Fix await usage in transcription timeout task

.claude-plugin/marketplace.json

@@ -1,27 +0,0 @@
-{
-  "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

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

.claude/skills/changelog/SKILL.md

@@ -7,30 +7,23 @@ Create changelog files for the important commits in this PR. The PR number is pr
 
 ## 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:
+1. 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`
+2. For each significant change, create a changelog file in the `changelog/` folder using the format:
    - `{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}.added.2.md`, `{PR_NUMBER}.added.3.md` - for additional new features
    - `{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.
+3. Each changelog file should at least contain a main single line starting with `- ` followed by a clear description of the change.
 
-5. If the change is complicated, changelog files can have indented lines after the main line with additional details or code samples.
+4. 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.
+5. Use ⚠️ emoji prefix for breaking changes.
 
 ## Example
 

.claude/skills/cleanup/SKILL.md

@@ -1,307 +0,0 @@
-# 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

@@ -1,107 +0,0 @@
----
-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

@@ -3,20 +3,21 @@ 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.
+Document a Python module and its classes using Google-style docstrings following project conventions. The class name is provided as an argument.
 
 ## Instructions
 
-1. Determine what to document based on the argument:
+1. First, find the class in the codebase:
+   ```
+   Search for "class ClassName" in src/pipecat/
+   ```
 
-   **If a module path is provided** (e.g. `src/pipecat/audio/vad/vad_analyzer.py`):
-   - Use that file directly
+2. If multiple files contain that class name:
+   - List all matches with their file paths
+   - Ask the user which one they want to document
+   - Wait for confirmation before proceeding
 
-   **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:
+3. 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
 

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

@@ -1,28 +0,0 @@
----
-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

@@ -1,306 +0,0 @@
----
-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

@@ -1,79 +0,0 @@
-# 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/coverage.yaml

@@ -29,22 +29,11 @@ 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 deepgram \
-            --extra google \
-            --extra langchain \
-            --extra livekit \
-            --extra piper \
-            --extra sagemaker \
-            --extra tracing \
-            --extra websocket
+          uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain --extra livekit --extra websocket
 
       - name: Run tests with coverage
         run: |

.github/workflows/generate-changelog.yml

@@ -86,7 +86,7 @@ jobs:
           fi
 
           # Validate fragment types
-          VALID_TYPES="added changed deprecated removed fixed performance security other"
+          VALID_TYPES="added changed deprecated removed fixed security other"
           INVALID_FRAGMENTS=""
 
           for file in changelog/*.md; do

.github/workflows/python-compatibility.yaml

@@ -14,7 +14,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ['3.10.19', '3.11.14', '3.12.12', '3.13.12']
+        python-version: ['3.10.18', '3.11.13', '3.12.11', '3.13.5']
 
     name: Python ${{ matrix.python-version }}
     steps:
@@ -40,10 +40,20 @@ jobs:
           uv python install ${{ matrix.python-version }}
           uv python pin ${{ matrix.python-version }}
 
-      - name: Test uv sync with all extras
+      - name: Test uv sync with all extras (Python < 3.13)
+        if: "!startsWith(matrix.python-version, '3.13.')"
         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 local-smart-turn \
+            --no-extra moondream \
+            --no-extra mlx-whisper
+
       - name: Verify installation
         run: |
           uv run python --version

.github/workflows/tests.yaml

@@ -33,22 +33,11 @@ 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 deepgram \
-            --extra google \
-            --extra langchain \
-            --extra livekit \
-            --extra piper \
-            --extra sagemaker \
-            --extra tracing \
-            --extra websocket
+          uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain --extra livekit --extra websocket
 
       - name: Test with pytest
         run: |

.github/workflows/update-docs.yml

@@ -1,147 +0,0 @@
-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"

CLAUDE.md

@@ -1,157 +0,0 @@
-# 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

@@ -25,6 +25,7 @@ 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
@@ -109,6 +110,7 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel
 #### Key requirements:
 
 - **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
@@ -233,79 +235,22 @@ def can_generate_metrics(self) -> bool:
 
