Merge pull request #3253 from pipecat-ai/changelog-0.0.98

Release 0.0.98 - Changelog Update

.github/workflows/generate-changelog.yml

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

.github/workflows/publish.yaml

@@ -5,25 +5,25 @@ on:
     inputs:
       gitref:
         type: string
-        description: "what git tag to build (e.g. v0.0.74)"
+        description: 'what git tag to build (e.g. v0.0.74)'
         required: true
 
 jobs:
   build:
-    name: "Build and upload wheels"
+    name: 'Build and upload wheels'
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repo
         uses: actions/checkout@v4
         with:
           ref: ${{ github.event.inputs.gitref }}
-      
+
       - name: Install uv
         uses: astral-sh/setup-uv@v3
         with:
-          version: "latest"
+          version: 'latest'
       - name: Set up Python
-        run: uv python install 3.10
+        run: uv python install 3.12
       - name: Install development dependencies
         run: uv sync --group dev
       - name: Build project
@@ -35,9 +35,9 @@ jobs:
           path: ./dist
 
   publish-to-pypi:
-    name: "Publish to PyPI"
+    name: 'Publish to PyPI'
     runs-on: ubuntu-latest
-    needs: [ build ]
+    needs: [build]
     environment:
       name: pypi
       url: https://pypi.org/p/pipecat-ai
@@ -56,12 +56,12 @@ jobs:
           print-hash: true
 
   publish-to-test-pypi:
-    name: "Publish to Test PyPI"
+    name: 'Publish to Test PyPI'
     runs-on: ubuntu-latest
-    needs: [ build ]
+    needs: [build]
     environment:
       name: testpypi
-      url: https://pypi.org/p/pipecat-ai
+      url: https://test.pypi.org/p/pipecat-ai
     permissions:
       id-token: write
     steps:
@@ -70,7 +70,7 @@ jobs:
         with:
           name: wheels
           path: ./dist
-      - name: Publish to PyPI
+      - name: Publish to Test PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           verbose: true

.github/workflows/publish_test.yaml

@@ -4,7 +4,7 @@ on: workflow_dispatch
 
 jobs:
   build:
-    name: "Build and upload wheels"
+    name: 'Build and upload wheels'
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repo
@@ -15,9 +15,9 @@ jobs:
       - name: Install uv
         uses: astral-sh/setup-uv@v3
         with:
-          version: "latest"
+          version: 'latest'
       - name: Set up Python
-        run: uv python install 3.10
+        run: uv python install 3.12
       - name: Install development dependencies
         run: uv sync --group dev
       - name: Build project
@@ -29,12 +29,12 @@ jobs:
           path: ./dist
 
   publish-to-test-pypi:
-    name: "Publish to Test PyPI"
+    name: 'Publish to Test PyPI'
     runs-on: ubuntu-latest
     needs: [build]
     environment:
       name: testpypi
-      url: https://pypi.org/p/pipecat-ai
+      url: https://test.pypi.org/p/pipecat-ai
     permissions:
       id-token: write
     steps:
@@ -43,7 +43,7 @@ jobs:
         with:
           name: wheels
           path: ./dist
-      - name: Publish to PyPI
+      - name: Publish to Test PyPI
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           verbose: true

.github/workflows/python-compatibility.yaml

@@ -50,7 +50,6 @@ jobs:
         run: |
           uv sync --group dev --all-extras \
             --no-extra krisp \
-            --no-extra ultravox \
             --no-extra local-smart-turn \
             --no-extra moondream \
             --no-extra mlx-whisper

