroVADAnalyzer(),
+        ),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            user_aggregator,  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            assistant_aggregator,  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07j-interruptible-gladia.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,20 +10,20 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig
+from pipecat.services.gladia.config import LanguageConfig
 from pipecat.services.gladia.stt import GladiaSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transcriptions.language import Language
@@ -33,27 +33,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -64,7 +57,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = GladiaSTTService(
         api_key=os.getenv("GLADIA_API_KEY", ""),
         region=os.getenv("GLADIA_REGION"),
-        params=GladiaInputParams(
+        settings=GladiaSTTService.Settings(
             language_config=LanguageConfig(
                 languages=[Language.EN],
             )
@@ -73,30 +66,33 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY", ""),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY", ""),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -113,7 +109,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07k-interruptible-lmnt.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,16 +10,16 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -31,27 +31,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -61,29 +54,35 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = LmntTTSService(api_key=os.getenv("LMNT_API_KEY"), voice_id="morgan")
+    tts = LmntTTSService(
+        api_key=os.getenv("LMNT_API_KEY"),
+        settings=LmntTTSService.Settings(
+            voice="morgan",
+        ),
+    )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User respones
+            user_aggregator,  # User respones
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -100,7 +99,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07l-interruptible-groq.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,17 +10,16 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response import LLMUserAggregatorParams
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.groq.llm import GroqLLMService
@@ -32,27 +31,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -63,32 +55,30 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = GroqSTTService(api_key=os.getenv("GROQ_API_KEY"))
 
     llm = GroqLLMService(
-        api_key=os.getenv("GROQ_API_KEY"), model="meta-llama/llama-4-maverick-17b-128e-instruct"
+        api_key=os.getenv("GROQ_API_KEY"),
+        settings=GroqLLMService.Settings(
+            model="llama-3.1-8b-instant",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
     )
 
     tts = GroqTTSService(api_key=os.getenv("GROQ_API_KEY"))
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
-        context, user_params=LLMUserAggregatorParams(aggregation_timeout=0.05)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
     )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -105,7 +95,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07m-interruptible-aws-strands.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -9,12 +9,15 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesAppendFrame, LLMRunFrame
+from pipecat.frames.frames import LLMMessagesAppendFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.processors.frameworks.strands_agents import StrandsAgentsProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -35,24 +38,20 @@ except ImportError:
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -71,9 +70,9 @@ def build_agent(model_id: str, max_tokens: int):
     @tool
     def check_weather(location: str) -> str:
         if location.lower() == "san francisco":
-            return "The weather in San Francisco is sunny and 30 degrees."
+            return "The weather in San Francisco is sunny and 75 degrees."
         elif location.lower() == "sydney":
-            return "The weather in Sydney is cloudy and 20 degrees."
+            return "The weather in Sydney is cloudy and 60 degrees."
         else:
             return "I'm not sure about the weather in that location."
 
@@ -96,13 +95,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = AWSPollyTTSService(
         region="us-west-2",  # only specific regions support generative TTS
-        voice_id="Joanna",
-        params=AWSPollyTTSService.InputParams(engine="generative", rate="1.1"),
+        settings=AWSPollyTTSService.Settings(
+            voice="Joanna",
+            engine="generative",
+            rate="1.1",
+        ),
     )
 
     # Create Strands agent processor
     try:
-        agent = build_agent(model_id="us.anthropic.claude-3-5-haiku-20241022-v1:0", max_tokens=8000)
+        agent = build_agent(model_id="us.anthropic.claude-sonnet-4-6", max_tokens=8000)
         llm = StrandsAgentsProcessor(agent=agent)
         logger.info("Successfully created Strands agent for NAB customer service coaching")
     except Exception as e:
@@ -114,17 +116,20 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     # Setup context aggregators for message handling
     context = LLMContext()
-    context_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # Speech-to-text
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # Strands Agents processor
             tts,  # Text-to-speech
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -146,8 +151,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 LLMMessagesAppendFrame(
                     messages=[
                         {
-                            "role": "user",
-                            "content": f"Greet the user and introduce yourself.",
+                            "role": "developer",
+                            "content": f"Greet the user and introduce yourself. Don't use emojis.",
                         }
                     ],
                     run_llm=True,