 ### Dynamic Settings Updates
 
-STT, LLM, and TTS services support runtime configuration changes via `*UpdateSettingsFrame`s (e.g. `STTUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `LLMUpdateSettingsFrame`).
-
-Each service declares a settings dataclass that extends the appropriate base (`STTSettings`, `TTSSettings`, `LLMSettings`). Fields default to `NOT_GIVEN` so that update objects can represent sparse deltas:
+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.
 
 ```python
-from dataclasses import dataclass, field
+async def set_language(self, language: Language):
+    """Set the recognition language and reconnect.
 
-from pipecat.services.settings import STTSettings, NOT_GIVEN
-
-@dataclass
-class MySTTSettings(STTSettings):
-    """Settings for my STT service.
-
-    Parameters:
-        region: Cloud region for the service.
+    Args:
+        language: The language to use for speech recognition.
     """
-
-    region: str = field(default_factory=lambda: NOT_GIVEN)
-```
-
-The service stores its current settings in `self._settings` and declares the type with a class-level annotation for editor support:
-
-```python
-class MySTTService(STTService):
-    _settings: MySTTSettings
-
-    def __init__(self, *, model: str, language: str, region: str, **kwargs):
-        # An initial value should be provided for every settings field.
-        # This will be validated at service start.
-        # (If you track sample_rate, it can be a placeholder value like 0; see
-        # "Sample Rate Handling").
-        super().__init__(
-            settings=MySTTSettings(model=model, language=language, region=region), **kwargs
-        )
-```
-
-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: STTSettings) -> dict[str, Any]:
-    """Apply a settings update, reconfiguring the recognizer if needed."""
-    changed = await super()._update_settings(update)
-
-    if not changed:
-        return changed
-
+    logger.info(f"Switching STT language to: [{language}]")
+    self._settings["language"] = language
     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: STTSettings) -> 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
-```
+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.
 
 ### Sample Rate Handling
 
@@ -315,7 +260,7 @@ 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_sample_rate = self.sample_rate
+    self._settings["output_format"]["sample_rate"] = self.sample_rate
     await self._connect()
 ```
 

CONTRIBUTING.md

@@ -49,12 +49,12 @@ Every pull request that makes a user-facing change should include a changelog en
    ```
 
 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.)
 
@@ -80,6 +80,7 @@ Every pull request that makes a user-facing change should include a changelog en
 
 ```markdown
 - Updated service configuration:
+
   - Changed default timeout to 30 seconds
   - Added retry logic for failed connections
 ```
@@ -104,6 +105,7 @@ changelog/1234.changed.2.md
 
 ```markdown
 - Updated service configuration:
+
   - Changed default timeout to 30 seconds
   - Added retry logic for failed connections
 ```

README.md

@@ -55,16 +55,6 @@ 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.
-
 ### 📺️ Pipecat TV Channel
 
 Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.youtube.com/playlist?list=PLzU2zoMTQIHjqC3v4q2XVSR3hGSzwKFwH) channel.
@@ -81,19 +71,19 @@ 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), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [Hathora](https://docs.pipecat.ai/server/services/stt/hathora), [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), [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), [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), [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), [Hathora](https://docs.pipecat.ai/server/services/tts/hathora), [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), [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), [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)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+| 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), [Hathora](https://docs.pipecat.ai/server/services/stt/hathora), [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), [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), [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), [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), [Hathora](https://docs.pipecat.ai/server/services/tts/hathora), [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), [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), [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)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 
@@ -173,15 +163,6 @@ 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/3510.added.2.md

@@ -0,0 +1 @@
+- Added `add_reached_upstream_filter()` and `add_reached_downstream_filter()` methods to `PipelineTask` for appending frame types.

changelog/3510.added.md

@@ -0,0 +1 @@
+- Added `reached_upstream_types` and `reached_downstream_types` read-only properties to `PipelineTask` for inspecting current frame filters.

changelog/3510.changed.3.md

@@ -0,0 +1 @@
+- Changed frame filter storage from tuples to sets in `PipelineTask`.

changelog/3519.added.2.md

@@ -0,0 +1 @@
+- Added `RTVIProcessor.create_rtvi_observer()` factory method for creating RTVI observers.

changelog/3519.added.3.md

@@ -0,0 +1 @@
+- Added `FrameProcessor.broadcast_frame_instance(frame)` method to broadcast a frame instance by extracting its fields and creating new instances for each direction.

changelog/3519.added.md

@@ -0,0 +1 @@
+- `PipelineTask` now automatically adds `RTVIProcessor` and registers `RTVIObserver` when `enable_rtvi=True` (default), simplifying pipeline setup.

changelog/3519.fixed.2.md

@@ -0,0 +1 @@
+- Fixed `FrameProcessor.broadcast_frame()` to deep copy kwargs, preventing shared mutable references between the downstream and upstream frame instances.

changelog/3519.fixed.md

@@ -0,0 +1 @@
+- Transports now properly broadcast `InputTransportMessageFrame` frames both upstream and downstream instead of only pushing downstream.

changelog/3520.added.md

@@ -0,0 +1 @@
+- Added `video_out_codec` parameter to `TransportParams` allowing configuration of the preferred video codec (e.g., `"VP8"`, `"H264"`, `"H265"`) for video output in `DailyTransport`.