.readthedocs.yaml

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

COMMUNITY_INTEGRATIONS.md

@@ -0,0 +1,336 @@
+# Community Integrations Guide
+
+Pipecat welcomes community-maintained integrations! As our ecosystem grows, we've established a process for any developer to create and maintain their own service integrations while ensuring discoverability for the Pipecat community.
+
+## Overview
+
+**What we support:** Community-maintained integrations that live in separate repositories and are maintained by their authors.
+
+**What we don't do:** The Pipecat team does not code review, test, or maintain community integrations. We provide guidance and list approved integrations for discoverability.
+
+**Why this approach:** This allows the community to move quickly while keeping the Pipecat core team focused on maintaining the framework itself.
+
+## Submitting your Integration
+
+To be listed as an official community integration, follow these steps:
+
+### Step 1: Build Your Integration
+
+Create your integration following the patterns and examples shown in the "Integration Patterns and Examples" section below.
+
+### Step 2: Set Up Your Repository
+
+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
+  - How to run your example
+  - Pipecat version compatibility (e.g., "Tested with Pipecat v0.0.86")
+  - Company attribution: If you work for the company providing the service, please mention this in your README. This helps build confidence that the integration will be actively maintained.
+
+- **LICENSE** - Permissive license (BSD-2 like Pipecat, or equivalent open source terms)
+- **Code documentation** - Source code with docstrings (we recommend following [Pipecat's docstring conventions](https://github.com/pipecat-ai/pipecat/blob/main/CONTRIBUTING.md#docstring-conventions))
+- **Changelog** - Maintain a changelog for version updates
+
+### Step 3: Join Discord
+
+Join our Discord: https://discord.gg/pipecat
+
+### Step 4: Submit for Listing
+
+Submit a pull request to add your integration to our [Community Integrations documentation page](https://docs.pipecat.ai/server/services/community-integrations).
+
+**To submit:**
+
+1. Fork the [Pipecat docs repository](https://github.com/pipecat-ai/docs)
+2. Edit the file `server/services/community-integrations.mdx`
+3. Add your integration to the appropriate service category table with:
+   - Service name
+   - Link to your repository
+   - Maintainer GitHub username(s)
+4. Include a link to your demo video (approx 30-60 seconds) in your PR description showing:
+   - Core functionality of your integration
+   - Handling of an interruption (if applicable to service type)
+5. Submit your pull request
+
+Once your PR is submitted, post in the `#community-integrations` Discord channel to let us know.
+
+## Integration Patterns and Examples
+
+### STT (Speech-to-Text) Services
+
+#### Websocket-based Services
+
+**Base class:** `STTService`
+
+**Examples:**
+
+- [DeepgramSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/deepgram/stt.py)
+- [SpeechmaticsSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/speechmatics/stt.py)
+
+#### File-based Services
+
+**Base class:** `SegmentedSTTService`
+
+**Examples:**
+
+- [NvidiaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/nvidia/stt.py)
+- [FalSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/fal/stt.py)
+
+#### Key requirements:
+
+- STT services should push `InterimTranscriptionFrames` and `TranscriptionFrames`
+- If confidence values are available, filter for values >50% confidence
+
+### LLM (Large Language Model) Services
+
+#### OpenAI-Compatible Services
+
+**Base class:** `OpenAILLMService`
+
+**Examples:**
+
+- [AzureLLMService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/azure/llm.py)
+- [GrokLLMService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/grok/llm.py) - Shows overriding the base class where needed
+
+#### Non-OpenAI Compatible Services
+
+**Requires:** Full implementation
+
+**Examples:**
+
+- [AnthropicLLMService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/anthropic/llm.py)
+- [GoogleLLMService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/llm.py)
+
+#### 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
+
+- **Context aggregation:** Implement context aggregation to collect user and assistant content:
+  - Aggregators come in pairs with a `user()` instance and `assistant()` instance
+  - Context must adhere to the `LLMContext` universal format
+  - Aggregators should handle adding messages, function calls, and images to the context
+
+### TTS (Text-to-Speech) Services
+
+#### AudioContextWordTTSService
+
+**Use for:** Websocket-based services supporting word/timestamp alignment
+
+**Example:**
+
+- [CartesiaTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/cartesia/tts.py)
+
+#### InterruptibleTTSService
+
+**Use for:** Websocket-based services without word/timestamp alignment, requiring disconnection on interruption
+
+**Example:**
+
+- [SarvamTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/sarvam/tts.py)
+
+#### WordTTSService
+
+**Use for:** HTTP-based services supporting word/timestamp alignment
+
+**Example:**
+
+- [ElevenLabsHttpTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/elevenlabs/tts.py)
+
+#### TTSService
+
+**Use for:** HTTP-based services without word/timestamp alignment
+
+**Example:**
+
+- [GoogleHttpTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/tts.py)
+
+#### Key requirements:
+
+- For websocket services, use asyncio WebSocket implementation (required for v13+ support)
+- Handle idle service timeouts with keepalives
+- TTSServices push both audio (`TTSRawAudioFrame`) and text (`TTSTextFrame`) frames
+
+### Telephony Serializers
+
+Pipecat supports telephony provider integration using websocket connections to exchange MediaStreams. These services use a FrameSerializer to serialize and deserialize inputs from the FastAPIWebsocketTransport.
+
+**Examples:**
+