examples/foundational/07m-interruptible-aws.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -8,16 +8,16 @@
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.aws.llm import AWSBedrockLLMService
@@ -29,27 +29,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -61,35 +54,37 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = AWSPollyTTSService(
         region="us-west-2",  # only specific regions support generative TTS
-        voice_id="Joanna",
-        params=AWSPollyTTSService.InputParams(engine="generative", rate="1.1"),
+        settings=AWSPollyTTSService.Settings(
+            voice="Joanna",
+            engine="generative",
+            rate="1.1",
+        ),
     )
 
     llm = AWSBedrockLLMService(
         aws_region="us-west-2",
-        model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
-        params=AWSBedrockLLMService.InputParams(temperature=0.8),
+        settings=AWSBedrockLLMService.Settings(
+            model="us.anthropic.claude-sonnet-4-6",
+            temperature=0.8,
+            # system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
     )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -106,7 +101,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07n-interruptible-gemini-image.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -25,16 +25,16 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.google.llm import GoogleLLMService
@@ -43,13 +43,11 @@ from pipecat.services.google.tts import GoogleTTSService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
-from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
@@ -57,8 +55,6 @@ transport_params = {
         video_out_enabled=True,
         video_out_width=1024,
         video_out_height=1024,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
@@ -66,8 +62,6 @@ transport_params = {
         video_out_enabled=True,
         video_out_width=1024,
         video_out_height=1024,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -76,40 +70,44 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
     stt = GoogleSTTService(
-        params=GoogleSTTService.InputParams(languages=Language.EN_US),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+        settings=GoogleSTTService.Settings(
+            languages=[Language.EN_US],
+        ),
     )
 
     tts = GoogleTTSService(
-        voice_id="en-US-Chirp3-HD-Charon",
-        params=GoogleTTSService.InputParams(language=Language.EN_US),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+        settings=GoogleTTSService.Settings(
+            voice="en-US-Chirp3-HD-Charon",
+            language=Language.EN_US,
+        ),
     )
 
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
-        model="gemini-2.5-flash-image",
+        settings=GoogleLLMService.Settings(
+            model="gemini-2.5-flash-image",
+            # model="gemini-3-pro-image-preview", # A more powerful model, but slower,
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
     )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # Gemini TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -126,7 +124,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation with a styled introduction
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07n-interruptible-gemini.py

@@ -1,43 +1,25 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""
-A conversational AI bot using Gemini for both LLM and TTS.
-
-This example demonstrates how to use Gemini's TTS capabilities with the new
-GeminiTTSService, which uses Gemini's TTS-specific models instead of Google Cloud TTS.
-
-Features showcased:
-- Gemini LLM for conversation
-- Gemini TTS with natural voice control
-- Support for different voice personalities
-- Style and tone control through natural language prompts
-
-Run with:
-    python examples/foundational/gemini-tts.py
-
-Make sure to set your environment variables:
-    export GOOGLE_API_KEY=your_api_key_here
-"""
 
 import os
 
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.google.llm import GoogleLLMService
@@ -50,27 +32,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -79,52 +54,62 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot with Gemini TTS")
 
     stt = GoogleSTTService(
-        params=GoogleSTTService.InputParams(languages=Language.EN_US),
+        settings=GoogleSTTService.Settings(
+            languages=[Language.EN_US],
+        ),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
     )
 
     tts = GeminiTTSService(
-        api_key=os.getenv("GOOGLE_API_KEY"),
-        model="gemini-2.5-flash-preview-tts",  # TTS-specific model
-        voice_id="Charon",
-        params=GeminiTTSService.InputParams(language=Language.EN_US),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+        settings=GeminiTTSService.Settings(
+            model="gemini-2.5-flash-tts",
+            voice="Charon",
+            language=Language.EN_US,
+            prompt="You are a helpful AI assistant. Speak in a natural, conversational tone.",
+        ),
     )
 