changelog/3523.added.md

@@ -0,0 +1 @@
+- Added `location` parameter to Google TTS services (`GoogleHttpTTSService`, `GoogleTTSService`, `GeminiTTSService`) for regional endpoint support.

changelog/3525.added.md

@@ -0,0 +1 @@
+- Added new `SMART_TURN_LOG_DATA` environment variable, which causes Smart Turn input data to be saved to disk

changelog/3531.changed.md

@@ -0,0 +1,2 @@
+- Changed default Inworld TTS model from `inworld-tts-1` to                      
+ `inworld-tts-1.5-max`.

changelog/3848.changed.md

@@ -1 +0,0 @@
-- ⚠️ Updated `DeepgramSTTService` to use `deepgram-sdk` v6. The `LiveOptions` class was removed from the SDK and is now provided by pipecat directly; import it from `pipecat.services.deepgram.stt` instead of `deepgram`.

changelog/3848.fixed.md

@@ -1 +0,0 @@
-- Fixed `DeepgramSTTService` keepalive ping timeout disconnections. The deepgram-sdk v6 removed automatic keepalive; pipecat now sends explicit `KeepAlive` messages every 5 seconds, within the recommended 3–5 second interval before Deepgram's 10-second inactivity timeout.

changelog/3889.changed.md

@@ -1,3 +0,0 @@
-- Support for Voice Focus 2.0 models.
-  - Updated `aic-sdk` to `~=2.1.0` to support Voice Focus 2.0 models.
-  - Cleaned unused `ParameterFixedError` exception handling in `AICFilter` parameter setup. 

changelog/3889.fixed.md

@@ -1 +0,0 @@
-- Fixed `BufferError: Existing exports of data: object cannot be re-sized` in `AICFilter` caused by holding a `memoryview` on the mutable audio buffer across async yield points.

changelog/3914.changed.md

@@ -1 +0,0 @@
-- `max_context_tokens` and `max_unsummarized_messages` in `LLMAutoContextSummarizationConfig` (and deprecated `LLMContextSummarizationConfig`) can now be set to `None` independently to disable that summarization threshold. At least one must remain set.

changelog/3915.added.md

@@ -1 +0,0 @@
-- Added optional `timeout_secs` parameter to `register_function()` and `register_direct_function()` for per-tool function call timeout control, overriding the global `function_call_timeout_secs` default.

changelog/3916.added.md

@@ -1 +0,0 @@
-- Added `cloud-audio-only` recording option to Daily transport's `enable_recording` property.

changelog/3918.added.md

@@ -1,15 +0,0 @@
-- Wired up `system_instruction` in `BaseOpenAILLMService`, `AnthropicLLMService`, and `AWSBedrockLLMService` so it works as a default system prompt, matching the behavior of the Google services. This enables sharing a single `LLMContext` across multiple LLM services, where each service provides its own system instruction independently.
-
-  ```python
-  llm = OpenAILLMService(
-      api_key=os.getenv("OPENAI_API_KEY"),
-      system_instruction="You are a helpful assistant.",
-  )
-
-  context = LLMContext()
-
-  @transport.event_handler("on_client_connected")
-  async def on_client_connected(transport, client):
-      context.add_message({"role": "user", "content": "Please introduce yourself."})
-      await task.queue_frames([LLMRunFrame()])
-  ```

changelog/3918.other.md

@@ -1 +0,0 @@
-- Updated foundational examples to use `system_instruction` on LLM services instead of adding system messages to `LLMContext`.

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)
+- Handles conflicting dependencies (like grpcio versions for Riva and PlayHT)
 - Builds the documentation in an isolated environment
 - Provides detailed logging of the build process
 