+- [Twilio](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/serializers/twilio.py)
+- [Telnyx](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/serializers/telnyx.py)
+
+#### Key requirements:
+
+- Include hang-up functionality using the provider's native API, ideally using `aiohttp`
+- Support DTMF (dual-tone multi-frequency) events if the provider supports them:
+  - Deserialize DTMF events from the provider's protocol to `InputDTMFFrame`
+  - Use `KeypadEntry` enum for valid keypad entries (0-9, \*, #, A-D)
+  - Handle invalid DTMF digits gracefully by returning `None`
+
+### Image Generation Services
+
+**Base class:** `ImageGenService`
+
+**Examples:**
+
+- [FalImageGenService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/fal/image.py)
+- [GoogleImageGenService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/image.py)
+
+#### Key requirements:
+
+- Must implement `run_image_gen` method returning an `AsyncGenerator`
+
+### Vision Services
+
+Vision services process images and provide analysis such as descriptions, object detection, or visual question answering.
+
+**Base class:** `VisionService`
+
+**Example:**
+
+- [MoondreamVisionService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/moondream/vision.py)
+
+#### Key requirements:
+
+- Must implement `run_vision` method that takes an `LLMContext` and returns an `AsyncGenerator[Frame, None]`
+- The method processes the latest image in the context and yields frames with analysis results
+- Typically yields `TextFrame` objects containing descriptions or answers
+
+## Implementation Guidelines
+
+### Naming Conventions
+
+- **STT:** `VendorSTTService`
+- **LLM:** `VendorLLMService`
+- **TTS:**
+  - Websocket: `VendorTTSService`
+  - HTTP: `VendorHttpTTSService`
+- **Image:** `VendorImageGenService`
+- **Vision:** `VendorVisionService`
+- **Telephony:** `VendorFrameSerializer`
+
+### Metrics Support
+
+Enable metrics in your service:
+
+```python
+def can_generate_metrics(self) -> bool:
+    """Check if this service can generate processing metrics.
+
+    Returns:
+        True, as this service supports metrics.
+    """
+    return True
+```
+
+### Dynamic Settings Updates
+
+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
+async def set_language(self, language: Language):
+    """Set the recognition language and reconnect.
+
+    Args:
+        language: The language to use for speech recognition.
+    """
+    logger.info(f"Switching STT language to: [{language}]")
+    self._settings["language"] = language
+    await self._disconnect()
+    await self._connect()
+```
+
+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
+
+Sample rates are set via PipelineParams and passed to each frame processor at initialization. The pattern is to _not_ set the sample rate value in the constructor of a given service. Instead, use the `start()` method to initialize sample rates from the frame:
+
+```python
+async def start(self, frame: StartFrame):
+    """Start the service."""
+    await super().start(frame)
+    self._settings["output_format"]["sample_rate"] = self.sample_rate
+    await self._connect()
+```
+
+Note that `self.sample_rate` is a `@property` set in the TTSService base class, which provides access to the private sample rate value obtained from the StartFrame.
+
+### Tracing Decorators
+
+Use Pipecat's tracing decorators:
+
+- **STT:** `@traced_stt` - decorate a function that handles `transcript`, `is_final`, `language` as args
+- **LLM:** `@traced_llm` - decorate the `_process_context()` method
+- **TTS:** `@traced_tts` - decorate the `run_tts()` method
+
+## Best Practices
+
+### Packaging and Distribution
+
+- Use [uv](https://docs.astral.sh/uv/) for packaging (encouraged)
+- Consider releasing to PyPI for easier installation
+- Follow semantic versioning principles
+- Maintain a changelog
+
+### HTTP Communication
+
+For REST-based communication, use aiohttp. Pipecat includes this as a required dependency, so using it prevents adding an additional dependency to your integration.
+
+### Error Handling
+
+- Wrap API calls in appropriate try/catch blocks
+- Handle rate limits and network failures gracefully
+- Provide meaningful error messages
+- When errors occur, raise exceptions AND push `ErrorFrame`s to notify the pipeline:
+
+```python
+from pipecat.frames.frames import ErrorFrame
+
+try:
+    # Your API call
+    result = await self._make_api_call()
+except Exception as e:
+    # Push error frame to pipeline
+    await self.push_error(ErrorFrame(error=f"{self} error: {e}"))
+    # Raise or handle as appropriate
+    raise
+```
+
+### Testing
+
+- Your foundational example serves as a valuable integration-level test
+- Unit tests are nice to have. As the Pipecat teams provides better guidance, we will encourage unit testing more
+
+## Disclaimer
+
+Community integrations are community-maintained and not officially supported by the Pipecat team. Users should evaluate these integrations independently. The Pipecat team reserves the right to remove listings that become unmaintained or problematic.
+
+## Staying Up to Date
+
+Pipecat evolves rapidly to support the latest AI technologies and patterns. While we strive to minimize breaking changes, they do occur as the framework matures.
+
+**We strongly recommend:**
+
+- Join our Discord at https://discord.gg/pipecat and monitor the `#announcements` channel for release notifications
+- Follow our changelog: https://github.com/pipecat-ai/pipecat/blob/main/CHANGELOG.md
+- Test your integration against new Pipecat releases promptly
+- Update your README with the last tested Pipecat version
+
+This helps ensure your integration remains compatible and your users have clear expectations about version support.
+
+## Questions?
+
+Join our Discord community at https://discord.gg/pipecat and post in the `#community-integrations` channel for guidance and support.
+
+For additional questions, you can also reach out to us at pipecat-ai@daily.co.