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         model="gemini-2.5-flash",
+        settings=GoogleLLMService.Settings(
+            system_instruction="""You are a helpful assistant in a voice conversation.
+
+            IMPORTANT: You're using Gemini TTS which supports expressive markup tags. You can use these tags in your responses:
+            - [sigh] - Insert a sigh sound
+            - [laughing] - Insert a laugh
+            - [uhm] - Insert a hesitation sound
+            - [whispering] - Speak the next part in a whisper
+            - [shouting] - Speak the next part louder
+            - [extremely fast] - Speak the next part very quickly
+            - [short pause], [medium pause], [long pause] - Add pauses for dramatic effect
+
+            Examples:
+            - "Well [sigh] that's a tricky question."
+            - "[laughing] That's a great joke!"
+            - "[whispering] Let me tell you a secret."
+            - "The answer is... [long pause] ...42!"
+
+            Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Keep responses concise. Respond to what the user said in a creative and helpful way.""",
+        ),
     )
 
-    # System message that instructs the AI on how to speak
-    messages = [
-        {
-            "role": "system",
-            "content": """You are a helpful AI assistant in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
-
-            IMPORTANT: Since you're using Gemini TTS which supports natural voice control, you can include speaking instructions in your responses. For example:
-            - "Say cheerfully: Welcome to our conversation!"
-            - "Read this in a calm, professional tone: Here are the details you requested."
-            - "Speak in an excited whisper: I have some great news to share!"
-            - "Say slowly and clearly: Let me explain this step by step."
-
-            Feel free to use natural language instructions to control your voice style, tone, pace, and emotion. The TTS system will interpret these instructions and adjust the speech accordingly.
-
-            Your output will be converted to audio, so avoid special characters in your answers. Respond to what the user said in a creative and helpful way.""",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # Gemini TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -140,11 +125,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
-        # Kick off the conversation with a styled introduction
-        messages.append(
+        # Kick off the conversation
+        context.add_message(
             {
-                "role": "system",
-                "content": "Say cheerfully and warmly: Hello! I'm your AI assistant powered by Gemini's new TTS technology. I can speak with different voices, tones, and styles. How can I help you today?",
+                "role": "developer",
+                "content": "You are an AI assistant. You can help with a variety of tasks. Introduce yourself and ask the user what they would like to know.",
             }
         )
         await task.queue_frames([LLMRunFrame()])

examples/foundational/07n-interruptible-google-http.py

@@ -0,0 +1,139 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.google.llm import GoogleLLMService
+from pipecat.services.google.stt import GoogleSTTService
+from pipecat.services.google.tts import GoogleHttpTTSService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = GoogleSTTService(
+        settings=GoogleSTTService.Settings(
+            languages=[Language.EN_US],
+            # Add model to use a specific model
+            # model="chirp_3",
+        ),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+        location="us",
+    )
+
+    tts = GoogleHttpTTSService(
+        settings=GoogleHttpTTSService.Settings(
+            voice="en-US-Chirp3-HD-Charon",
+            language=Language.EN_US,
+        ),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+    )
+
+    llm = GoogleLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        settings=GoogleLLMService.Settings(
+            model="gemini-2.5-flash",
+            # force a certain amount of thinking if you want it
+            # thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
+
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            user_aggregator,  # User respones
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            assistant_aggregator,  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07n-interruptible-google.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,16 +10,16 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.google.llm import GoogleLLMService
@@ -32,27 +32,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -61,43 +54,48 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
     stt = GoogleSTTService(
-        params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
+        settings=GoogleSTTService.Settings(
+            languages=[Language.EN_US],
+            # Add model to use a specific model
+            # model="chirp_3",
+        ),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
         location="us",
     )
 
     tts = GoogleTTSService(
-        voice_id="en-US-Chirp3-HD-Charon",
-        params=GoogleTTSService.InputParams(language=Language.EN_US),
+        settings=GoogleTTSService.Settings(
+            voice="en-US-Chirp3-HD-Charon",
+            language=Language.EN_US,
+        ),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
     )
 
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
-        model="gemini-2.5-flash",
-        # turn on thinking if you want it
-        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),)
+        settings=GoogleLLMService.Settings(
+            model="gemini-2.5-flash",
+            # force a certain amount of thinking if you want it
+            # thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096),
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
     )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User respones
+            user_aggregator,  # User respones
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -114,7 +112,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07o-interruptible-assemblyai-turn-detection.py