@@ -74,6 +74,7 @@ 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
 ```

env.example

@@ -43,12 +43,11 @@ CEREBRAS_API_KEY=...
 
 # Daily
 DAILY_API_KEY=...
-DAILY_ROOM_URL=https://...
+DAILY_SAMPLE_ROOM_URL=https://...
 
 # Deepgram
 DEEPGRAM_API_KEY=...
-SAGEMAKER_STT_ENDPOINT_NAME=...
-SAGEMAKER_TTS_ENDPOINT_NAME=...
+SAGEMAKER_ENDPOINT_NAME=...
 
 # DeepSeek
 DEEPSEEK_API_KEY=...
@@ -104,14 +103,9 @@ INWORLD_API_KEY=...
 KRISP_MODEL_PATH=...
 
 # Krisp Viva
-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=...
 LIVEKIT_API_SECRET=...
@@ -151,6 +145,10 @@ KOALA_ACCESS_KEY=...
 # Piper
 PIPER_BASE_URL=...
 
+# PlayHT
+PLAYHT_USER_ID=...
+PLAYHT_API_KEY=...
+
 # Plivo
 PLIVO_AUTH_ID=...
 PLIVO_AUTH_TOKEN=...
@@ -158,10 +156,6 @@ PLIVO_AUTH_TOKEN=...
 # Qwen
 QWEN_API_KEY=...
 
-# Resemble AI
-RESEMBLE_API_KEY=
-RESEMBLE_VOICE_UUID=
-
 # Rime
 RIME_API_KEY=...
 RIME_VOICE_ID=...

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

@@ -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 PiperHttpTTSService
+from pipecat.services.piper.tts import PiperTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -24,8 +24,9 @@ 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.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(audio_out_enabled=True),
     "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
@@ -38,7 +39,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     # Create an HTTP session
     async with aiohttp.ClientSession() as session:
-        tts = PiperHttpTTSService(
+        tts = PiperTTSService(
             base_url=os.getenv("PIPER_BASE_URL"), aiohttp_session=session, sample_rate=24000
         )
 

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

@@ -23,8 +23,9 @@ 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.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(audio_out_enabled=True),
     "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),

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

@@ -23,8 +23,9 @@ 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.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(audio_out_enabled=True),
     "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),

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

@@ -23,8 +23,9 @@ 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.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(audio_out_enabled=True),
     "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),

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

@@ -25,8 +25,9 @@ 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.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(audio_out_enabled=True),
     "twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
@@ -42,10 +43,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are an LLM in a WebRTC session, and this is a 'hello world' demo.",
-    )
+    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.",
+        }
+    ]
 
     task = PipelineTask(
         Pipeline([llm, tts, transport.output()]),
@@ -55,9 +60,7 @@ 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):
-        context = LLMContext()
-        context.add_message({"role": "system", "content": "Say hello to the world."})
-        await task.queue_frames([LLMContextFrame(context), EndFrame()])
+        await task.queue_frames([LLMContextFrame(LLMContext(messages)), EndFrame()])
 
     runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
 

examples/foundational/03-still-frame.py

@@ -23,8 +23,9 @@ from pipecat.transports.daily.transport import DailyParams
 load_dotenv(override=True)
 
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         video_out_enabled=True,

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

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

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

@@ -17,7 +17,9 @@ from fastapi.responses import RedirectResponse
 from loguru import logger
 from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
 
+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
@@ -33,6 +35,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.smallwebrtc.connection import IceServer, SmallWebRTCConnection
 from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
+from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
@@ -60,6 +64,7 @@ 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)),
         ),
     )
 
@@ -70,15 +75,23 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -105,7 +118,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -12,7 +12,9 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -26,6 +28,8 @@ from pipecat.runner.daily import configure
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.daily.transport import DailyParams, DailyTransport
+from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
@@ -45,6 +49,7 @@ async def main():
                 audio_in_enabled=True,
                 audio_out_enabled=True,
                 transcription_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
             ),
         )
 
@@ -53,16 +58,25 @@ async def main():
             voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
         )
 
-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4o",
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-        )
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
 
-        context = LLMContext()
+        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 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.",
+            },
+        ]
+
+        context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
-            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+            user_params=LLMUserAggregatorParams(
+                user_turn_strategies=UserTurnStrategies(
+                    stop=[
+                        TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
+                    ]
+                ),
+            ),
         )
 
         pipeline = Pipeline(
@@ -88,9 +102,7 @@ async def main():
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
-            context.add_message(
-                {"role": "system", "content": "Please introduce yourself to the user."}
-            )
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_participant_left")

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

@@ -12,7 +12,9 @@ import sys
 from dotenv import load_dotenv
 from loguru import logger
 
+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,
@@ -33,6 +35,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
+from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
@@ -50,25 +54,37 @@ async def main():
         params=LiveKitParams(
             audio_in_enabled=True,
             audio_out_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
         ),
     )
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(

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

@@ -65,8 +65,9 @@ class MonthPrepender(FrameProcessor):
             await self.push_frame(frame, direction)
 
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_out_enabled=True,

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

@@ -9,7 +9,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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,
@@ -34,6 +36,8 @@ 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)
 
@@ -58,20 +62,24 @@ class MetricsLogger(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -86,17 +94,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     ml = MetricsLogger()
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -125,7 +141,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -10,7 +10,9 @@ from dotenv import load_dotenv
 from loguru import logger
 from PIL import Image
 
+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,
@@ -34,6 +36,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
+from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
@@ -73,8 +77,9 @@ class ImageSyncAggregator(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
@@ -82,6 +87,7 @@ transport_params = {
         video_out_enabled=True,
         video_out_width=1024,
         video_out_height=1024,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
@@ -89,6 +95,7 @@ transport_params = {
         video_out_enabled=True,
         video_out_width=1024,
         video_out_height=1024,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -103,15 +110,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     image_sync_aggregator = ImageSyncAggregator(