CONTRIBUTING.md

@@ -1,5 +1,9 @@
 ## Contributing to Pipecat
 
+**Want to add a new service integration?**
+We encourage community-maintained integrations! Please see our [Community Integration Guide](COMMUNITY_INTEGRATIONS.md) for the process and requirements.
+
+**Want to contribute to Pipecat core?**
 We welcome contributions of all kinds! Your help is appreciated. Follow these steps to get involved:
 
 1. **Fork this repository**: Start by forking the Pipecat Documentation repository to your GitHub account.
@@ -13,24 +17,121 @@ We welcome contributions of all kinds! Your help is appreciated. Follow these st
    git checkout -b your-branch-name
    ```
 4. **Make your changes**: Edit or add files as necessary.
-5. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
-6. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
+5. **Add a changelog entry**: Create a changelog fragment file (see [Changelog Entries](#changelog-entries) below).
+6. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
+7. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
 
 ```bash
 git commit -m "Description of your changes"
 ```
 
-7. **Push your changes**: Push your branch to your forked repository.
+8. **Push your changes**: Push your branch to your forked repository.
 
 ```bash
 git push origin your-branch-name
 ```
 
-8. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
+9. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
    > Important: Describe the changes you've made clearly!
 
 Our maintainers will review your PR, and once everything is good, your contributions will be merged!
 
+## Changelog Entries
+
+Every pull request that makes a user-facing change should include a changelog entry. We use a changelog fragment system to avoid merge conflicts.
+
+### Creating a Changelog Fragment
+
+1. Create a new file in the `changelog/` directory with this naming pattern:
+
+   ```
+   <PR_number>.<type>.md
+   ```
+
+2. Choose the appropriate type:
+
+   - `added.md` - New features
+   - `changed.md` - Changes in existing functionality
+   - `deprecated.md` - Soon-to-be removed features
+   - `removed.md` - Removed features
+   - `fixed.md` - Bug fixes
+   - `security.md` - Security fixes
+
+3. Write your changelog entry as a Markdown bullet point. Include the `-` at the start:
+
+**Example files:**
+
+`changelog/1234.added.md`:
+
+```markdown
+- Added support for Anthropic Claude 3.5 Sonnet with improved streaming performance.
+```
+
+`changelog/5678.fixed.md`:
+
+```markdown
+- Fixed an issue where audio frames were dropped during high-load scenarios.
+```
+
+**For entries with nested bullets:**
+
+`changelog/1234.changed.md`:
+
+```markdown
+- Updated service configuration:
+
+  - Changed default timeout to 30 seconds
+  - Added retry logic for failed connections
+```
+
+### Multiple Changes in One PR
+
+**Different types of changes:** Create separate fragment files for each type:
+
+```
+changelog/1234.added.md
+changelog/1234.fixed.md
+```
+
+**Multiple changes of the same type:** Create numbered fragment files:
+
+```
+changelog/1234.changed.md
+changelog/1234.changed.2.md
+```
+
+**Related changes:** Use nested bullets in a single fragment:
+
+```markdown
+- Updated service configuration:
+
+  - Changed default timeout to 30 seconds
+  - Added retry logic for failed connections
+```
+
+**Rule of thumb:** One logical change per fragment file. If changes are unrelated, use separate files.
+
+### Preview Your Changes
+
+To see what your changelog entry will look like:
+
+```bash
+towncrier build --draft --version Unreleased
+```
+
+This won't modify any files, just show you a preview.
+
+### When to Skip Changelog Entries
+
+You can skip adding a changelog entry for:
+
+- Documentation-only changes
+- Internal refactoring with no user-facing impact
+- Test-only changes
+- CI/build configuration changes
+
+If you're unsure whether your change needs a changelog entry, ask in your PR!
+
 ## Dependency Management
 
 This project uses [uv](https://docs.astral.sh/uv/) for dependency management. The `uv.lock` file is committed to ensure reproducible builds.

README.md

@@ -19,10 +19,6 @@
 - **Business Agents** – customer intake, support bots, guided flows
 - **Complex Dialog Systems** – design logic with structured conversations
 
-🧭 Looking to build structured conversations? Check out [Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) for managing complex conversational states and transitions.
-
-🔍 Looking for help debugging your pipeline and processors? Check out [Whisker](https://github.com/pipecat-ai/whisker), a real-time Pipecat debugger.
-
 ## 🧠 Why Pipecat?
 
 - **Voice-first**: Integrates speech recognition, text-to-speech, and conversation handling
@@ -30,40 +26,38 @@
 - **Composable Pipelines**: Build complex behavior from modular components
 - **Real-Time**: Ultra-low latency interaction with different transports (e.g. WebSockets or WebRTC)
 
-## 📱 Client SDKs
+## 🌐 Pipecat Ecosystem
 
-You can connect to Pipecat from any platform using our official SDKs:
+### 📱 Client SDKs
 