@@ -0,0 +1,180 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.assemblyai.stt import AssemblyAISTTService
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.user_turn_strategies import ExternalUserTurnStrategies
+
+load_dotenv(override=True)
+
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    """AssemblyAI u3-rt-pro with Built-in Turn Detection
+
+    This example demonstrates using AssemblyAI's u3-rt-pro Speech-to-Text model
+    with AssemblyAI's built-in turn detection for more natural conversation flow.
+
+    Key features:
+
+    1. AssemblyAI Turn Detection
+       - Set `vad_force_turn_endpoint=False` to use AssemblyAI's built-in turn detection
+       - AssemblyAI's model determines when user starts/stops speaking
+       - Uses `ExternalUserTurnStrategies` to delegate turn control to AssemblyAI
+       - More natural turn detection based on speech patterns and pauses
+
+    2. Advanced Turn Detection Tuning
+       - `min_turn_silence`: Minimum silence (ms) when confident about end-of-turn.
+         Lower values = faster responses. Default: 100ms
+       - `max_turn_silence`: Maximum silence (ms) before forcing end-of-turn.
+         Prevents long pauses. Default: 1000ms
+
+    3. Prompt-Based Transcription Enhancement
+       - Use `prompt` parameter to improve accuracy for specific names/terms
+       - Particularly useful for proper nouns, technical terms, domain vocabulary
+       - Example: "Names: Xiomara, Saoirse, Krzystof. Technical terms: API, OAuth."
+
+    4. Speaker Diarization (Optional)
+       - Enable with `speaker_labels=True`
+       - Automatically identifies different speakers in multi-party conversations
+       - TranscriptionFrame includes speaker_id field (e.g., "Speaker A", "Speaker B")
+
+    5. Language Detection (Optional, multilingual model only)
+       - Enable with `language_detection=True`
+       - Automatically detects spoken language
+       - Available with universal-streaming-multilingual model
+
+    For more information: https://www.assemblyai.com/docs/speech-to-text/streaming
+    """
+    logger.info(f"Starting bot")
+
+    stt = AssemblyAISTTService(
+        api_key=os.getenv("ASSEMBLYAI_API_KEY"),
+        vad_force_turn_endpoint=False,  # Use AssemblyAI's built-in turn detection
+        settings=AssemblyAISTTService.Settings(
+            model="u3-rt-pro",
+            # Optional: Tune turn detection timing (defaults shown below)
+            # min_turn_silence=100,  # Default
+            # max_turn_silence=1000,  # Default
+            # Optional: Boost accuracy for specific names/terms
+            # keyterms_prompt=["Xiomara", "Saoirse", "Krzystof", "API", "OAuth"],
+            # Optional: Enable speaker diarization
+            # speaker_labels=True,
+        ),
+    )
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
+    )
+
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
+
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=ExternalUserTurnStrategies(),
+            vad_analyzer=SileroVADAnalyzer(),
+        ),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            user_aggregator,  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            assistant_aggregator,  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07o-interruptible-assemblyai.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,16 +10,16 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.assemblyai.stt import AssemblyAISTTService
@@ -32,27 +32,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -66,30 +59,33 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -106,7 +102,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07p-interruptible-krisp-viva.py

@@ -1,9 +1,26 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
+"""Interruptible bot with Krisp VIVA noise filtering and turn detection.
+
+This example demonstrates a conversational bot with:
+- Krisp VIVA noise reduction on incoming audio
+- Krisp VIVA Turn detection for natural interruptions
+- Voice activity detection (VAD)
+
+Required environment variables:
+- KRISP_VIVA_FILTER_MODEL_PATH: Path to the Krisp noise filter model file (.kef)
+- KRISP_VIVA_TURN_MODEL_PATH: Path to the Krisp turn detection model file (.kef)
+- DEEPGRAM_API_KEY: Deepgram API key for STT/TTS
+- OPENAI_API_KEY: OpenAI API key for LLM
+
+Optional environment variables:
+- KRISP_NOISE_SUPPRESSION_LEVEL: Noise suppression level 0-100 (default: 100)
+  Higher values = more aggressive noise reduction
+"""
 