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

@@ -9,7 +9,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -27,24 +29,30 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -59,15 +67,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -95,7 +111,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07-interruptible.py

@@ -9,7 +9,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -24,27 +26,32 @@ from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 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
 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -57,20 +64,25 @@ 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
-        # Alternatively, you can use TextAggregationMode.TOKEN to stream tokens instead of
-        # sentencesfor faster response times.
-        # text_aggregation_mode=TextAggregationMode.TOKEN,
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -98,7 +110,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "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

@@ -33,8 +33,9 @@ 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.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,

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

@@ -10,7 +10,9 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -30,23 +32,29 @@ 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_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -111,7 +119,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
-            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+            user_params=LLMUserAggregatorParams(
+                user_turn_strategies=UserTurnStrategies(
+                    stop=[
+                        TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
+                    ]
+                ),
+            ),
         )
 
         pipeline = Pipeline(

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

@@ -15,7 +15,9 @@ from langchain_core.runnables.history import RunnableWithMessageHistory
 from langchain_openai import ChatOpenAI
 from loguru import logger
 
+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
@@ -33,6 +35,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 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)
 
@@ -46,20 +50,24 @@ def get_session_history(session_id: str) -> BaseChatMessageHistory:
     return message_store[session_id]
 
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -97,7 +105,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     context = LLMContext()
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(

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

@@ -10,7 +10,6 @@ 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
@@ -33,8 +32,9 @@ 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.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
@@ -61,18 +61,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(
-            user_turn_strategies=ExternalUserTurnStrategies(),
-            vad_analyzer=SileroVADAnalyzer(),
-        ),
+        user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
     )
 
     pipeline = Pipeline(
@@ -100,7 +101,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "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

@@ -11,7 +11,9 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -29,24 +31,30 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -63,17 +71,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-        )
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        messages = []
+        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 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.",
+            },
+        ]
 
         context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
-            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+            user_params=LLMUserAggregatorParams(
+                user_turn_strategies=UserTurnStrategies(
+                    stop=[
+                        TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
+                    ]
+                ),
+            ),
         )
 
         pipeline = Pipeline(
@@ -101,9 +117,7 @@ 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.
-            context.add_message(
-                {"role": "system", "content": "Please introduce yourself to the user."}
-            )
+            messages.append({"role": "system", "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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -23,29 +25,35 @@ from pipecat.processors.aggregators.llm_response_universal import (
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.aws.llm import AWSBedrockLLMService
-from pipecat.services.deepgram.sagemaker.stt import DeepgramSageMakerSTTService
-from pipecat.services.deepgram.sagemaker.tts import DeepgramSageMakerTTSService
+from pipecat.services.deepgram.stt_sagemaker import DeepgramSageMakerSTTService
+from pipecat.services.deepgram.tts import DeepgramTTSService
 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -58,31 +66,33 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     # - 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"),
+        endpoint_name=os.getenv("SAGEMAKER_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"),
-        voice="aura-2-andromeda-en",
-    )
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
 
     llm = AWSBedrockLLMService(
         aws_region=os.getenv("AWS_REGION"),
         model="us.amazon.nova-pro-v1:0",
         params=AWSBedrockLLMService.InputParams(temperature=0.8),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
     )
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -110,7 +120,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -33,8 +33,9 @@ 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.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
@@ -61,12 +62,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
@@ -97,7 +102,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,24 +30,30 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -57,15 +65,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -93,7 +109,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "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

@@ -11,7 +11,9 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -29,24 +31,30 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -67,15 +75,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-        )
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        context = LLMContext()
+        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 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.",
+            },
+        ]
+
+        context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
-            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+            user_params=LLMUserAggregatorParams(
+                user_turn_strategies=UserTurnStrategies(
+                    stop=[
+                        TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
+                    ]
+                ),
+            ),
         )
 
         pipeline = Pipeline(
@@ -103,9 +121,7 @@ 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.
-            context.add_message(
-                {"role": "system", "content": "Please introduce yourself to the user."}
-            )
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,24 +30,30 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -60,15 +68,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -96,7 +112,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07e-interruptible-playht-http.py

@@ -4,12 +4,15 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
+
 import os
 
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -23,10 +26,12 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.services.resembleai.tts import ResembleAITTSService
+from pipecat.services.playht.tts import PlayHTHttpTTSService
 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)
 
@@ -37,17 +42,17 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -57,20 +62,29 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = ResembleAITTSService(
-        api_key=os.getenv("RESEMBLE_API_KEY"),
-        voice_id=os.getenv("RESEMBLE_VOICE_UUID"),
+    tts = PlayHTHttpTTSService(
+        user_id=os.getenv("PLAYHT_USER_ID"),
+        api_key=os.getenv("PLAYHT_API_KEY"),
+        voice_url="s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json",