-<table>
-  <tr>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/javascript/javascript-original.svg" width="40" height="40" alt="JavaScript"/>
-      <a href="https://docs.pipecat.ai/client/js/introduction">JavaScript</a>
-    </td>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/react/react-original.svg" width="40" height="40" alt="React"/>
-      <a href="https://docs.pipecat.ai/client/react/introduction">React</a>
-    </td>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/react/react-original.svg" width="40" height="40" alt="React Native"/>
-      <a href="https://docs.pipecat.ai/client/react-native/introduction">React Native</a>
-    </td>
-  </tr>
-  <tr>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/swift/swift-original.svg" width="40" height="40" alt="Swift"/>
-      <a href="https://docs.pipecat.ai/client/ios/introduction">Swift</a>
-    </td>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/kotlin/kotlin-original.svg" width="40" height="40" alt="Kotlin"/>
-      <a href="https://docs.pipecat.ai/client/android/introduction">Kotlin</a>
-    </td>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/cplusplus/cplusplus-original.svg" width="40" height="40" alt="JavaScript"/>
-      <a href="https://docs.pipecat.ai/client/c++/introduction">C++</a>
-    </td>
-  </tr>
-</table>
+Building client applications? You can connect to Pipecat from any platform using our official SDKs:
+
+<a href="https://docs.pipecat.ai/client/js/introduction">JavaScript</a> | <a href="https://docs.pipecat.ai/client/react/introduction">React</a> | <a href="https://docs.pipecat.ai/client/react-native/introduction">React Native</a> |
+<a href="https://docs.pipecat.ai/client/ios/introduction">Swift</a> | <a href="https://docs.pipecat.ai/client/android/introduction">Kotlin</a> | <a href="https://docs.pipecat.ai/client/c++/introduction">C++</a> | <a href="https://github.com/pipecat-ai/pipecat-esp32">ESP32</a>
+
+### 🧭 Structured conversations
+
+Looking to build structured conversations? Check out [Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) for managing complex conversational states and transitions.
+
+### 🪄 Beautiful UIs
+
+Want to build beautiful and engaging experiences? Checkout the [Voice UI Kit](https://github.com/pipecat-ai/voice-ui-kit), a collection of components, hooks and templates for building voice AI applications quickly.
+
+### 🛠️ Create and deploy projects
+
+Create a new project in under a minute with the [Pipecat CLI](https://github.com/pipecat-ai/pipecat-cli). Then use the CLI to monitor and deploy your agent to production.
+
+### 🔍 Debugging
+
+Looking for help debugging your pipeline and processors? Check out [Whisker](https://github.com/pipecat-ai/whisker), a real-time Pipecat debugger.
+
+### 🖥️ Terminal
+
+Love terminal applications? Check out [Tail](https://github.com/pipecat-ai/tail), a terminal dashboard for Pipecat.
+
+### 📺️ Pipecat TV Channel
+
+Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.youtube.com/playlist?list=PLzU2zoMTQIHjqC3v4q2XVSR3hGSzwKFwH) channel.
 
 ## 🎬 See it in action
 
@@ -72,24 +66,24 @@ You can connect to Pipecat from any platform using our official SDKs:
     <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/storytelling-chatbot/image.png" width="400" /></a>
     <br/>
     <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/translation-chatbot/image.png" width="400" /></a>&nbsp;
-    <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/moondream-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/moondream-chatbot/image.png" width="400" /></a>
+    <a href="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/12-describe-video.py"><img src="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/assets/moondream.png" width="400" /></a>
 </p>
 
 ## 🧩 Available services
 
-| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
-| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                    |
-| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                          |
-| Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [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), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
-| Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
-| Serializers         | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
-| Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
-| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
-| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
+| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [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), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
+| Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), 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         | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 
@@ -159,7 +153,6 @@ You can get started with Pipecat running on your local machine, then move your a
      --no-extra gstreamer \
      --no-extra krisp \
      --no-extra local \
-     --no-extra ultravox # (ultravox not fully supported on macOS)
    ```
 