 import os
 
@@ -11,51 +28,52 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.filters.krisp_viva_filter import KrispVivaFilter
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.turn.krisp_viva_turn import KrispVivaTurn
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
+from pipecat.metrics.metrics import TurnMetricsData
+from pipecat.observers.loggers.metrics_log_observer import MetricsLogObserver
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
-from pipecat.services.deepgram.tts import DeepgramTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+
+krisp_viva_filter = KrispVivaFilter()
+
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-        audio_in_filter=KrispVivaFilter(),
+        audio_in_filter=krisp_viva_filter,
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-        audio_in_filter=KrispVivaFilter(),
+        audio_in_filter=krisp_viva_filter,
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-        audio_in_filter=KrispVivaFilter(),
+        audio_in_filter=krisp_viva_filter,
     ),
 }
 
@@ -65,29 +83,40 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
+    )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=KrispVivaTurn())]
+            ),
+            vad_analyzer=SileroVADAnalyzer(),  # or KrispVivaVadAnalyzer
+        ),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -98,13 +127,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_usage_metrics=True,
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        observers=[MetricsLogObserver(include_metrics={TurnMetricsData})],
     )
 
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07p-interruptible-krisp.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,16 +11,16 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.filters.krisp_filter import KrispFilter
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -32,29 +32,22 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         audio_in_filter=KrispFilter(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         audio_in_filter=KrispFilter(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         audio_in_filter=KrispFilter(),
     ),
 }
@@ -65,29 +58,35 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
+    tts = DeepgramTTSService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        settings=DeepgramTTSService.Settings(
+            voice="aura-helios-en",
+        ),
+    )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -104,7 +103,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07q-interruptible-rime-http.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,16 +11,16 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -33,27 +33,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -67,32 +60,36 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = RimeHttpTTSService(
             api_key=os.getenv("RIME_API_KEY", ""),
-            voice_id="luna",
+            settings=RimeHttpTTSService.Settings(
+                voice="luna",
+                model="arcana",
+            ),
             model="arcana",
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            settings=OpenAILLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(context)
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -109,7 +106,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         async def on_client_connected(transport, client):
             logger.info(f"Client connected")
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

examples/foundational/07q-interruptible-rime.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,16 +10,16 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -31,27 +31,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -63,30 +56,33 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = RimeTTSService(
         api_key=os.getenv("RIME_API_KEY", ""),
-        voice_id="rex",
+        settings=RimeTTSService.Settings(
+            voice="luna",
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -103,7 +99,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07r-interruptible-nvidia.py

@@ -0,0 +1,122 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.nvidia.llm import NvidiaLLMService
+from pipecat.services.nvidia.stt import NvidiaSTTService
+from pipecat.services.nvidia.tts import NvidiaTTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = NvidiaSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
+
+    llm = NvidiaLLMService(
+        api_key=os.getenv("NVIDIA_API_KEY"),
+        settings=NvidiaLLMService.Settings(
+            model="meta/llama-3.3-70b-instruct",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
+
+    tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            user_aggregator,  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            assistant_aggregator,  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07s-interruptible-google-audio-in.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -12,10 +12,7 @@ from dotenv import load_dotenv
 from google.genai.types import Content, Part
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import (
     Frame,
     InputAudioRawFrame,
@@ -32,7 +29,10 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.processors.frame_processor import FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -48,12 +48,12 @@ load_dotenv(override=True)
 
 marker = "|----|"
 system_message = f"""
-You are a helpful LLM in a WebRTC call. Your goals are to be helpful and brief in your responses.
+You are a helpful LLM in a voice call. Your goals are to be helpful and brief in your responses.
 
 You are expert at transcribing audio to text. You will receive a mixture of audio and text input. When
 asked to transcribe what the user said, output an exact, word-for-word transcription.
 
-Your output will be converted to audio so don't include special characters in your answers.
+Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points.
 
 Each time you answer, you should respond in three parts.
 