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -98,7 +112,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -4,12 +4,15 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
+
 import os
 
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -22,11 +25,14 @@ from pipecat.processors.aggregators.llm_response_universal import (
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
-from pipecat.services.kokoro.tts import KokoroTTSService
 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
+from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
@@ -37,14 +43,17 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -54,17 +63,30 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = KokoroTTSService(voice_id="af_heart")
-
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
+    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),
     )
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -92,7 +114,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,23 +30,29 @@ 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
+from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -66,13 +74,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
         endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
         model=os.getenv("AZURE_CHATGPT_MODEL"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
     )
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -100,7 +118,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,23 +30,29 @@ from pipecat.services.azure.tts import AzureTTSService
 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -66,13 +74,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
         endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
         model=os.getenv("AZURE_CHATGPT_MODEL"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
     )
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -100,7 +118,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "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

@@ -1,122 +0,0 @@
-#
-# 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.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 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 = OpenAISTTService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        model="gpt-4o-transcribe",
-        prompt="Expect words related to dogs, such as breed names.",
-    )
-
-    tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
-
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        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.",
-    )
-
-    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(
-            audio_out_sample_rate=24000,
-            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": "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()
-
-    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/07g-interruptible-openai.py

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -23,29 +25,34 @@ from pipecat.processors.aggregators.llm_response_universal import (
 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 OpenAIRealtimeSTTService
+from pipecat.services.openai.stt import OpenAISTTService
 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
+from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -53,28 +60,31 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = OpenAIRealtimeSTTService(
+    stt = OpenAISTTService(
         api_key=os.getenv("OPENAI_API_KEY"),
         model="gpt-4o-transcribe",
         prompt="Expect words related to dogs, such as breed names.",
-        language=Language.EN,
-        # Uses local VAD by default.
-        # To enable server-side VAD, set turn_detection=None or
-        # a dict with server_vad settings.
-        # turn_detection={"type": "server_vad", "threshold": 0.5},
     )
 
     tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    messages = [
+        {
+            "role": "system",
+            "content": "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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -103,7 +113,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -11,7 +11,9 @@ import time
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -29,23 +31,29 @@ from pipecat.services.openpipe.llm import OpenPipeLLMService
 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -65,13 +73,23 @@ 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}"},
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
     )
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -99,7 +117,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -11,7 +11,9 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -29,23 +31,29 @@ from pipecat.services.xtts.tts import XTTSService
 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -63,15 +71,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             base_url="http://localhost:8000",
         )
 
-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-        )
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        context = LLMContext()
+        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 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.",
+            },
+        ]
+
+        context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
-            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+            user_params=LLMUserAggregatorParams(
+                user_turn_strategies=UserTurnStrategies(
+                    stop=[
+                        TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
+                    ]
+                ),
+            ),
         )
 
         pipeline = Pipeline(
@@ -99,9 +117,7 @@ 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.
-            context.add_message(
-                {"role": "system", "content": "Please introduce yourself to the user."}
-            )
+            messages.append({"role": "system", "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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 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
@@ -34,20 +35,24 @@ 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.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -83,10 +88,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(
-            user_turn_strategies=ExternalUserTurnStrategies(),
-            vad_analyzer=SileroVADAnalyzer(),
-        ),
+        user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
     )
 
     pipeline = Pipeline(

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -30,23 +32,29 @@ 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_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -81,7 +89,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,23 +30,29 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -56,15 +64,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = LmntTTSService(api_key=os.getenv("LMNT_API_KEY"), voice_id="morgan")
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -92,7 +108,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,23 +30,29 @@ from pipecat.services.groq.tts import GroqTTSService
 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -55,17 +63,26 @@ 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",
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
+        api_key=os.getenv("GROQ_API_KEY"), model="meta-llama/llama-4-maverick-17b-128e-instruct"
     )
 
     tts = GroqTTSService(api_key=os.getenv("GROQ_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -93,7 +110,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "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

@@ -8,6 +8,7 @@
 from dotenv import load_dotenv
 from loguru import logger
 
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesAppendFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -26,6 +27,8 @@ from pipecat.services.aws.tts import AWSPollyTTSService
 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
 
 # Strands agent setup
 try:
@@ -38,20 +41,24 @@ except ImportError:
 
 load_dotenv(override=True)
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 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(),
     ),
 }
 
@@ -115,7 +122,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     context = LLMContext()
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(

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

@@ -8,7 +8,9 @@
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -26,23 +28,29 @@ from pipecat.services.aws.tts import AWSPollyTTSService