 3. Install the git pre-commit hooks:
@@ -184,54 +177,6 @@ Run a specific test suite:
 uv run pytest tests/test_name.py
 ```
 
-### Setting up your editor
-
-This project uses strict [PEP 8](https://peps.python.org/pep-0008/) formatting via [Ruff](https://github.com/astral-sh/ruff).
-
-#### Emacs
-
-You can use [use-package](https://github.com/jwiegley/use-package) to install [emacs-lazy-ruff](https://github.com/christophermadsen/emacs-lazy-ruff) package and configure `ruff` arguments:
-
-```elisp
-(use-package lazy-ruff
-  :ensure t
-  :hook ((python-mode . lazy-ruff-mode))
-  :config
-  (setq lazy-ruff-format-command "ruff format")
-  (setq lazy-ruff-check-command "ruff check --select I"))
-```
-
-`ruff` was installed in the `venv` environment described before, so you should be able to use [pyvenv-auto](https://github.com/ryotaro612/pyvenv-auto) to automatically load that environment inside Emacs.
-
-```elisp
-(use-package pyvenv-auto
-  :ensure t
-  :defer t
-  :hook ((python-mode . pyvenv-auto-run)))
-```
-
-#### Visual Studio Code
-
-Install the
-[Ruff](https://marketplace.visualstudio.com/items?itemName=charliermarsh.ruff) extension. Then edit the user settings (_Ctrl-Shift-P_ `Open User Settings (JSON)`) and set it as the default Python formatter, and enable formatting on save:
-
-```json
-"[python]": {
-    "editor.defaultFormatter": "charliermarsh.ruff",
-    "editor.formatOnSave": true
-}
-```
-
-#### PyCharm
-
-`ruff` was installed in the `venv` environment described before, now to enable autoformatting on save, go to `File` -> `Settings` -> `Tools` -> `File Watchers` and add a new watcher with the following settings:
-
-1. **Name**: `Ruff formatter`
-2. **File type**: `Python`
-3. **Working directory**: `$ContentRoot$`
-4. **Arguments**: `format $FilePath$`
-5. **Program**: `$PyInterpreterDirectory$/ruff`
-
 ## 🤝 Contributing
 
 We welcome contributions from the community! Whether you're fixing bugs, improving documentation, or adding new features, here's how you can help:

SECURITY.md

@@ -0,0 +1,5 @@
+# Security Policy
+
+## Reporting a Vulnerability
+
+Please email `disclosures@daily.co`.

changelog/_template.md.j2

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

docs/api/build-docs.sh

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

docs/api/conf.py

@@ -50,6 +50,7 @@ autodoc_mock_imports = [
     # Krisp - has build issues on some platforms
     "pipecat_ai_krisp",
     "krisp",
+    "krisp_audio",
     # System-specific GUI libraries
     "_tkinter",
     "tkinter",
@@ -60,9 +61,6 @@ autodoc_mock_imports = [
     # OpenCV - sometimes has import issues during docs build
     "cv2",
     # Heavy ML packages excluded from ReadTheDocs
-    # ultravox dependencies
-    "vllm",
-    "vllm.engine.arg_utils",
     # local-smart-turn dependencies
     "coremltools",
     "coremltools.models",
@@ -118,7 +116,6 @@ def import_core_modules():
         "pipecat.observers",
         "pipecat.runner",
         "pipecat.serializers",
-        "pipecat.sync",
         "pipecat.transcriptions",
         "pipecat.utils",
     ]

docs/api/index.rst

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

env.example

@@ -4,6 +4,9 @@ AICOUSTICS_LICENSE_KEY=...
 # Anthropic
 ANTHROPIC_API_KEY=...
 
+# Assembly AI
+ASSEMBLYAI_API_KEY=...
+
 # Async
 ASYNCAI_API_KEY=...
 ASYNCAI_VOICE_ID=...
@@ -21,12 +24,19 @@ AZURE_CHATGPT_API_KEY=...
 AZURE_CHATGPT_ENDPOINT=https://...
 AZURE_CHATGPT_MODEL=...
 
+AZURE_REALTIME_API_KEY=...
+AZURE_REALTIME_BASE_URL=...
+
 AZURE_DALLE_API_KEY=...
 AZURE_DALLE_ENDPOINT=https://...
 AZURE_DALLE_MODEL=...
 
 # Cartesia
 CARTESIA_API_KEY=...
+CARTESIA_VOICE_ID=...
+
+# Cerebras
+CEREBRAS_API_KEY=...
 
 # Daily
 DAILY_API_KEY=...
@@ -34,40 +44,81 @@ DAILY_SAMPLE_ROOM_URL=https://...
 
 # Deepgram
 DEEPGRAM_API_KEY=...
+SAGEMAKER_ENDPOINT_NAME=...
+
+# DeepSeek
+DEEPSEEK_API_KEY=...
 
 # ElevenLabs
 ELEVENLABS_API_KEY=...
 ELEVENLABS_VOICE_ID=...
 
-# Neuphonic
-NEUPHONIC_API_KEY=...
-
 # Fal
 FAL_KEY=...
 
 # Fireworks
 FIREWORKS_API_KEY=...
 
+# Fish Audio
+FISH_API_KEY=...
+
 # Gladia
 GLADIA_API_KEY=...
 GLADIA_REGION=...
 
 # Google
 GOOGLE_API_KEY=...
-GOOGLE_CLOUD_PROJECT_ID=...
-GOOGLE_TEST_CREDENTIALS=...
 GOOGLE_VERTEX_TEST_CREDENTIALS=...
+GOOGLE_CLOUD_PROJECT_ID=...
+GOOGLE_CLOUD_LOCATION=...
+GOOGLE_TEST_CREDENTIALS=...
+
+# Gradium
+GRAPDIUM_API_KEY=...
+
+# Grok
+GROK_API_KEY=...
+
+# Groq
+GROQ_API_KEY=...
+
+# Heygen
+HEYGEN_API_KEY=...
+HEYGEN_LIVE_AVATAR_API_KEY=...
+
+# Hume
+HUME_API_KEY=...
+HUME_VOICE_ID=...
+
+# Inworld
+INWORLD_API_KEY=...
+
+# Krisp
+KRISP_MODEL_PATH=...
+
+# Krisp Viva
+KRISP_VIVA_MODEL_PATH=...
+
+# LiveKit
+LIVEKIT_API_KEY=...
+LIVEKIT_API_SECRET=...
 
 # LMNT
 LMNT_API_KEY=...
 LMNT_VOICE_ID=...
 
-# Perplexity
-PERPLEXITY_API_KEY=...
+# MiniMax
+MINIMAX_API_KEY=...
+MINIMAX_GROUP_ID=...
 
-# PlayHT
-PLAYHT_USER_ID=...
-PLAYHT_API_KEY=...
+# Mistral
+MISTRAL_API_KEY=...
+
+# Neuphonic
+NEUPHONIC_API_KEY=...
+
+# NVIDIA
+NVIDIA_API_KEY=...
 
 # OpenAI
 OPENAI_API_KEY=...
@@ -75,83 +126,76 @@ OPENAI_API_KEY=...
 # OpenPipe
 OPENPIPE_API_KEY=...
 
-# Tavus
-TAVUS_API_KEY=...
-TAVUS_REPLICA_ID=...
-TAVUS_PERSONA_ID=...
+# OpenRouter
+OPENROUTER_API_KEY=...
+
+# Perplexity
+PERPLEXITY_API_KEY=...
+
+# Picovoice Koala
+KOALA_ACCESS_KEY=...
+