@@ -96,7 +96,7 @@ class UserAudioCollector(FrameProcessor):
             self._user_speaking = True
         elif isinstance(frame, UserStoppedSpeakingFrame):
             self._user_speaking = False
-            self._context.add_audio_frames_message(audio_frames=self._audio_frames)
+            await self._context.add_audio_frames_message(audio_frames=self._audio_frames)
             await self._user_context_aggregator.push_frame(LLMRunFrame())
 
         elif isinstance(frame, InputAudioRawFrame):
@@ -193,27 +193,20 @@ class TranscriptionContextFixup(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -223,31 +216,29 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
-        model="gemini-2.5-flash",
-        # turn on thinking if you want it
-        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),
+        settings=GoogleLLMService.Settings(
+            model="gemini-2.5-flash",
+            system_instruction=system_message,
+            # force a certain amount of thinking if you want it
+            # thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
+        ),
     )
 
     tts = GoogleTTSService(
-        voice_id="en-US-Chirp3-HD-Charon",
+        settings=GoogleTTSService.Settings(
+            voice="en-US-Chirp3-HD-Charon",
+            language=Language.EN_US,
+        ),
         params=GoogleTTSService.InputParams(language=Language.EN_US),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
     )
 
-    messages = [
-        {
-            "role": "system",
-            "content": system_message,
-        },
-        {
-            "role": "user",
-            "content": "Start by saying hello.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
-    audio_collector = UserAudioCollector(context, context_aggregator.user())
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
+    audio_collector = UserAudioCollector(context, user_aggregator)
     pull_transcript_out_of_llm_output = TranscriptExtractor(context)
     fixup_context_messages = TranscriptionContextFixup(context)
 
@@ -255,12 +246,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             audio_collector,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             pull_transcript_out_of_llm_output,
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
             fixup_context_messages,
         ]
     )
@@ -278,7 +269,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07t-interruptible-fish.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,16 +10,16 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -32,27 +32,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -64,30 +57,33 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = FishAudioTTSService(
         api_key=os.getenv("FISH_API_KEY"),
-        model="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
+        settings=FishAudioTTSService.Settings(
+            voice="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -104,7 +100,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07v-interruptible-neuphonic-http.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,16 +11,16 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -33,27 +33,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -67,31 +60,34 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = NeuphonicHttpTTSService(
             api_key=os.getenv("NEUPHONIC_API_KEY"),
-            voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
+            settings=NeuphonicHttpTTSService.Settings(
+                voice="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
+            ),
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            settings=OpenAILLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(context)
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -108,7 +104,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         async def on_client_connected(transport, client):
             logger.info(f"Client connected")
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

examples/foundational/07v-interruptible-neuphonic.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,16 +10,16 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -31,27 +31,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -63,30 +56,33 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = NeuphonicTTSService(
         api_key=os.getenv("NEUPHONIC_API_KEY"),
-        voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
+        settings=NeuphonicTTSService.Settings(
+            voice="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -103,7 +99,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07w-interruptible-fal.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -7,19 +7,20 @@
 
 import os
 
+import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
@@ -32,27 +33,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -60,63 +54,70 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = FalSTTService(
-        api_key=os.getenv("FAL_KEY"),
-    )
+    async with aiohttp.ClientSession() as session:
+        stt = FalSTTService(
+            api_key=os.getenv("FAL_KEY"),
+            aiohttp_session=session,
+        )
 
-    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-    )
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            settings=CartesiaTTSService.Settings(
+                voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            ),
+        )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            settings=OpenAILLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                user_aggregator,  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                assistant_aggregator,  # Assistant spoken responses
+            ]
+        )
 
-    pipeline = Pipeline(
-        [
-            transport.input(),  # Transport user input
-            stt,  # STT
-            context_aggregator.user(),  # User responses
-            llm,  # LLM
-            tts,  # TTS
-            transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
-        ]
-    )
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
 
-    task = PipelineTask(
-        pipeline,
-        params=PipelineParams(
-            enable_metrics=True,
-            enable_usage_metrics=True,
-        ),
-        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
-    )
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info(f"Client connected")
+            # Kick off the conversation.
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
+            await task.queue_frames([LLMRunFrame()])
 
-    @transport.event_handler("on_client_connected")
-    async def on_client_connected(transport, client):
-        logger.info(f"Client connected")
-        # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([LLMRunFrame()])
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+            await task.cancel()
 