 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -62,13 +70,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         aws_region="us-west-2",
         model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
         params=AWSBedrockLLMService.InputParams(temperature=0.8),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
     )
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -96,7 +114,7 @@ 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.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "user", "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

@@ -25,7 +25,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -43,11 +45,14 @@ 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.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
@@ -55,6 +60,7 @@ transport_params = {
         video_out_enabled=True,
         video_out_width=1024,
         video_out_height=1024,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
@@ -62,6 +68,7 @@ transport_params = {
         video_out_enabled=True,
         video_out_width=1024,
         video_out_height=1024,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -83,14 +90,24 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         model="gemini-2.5-flash-image",
-        # model="gemini-3-pro-image-preview", # A more powerful model, but slower,
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
+        # model="gemini-3-pro-image-preview", # A more powerful model, but slower
     )
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -118,7 +135,7 @@ 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 with a styled introduction
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -29,23 +31,29 @@ 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_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -71,7 +79,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         model="gemini-2.5-flash",
-        system_instruction="""You are a helpful AI assistant in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct 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: You're using Gemini TTS which supports expressive markup tags. You can use these tags in your responses:
             - [sigh] - Insert a sigh sound
@@ -89,12 +103,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             - "The answer is... [long pause] ...42!"
 
             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.""",
-    )
+        },
+    ]
 
-    context = LLMContext()
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -122,7 +141,7 @@ 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
-        context.add_message(
+        messages.append(
             {
                 "role": "system",
                 "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.",

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -29,23 +31,29 @@ 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_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -72,13 +80,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         # params=GoogleLLMService.InputParams(
         #     thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
         # ),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
     )
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -106,7 +124,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -29,23 +31,29 @@ 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_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -72,13 +80,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         # params=GoogleLLMService.InputParams(
         #     thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
         # ),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
     )
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -106,7 +124,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "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

@@ -1,175 +0,0 @@
-#
-# 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.models import AssemblyAIConnectionParams
-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
-        connection_params=AssemblyAIConnectionParams(
-            speech_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
-            # prompt="Names: Xiomara, Saoirse, Krzystof. Technical terms: API, OAuth.",
-            # Optional: Enable speaker diarization
-            # speaker_labels=True,
-        ),
-    )
-
-    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-    )
-
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
-
-    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": "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()
-
-    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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,24 +30,30 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -62,15 +70,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -98,7 +114,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "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

@@ -30,9 +30,8 @@ from loguru import logger
 from pipecat.audio.filters.krisp_viva_filter import KrispVivaFilter
 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
@@ -43,8 +42,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
 )
 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
@@ -54,26 +53,27 @@ from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
-
-krisp_viva_filter = KrispVivaFilter()
-
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        audio_in_filter=krisp_viva_filter,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        audio_in_filter=KrispVivaFilter(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        audio_in_filter=krisp_viva_filter,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        audio_in_filter=KrispVivaFilter(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        audio_in_filter=krisp_viva_filter,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        audio_in_filter=KrispVivaFilter(),
     ),
 }
 
@@ -83,23 +83,24 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121"
-    )
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
                 stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=KrispVivaTurn())]
             ),
-            vad_analyzer=SileroVADAnalyzer(),
         ),
     )
 
@@ -122,14 +123,13 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -11,7 +11,9 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.filters.krisp_filter import KrispFilter
+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
@@ -29,25 +31,31 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
         audio_in_filter=KrispFilter(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
         audio_in_filter=KrispFilter(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
         audio_in_filter=KrispFilter(),
     ),
 }
@@ -60,15 +68,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -96,7 +112,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "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

@@ -11,7 +11,9 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -29,24 +31,30 @@ from pipecat.services.rime.tts import RimeHttpTTSService
 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -65,15 +73,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-        )
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        context = LLMContext()
+        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 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.",
+            },
+        ]
+
+        context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
-            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+            user_params=LLMUserAggregatorParams(
+                user_turn_strategies=UserTurnStrategies(
+                    stop=[
+                        TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
+                    ]
+                ),
+            ),
         )
 
         pipeline = Pipeline(
@@ -101,9 +119,7 @@ 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.
-            context.add_message(
-                {"role": "system", "content": "Please introduce yourself to the user."}
-            )
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,23 +30,29 @@ from pipecat.services.rime.tts import RimeTTSService
 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -56,18 +64,26 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = RimeTTSService(