+# Piper
+PIPER_BASE_URL=...
+
+# PlayHT
+PLAYHT_USER_ID=...
+PLAYHT_API_KEY=...
+
+# Plivo
+PLIVO_AUTH_ID=...
+PLIVO_AUTH_TOKEN=...
+
+# Qwen
+QWEN_API_KEY=...
+
+# Rime
+RIME_API_KEY=...
+RIME_VOICE_ID=...
+
+# SambaNova
+SAMBANOVA_API_KEY=...
+
+# Sarvam AI
+SARVAM_API_KEY=...
+
+# Sentry
+SENTRY_DSN=...
 
 # Simli
 SIMLI_API_KEY=...
 SIMLI_FACE_ID=...
 
-# Krisp
-KRISP_MODEL_PATH=...
-
-# DeepSeek
-DEEPSEEK_API_KEY=...
-
-# Groq
-GROQ_API_KEY=...
-
-# Grok
-GROK_API_KEY=...
-
-# Inworld
-INWORLD_API_KEY=...
-
-# Together.ai
-TOGETHER_API_KEY=...
-
-# Cerebras
-CEREBRAS_API_KEY=...
-
-# Fish Audio
-FISH_API_KEY=...
-
-# Assembly AI
-ASSEMBLYAI_API_KEY=...
-
-# OpenRouter
-OPENROUTER_API_KEY=...
-
-# Piper
-PIPER_BASE_URL=...
-
 # Smart turn
 LOCAL_SMART_TURN_MODEL_PATH=...
 FAL_SMART_TURN_API_KEY=...
 
+# Soniox
+SONIOX_API_KEY=...
+
+# Speechmatics
+SPEECHMATICS_API_KEY=...
+
+# Tavus
+TAVUS_API_KEY=...
+TAVUS_REPLICA_ID=...
+
+# Telnyx
+TELNYX_API_KEY=...
+TELNYX_ACCOUNT_SID=...
+
+# Together.ai
+TOGETHER_API_KEY=...
+
 # Twilio
 TWILIO_ACCOUNT_SID=...
 TWILIO_AUTH_TOKEN=...
 
-# MiniMax
-MINIMAX_API_KEY=...
-MINIMAX_GROUP_ID=...
+# Ultravox Realtime
+ULTRAVOX_API_KEY=...
 
-# Sarvam AI
-SARVAM_API_KEY=...
-
-# Soniox
-SONIOX_API_KEY=
-
-# Speechmatics
-SPEECHMATICS_API_KEY=...
-
-# SambaNova
-SAMBANOVA_API_KEY=...
-
-# Sentry
-SENTRY_DSN=...
-
-# Heygen
-HEYGEN_API_KEY=...
-
-# Mistral
-MISTRAL_API_KEY=...
-
-# NVIDIA
-NVIDIA_API_KEY=...
-
-# Qwen
-QWEN_API_KEY=...
+# WhatsApp
+WHATSAPP_TOKEN=...
+WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=...
+WHATSAPP_PHONE_NUMBER_ID=...
+WHATSAPP_APP_SECRET=...

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

@@ -15,7 +15,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.riva.tts import FastPitchTTSService
+from pipecat.services.nvidia.tts import NvidiaTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -36,7 +36,7 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+    tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
 
     task = PipelineTask(
         Pipeline([tts, transport.output()]),

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

@@ -77,7 +77,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -25,7 +25,7 @@ from pipecat.processors.aggregators.llm_response_universal import LLMContextAggr
 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 DailyLogLevel, DailyParams, DailyTransport
+from pipecat.transports.daily.transport import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -49,7 +49,6 @@ async def main():
                 turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
             ),
         )
-        transport.set_log_level(DailyLogLevel.Info)
 
         tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
@@ -61,7 +60,7 @@ async def main():
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "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.",
             },
         ]
 

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

@@ -69,7 +69,7 @@ async def main():
             "role": "system",
             "content": "You are a helpful LLM in a WebRTC call. "
             "Your goal is to demonstrate your capabilities in a succinct way. "
-            "Your output will be converted to audio so don't include special characters in your answers. "
+            "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.",
         },
     ]

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

@@ -100,7 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -113,7 +113,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -21,8 +21,8 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.stt import CartesiaSTTService
 from pipecat.services.cartesia.tts import CartesiaHttpTTSService
-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
@@ -59,7 +59,7 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
 
     tts = CartesiaHttpTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/07-interruptible.py

@@ -70,7 +70,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -6,6 +6,7 @@
 
 import os
 
+import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
@@ -20,10 +21,10 @@ from pipecat.processors.aggregators.llm_response import (
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
 from pipecat.services.openai.base_llm import BaseOpenAILLMService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
+from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
@@ -51,121 +52,127 @@ transport_params = {
 
 
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
-    """Speechmatics STT Service Example
+    """Speechmatics STT and TTS Service Example
 
-    This example demonstrates using Speechmatics Speech-to-Text service with speaker diarization and intelligent speaker management. Key features:
+    This example demonstrates using Speechmatics Speech-to-Text and Text-to-Speech services
+    with speaker diarization and intelligent speaker management. Key features:
 
-    1. Speaker Diarization
+    1. Speaker Diarization (STT)
        - Automatically identifies and distinguishes between different speakers
        - First speaker is identified as 'S1', others get subsequent IDs
        - Uses `enable_diarization` parameter to manage speaker detection
 
-    2. Smart Speaker Control
+    2. Smart Speaker Control (STT)