-    @transport.event_handler("on_client_disconnected")
-    async def on_client_disconnected(transport, client):
-        logger.info(f"Client disconnected")
-        await task.cancel()
+        runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
 
-    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
-
-    await runner.run(task)
+        await runner.run(task)
 
 
 async def bot(runner_args: RunnerArguments):

examples/foundational/07x-interruptible-local.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,18 +11,16 @@ import sys
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
-from pipecat.runner.types import RunnerArguments
-from pipecat.runner.utils import create_transport
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
@@ -39,8 +37,6 @@ async def main():
         LocalAudioTransportParams(
             audio_in_enabled=True,
             audio_out_enabled=True,
-            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         )
     )
 
@@ -48,30 +44,33 @@ async def main():
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -83,7 +82,7 @@ async def main():
         ),
     )
 
-    messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+    context.add_message({"role": "developer", "content": "Please introduce yourself to the user."})
     await task.queue_frames([LLMRunFrame()])
 
     runner = PipelineRunner()

examples/foundational/07y-interruptible-minimax.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,16 +11,16 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -34,27 +34,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -70,30 +63,33 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             api_key=os.getenv("MINIMAX_API_KEY", ""),
             group_id=os.getenv("MINIMAX_GROUP_ID", ""),
             aiohttp_session=session,
-            params=MiniMaxHttpTTSService.InputParams(language=Language.EN),
+            settings=MiniMaxHttpTTSService.Settings(
+                language=Language.EN,
+            ),
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            settings=OpenAILLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(context)
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -110,7 +106,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         async def on_client_connected(transport, client):
             logger.info(f"Client connected")
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

examples/foundational/07z-interruptible-sarvam-http.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,18 +11,19 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.sarvam.llm import SarvamLLMService
 from pipecat.services.sarvam.stt import SarvamSTTService
 from pipecat.services.sarvam.tts import SarvamHttpTTSService
 from pipecat.transcriptions.language import Language
@@ -33,27 +34,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -65,36 +59,41 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async with aiohttp.ClientSession() as session:
         stt = SarvamSTTService(
             api_key=os.getenv("SARVAM_API_KEY"),
-            model="saarika:v2.5",
+            settings=SarvamSTTService.Settings(
+                model="saarika:v2.5",
+            ),
         )
 
         tts = SarvamHttpTTSService(
             api_key=os.getenv("SARVAM_API_KEY"),
             aiohttp_session=session,
-            params=SarvamHttpTTSService.InputParams(language=Language.EN),
+            settings=SarvamHttpTTSService.Settings(
+                language=Language.EN_IN,
+            ),
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = SarvamLLMService(
+            api_key=os.getenv("SARVAM_API_KEY"),
+            settings=SarvamLLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(context)
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -111,8 +110,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         async def on_client_connected(transport, client):
             logger.info(f"Client connected")
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
+            await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):

examples/foundational/07z-interruptible-sarvam.py

@@ -1,30 +1,27 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-
-import asyncio
 import os
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import LLMRunFrame, TTSUpdateSettingsFrame
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.sarvam.llm import SarvamLLMService
 from pipecat.services.sarvam.stt import SarvamSTTService
 from pipecat.services.sarvam.tts import SarvamTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -34,27 +31,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -64,35 +54,40 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = SarvamSTTService(
         api_key=os.getenv("SARVAM_API_KEY"),
-        model="saarika:v2.5",
+        settings=SarvamSTTService.Settings(
+            model="saaras:v3",
+        ),
     )
 
     tts = SarvamTTSService(
         api_key=os.getenv("SARVAM_API_KEY"),
-        model="bulbul:v2",
-        voice_id="manisha",
+        settings=SarvamTTSService.Settings(
+            model="bulbul:v3",
+            voice="shubh",
+        ),
+    )
+    llm = SarvamLLMService(
+        api_key=os.getenv("SARVAM_API_KEY"),
+        settings=SarvamLLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
     )
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -101,6 +96,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            allow_interruptions=True,
         ),
     )
 
@@ -108,7 +104,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
         # Optionally, you can wait for 30 seconds and then change the voice.