         api_key=os.getenv("RIME_API_KEY", ""),
-        voice_id="luna",
+        voice_id="rex",
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -95,7 +111,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,23 +30,29 @@ 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
+from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -55,17 +63,26 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = NvidiaSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
 
     llm = NvidiaLLMService(
-        api_key=os.getenv("NVIDIA_API_KEY"),
-        model="meta/llama-3.3-70b-instruct",
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
+        api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct"
     )
 
     tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -93,7 +110,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -12,7 +12,9 @@ from dotenv import load_dotenv
 from google.genai.types import Content, Part
 from loguru import logger
 
+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,
@@ -42,6 +44,8 @@ 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_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
@@ -96,7 +100,7 @@ class UserAudioCollector(FrameProcessor):
             self._user_speaking = True
         elif isinstance(frame, UserStoppedSpeakingFrame):
             self._user_speaking = False
-            await self._context.add_audio_frames_message(audio_frames=self._audio_frames)
+            self._context.add_audio_frames_message(audio_frames=self._audio_frames)
             await self._user_context_aggregator.push_frame(LLMRunFrame())
 
         elif isinstance(frame, InputAudioRawFrame):
@@ -193,20 +197,24 @@ class TranscriptionContextFixup(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -243,7 +251,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
     audio_collector = UserAudioCollector(context, user_aggregator)
     pull_transcript_out_of_llm_output = TranscriptExtractor(context)

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,24 +30,30 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -60,15 +68,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         model="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -96,7 +112,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "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

@@ -11,7 +11,9 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -29,24 +31,30 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -64,15 +72,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-        )
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        context = LLMContext()
+        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 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.",
+            },
+        ]
+
+        context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
-            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+            user_params=LLMUserAggregatorParams(
+                user_turn_strategies=UserTurnStrategies(
+                    stop=[
+                        TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
+                    ]
+                ),
+            ),
         )
 
         pipeline = Pipeline(
@@ -100,9 +118,7 @@ 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.
-            context.add_message(
-                {"role": "system", "content": "Please introduce yourself to the user."}
-            )
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,23 +30,29 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -59,15 +67,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -95,7 +111,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -10,7 +10,9 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -28,24 +30,30 @@ 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 use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -62,15 +70,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    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 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -98,7 +114,7 @@ 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.
-        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -11,7 +11,9 @@ import sys
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -25,6 +27,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
+from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
@@ -37,6 +41,7 @@ async def main():
         LocalAudioTransportParams(
             audio_in_enabled=True,
             audio_out_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
         )
     )
 
@@ -47,15 +52,23 @@ async def main():
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    context = LLMContext()
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. 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.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
-        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
     )
 
     pipeline = Pipeline(
@@ -78,7 +91,7 @@ async def main():
         ),
     )
 
-    context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+    messages.append({"role": "system", "content": "Please introduce yourself to the user."})
     await task.queue_frames([LLMRunFrame()])
 
     runner = PipelineRunner()

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

@@ -11,7 +11,9 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -30,24 +32,30 @@ 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_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -66,15 +74,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             params=MiniMaxHttpTTSService.InputParams(language=Language.EN),
         )
 
-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-        )
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        context = LLMContext()
+        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 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.",
+            },
+        ]
+
+        context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
-            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+            user_params=LLMUserAggregatorParams(
+                user_turn_strategies=UserTurnStrategies(
+                    stop=[
+                        TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
+                    ]
+                ),
+            ),
         )
 
         pipeline = Pipeline(
@@ -102,9 +120,7 @@ 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.
-            context.add_message(
-                {"role": "system", "content": "Please introduce yourself to the user."}
-            )
+            messages.append({"role": "system", "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

@@ -11,7 +11,9 @@ import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
+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
@@ -30,24 +32,30 @@ 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_stop import TurnAnalyzerUserTurnStopStrategy
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 load_dotenv(override=True)
 
 
-# We use lambdas to defer transport parameter creation until the transport
-# type is selected at runtime.
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
     ),
 }
 
@@ -68,15 +76,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             params=SarvamHttpTTSService.InputParams(language=Language.EN),
         )
 
-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 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.",
-        )
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        context = LLMContext()
+        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 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.",
+            },
+        ]
+
+        context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
-            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+            user_params=LLMUserAggregatorParams(
+                user_turn_strategies=UserTurnStrategies(
+                    stop=[
+                        TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
+                    ]
+                ),
+            ),
         )
 
         pipeline = Pipeline(
@@ -104,9 +122,7 @@ 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.
-            context.add_message(
-                {"role": "system", "content": "Please introduce yourself to the user."}
-            )
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")