examples/foundational/07za-interruptible-soniox.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,21 +10,22 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.soniox.stt import SonioxSTTService
+from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -35,20 +36,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -58,34 +53,43 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = SonioxSTTService(
         api_key=os.getenv("SONIOX_API_KEY"),
+        settings=SonioxSTTService.Settings(
+            # Add language hints to use a specific language
+            # Add strict mode to enforce the language hints
+            language_hints=[Language.EN],
+            language_hints_strict=True,
+        ),
     )
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
     task = PipelineTask(
@@ -101,7 +105,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07zb-interruptible-inworld-http.py

@@ -0,0 +1,137 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame, TTSTextFrame
+from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.inworld.tts import InworldHttpTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_output import BaseOutputTransport
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info("Starting bot")
+
+    async with aiohttp.ClientSession() as session:
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = InworldHttpTTSService(
+            api_key=os.getenv("INWORLD_API_KEY", ""),
+            aiohttp_session=session,
+            streaming=True,
+            settings=InworldHttpTTSService.Settings(
+                voice="Ashley",
+            ),
+            # Set to False for non-streaming mode or True for streaming mode.
+        )
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            settings=OpenAILLMService.Settings(
+                system_instruction="You are a helpful AI demonstrating Inworld AI's TTS. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a friendly and helpful way.",
+            ),
+        )
+
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                stt,
+                user_aggregator,
+                llm,
+                tts,
+                transport.output(),
+                assistant_aggregator,
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+            observers=[
+                DebugLogObserver(
+                    frame_types={
+                        TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
+                    }
+                ),
+            ],
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
+
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info("Client connected")
+            # Kick off the conversation.
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
+            await task.queue_frames([LLMRunFrame()])
+
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info("Client disconnected")
+            await task.cancel()
+
+        runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+        await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07zb-interruptible-inworld.py

@@ -0,0 +1,125 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.inworld.tts import InworldTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info("Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = InworldTTSService(
+        api_key=os.getenv("INWORLD_API_KEY", ""),
+        settings=InworldTTSService.Settings(
+            voice="Ashley",
+            temperature=1.1,
+        ),
+    )
+
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful AI demonstrating Inworld AI's TTS. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a friendly and helpful way.",
+        ),
+    )
+
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            user_aggregator,
+            llm,
+            tts,
+            transport.output(),
+            assistant_aggregator,
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info("Client connected")
+        # Kick off the conversation.
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info("Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07zc-interruptible-asyncai-http.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,16 +11,16 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.asyncai.tts import AsyncAIHttpTTSService
@@ -33,27 +33,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 load_dotenv(override=True)
 
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -67,31 +60,34 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = AsyncAIHttpTTSService(
             api_key=os.getenv("ASYNCAI_API_KEY", ""),
-            voice_id=os.getenv("ASYNCAI_VOICE_ID", "e0f39dc4-f691-4e78-bba5-5c636692cc04"),
+            settings=AsyncAIHttpTTSService.Settings(
+                voice="e0f39dc4-f691-4e78-bba5-5c636692cc04",
+            ),
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            settings=OpenAILLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(context)
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 
@@ -108,7 +104,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         async def on_client_connected(transport, client):
             logger.info(f"Client connected")
             # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            context.add_message(
+                {"role": "developer", "content": "Please introduce yourself to the user."}
+            )
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

examples/foundational/07zc-interruptible-asyncai.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -10,49 +10,42 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
+from pipecat.services.asyncai.tts import AsyncAITTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.services.playht.tts import PlayHTTTSService
-from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -62,34 +55,35 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = PlayHTTTSService(
-        user_id=os.getenv("PLAYHT_USER_ID"),
-        api_key=os.getenv("PLAYHT_API_KEY"),
-        voice_url="s3://voice-cloning-zero-shot/e46b4027-b38d-4d24-b292-38fbca2be0ef/original/manifest.json",
-        params=PlayHTTTSService.InputParams(language=Language.EN),
+    tts = AsyncAITTSService(
+        api_key=os.getenv("ASYNCAI_API_KEY", ""),
+        settings=AsyncAITTSService.Settings(
+            voice="e0f39dc4-f691-4e78-bba5-5c636692cc04",
+        ),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAILLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 
@@ -106,7 +100,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")