        - `focus_speakers` parameter lets you target specific speakers (e.g. ["S1"])
        - Other speakers will be wrapped in PASSIVE tags
        - Only processes speech from focused speakers
        - Words from all speakers are wrapped with XML tags for clear speaker identification
        - Other speakers' speech only sent when focused speaker is active
 
-    3. Voice Activity Detection
+    3. Voice Activity Detection (STT)
        - Built-in VAD using `enable_vad` parameter
        - Remove `vad_analyzer` from `transport` config to use module's VAD
        - Emits speaker started/stopped events
 
-    4. Configuration Options
+    4. Text-to-Speech (TTS)
+       - Low latency streaming audio synthesis
+       - Multiple voice options available including `sarah`, `theo`, and `megan`
+
+    5. Configuration Options
        - `operating_point` parameter defaults to `ENHANCED` for optimal accuracy
        - Configurable `end_of_utterance_silence_trigger` (default 0.5s)
        - Customizable speaker formatting
        - Additional diarization settings available
 
-    For detailed information about operating points and configuration:
-    https://docs.speechmatics.com/rt-api-ref
+    For detailed information:
+    - STT: https://docs.speechmatics.com/rt-api-ref
+    - TTS: https://docs.speechmatics.com/text-to-speech/quickstart
     """
 
     logger.info(f"Starting bot")
-
-    stt = SpeechmaticsSTTService(
-        api_key=os.getenv("SPEECHMATICS_API_KEY"),
-        params=SpeechmaticsSTTService.InputParams(
-            language=Language.EN,
-            enable_vad=True,
-            enable_diarization=True,
-            focus_speakers=["S1"],
-            end_of_utterance_silence_trigger=0.5,
-            speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
-            speaker_passive_format="<PASSIVE><{speaker_id}>{text}</{speaker_id}></PASSIVE>",
-        ),
-    )
-
-    tts = ElevenLabsTTSService(
-        api_key=os.getenv("ELEVENLABS_API_KEY"),
-        voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
-        model="eleven_turbo_v2_5",
-    )
-
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        params=BaseOpenAILLMService.InputParams(temperature=0.75),
-    )
-
-    messages = [
-        {
-            "role": "system",
-            "content": (
-                "You are a helpful British assistant called Alfred. "
-                "Your goal is to demonstrate your capabilities in a succinct way. "
-                "Your output will be converted to audio so don't include special characters in your answers. "
-                "Always include punctuation in your responses. "
-                "Give very short replies - do not give longer replies unless strictly necessary. "
-                "Respond to what the user said in a concise, funny, creative and helpful way. "
-                "Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. "
-                "Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to. "
+    async with aiohttp.ClientSession() as session:
+        stt = SpeechmaticsSTTService(
+            api_key=os.getenv("SPEECHMATICS_API_KEY"),
+            params=SpeechmaticsSTTService.InputParams(
+                language=Language.EN,
+                enable_vad=True,
+                enable_diarization=True,
+                focus_speakers=["S1"],
+                end_of_utterance_silence_trigger=0.5,
+                speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
+                speaker_passive_format="<PASSIVE><{speaker_id}>{text}</{speaker_id}></PASSIVE>",
             ),
-        },
-    ]
+        )
 
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
-    )
+        tts = SpeechmaticsTTSService(
+            api_key=os.getenv("SPEECHMATICS_API_KEY"),
+            voice_id="sarah",
+            aiohttp_session=session,
+        )
 
-    pipeline = Pipeline(
-        [
-            transport.input(),  # Transport user input
-            stt,
-            context_aggregator.user(),  # User responses
-            llm,  # LLM
-            tts,  # TTS
-            transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            params=BaseOpenAILLMService.InputParams(temperature=0.75),
+        )
+
+        messages = [
+            {
+                "role": "system",
+                "content": (
+                    "You are a helpful British assistant called Sarah. "
+                    "Your goal is to demonstrate your capabilities in a succinct way. "
+                    "Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. "
+                    "Always include punctuation in your responses. "
+                    "Give very short replies - do not give longer replies unless strictly necessary. "
+                    "Respond to what the user said in a concise, funny, creative and helpful way. "
+                    "Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. "
+                    "Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to. "
+                ),
+            },
         ]
-    )
 
-    task = PipelineTask(
-        pipeline,
-        params=PipelineParams(
-            enable_metrics=True,
-            enable_usage_metrics=True,
-        ),
-        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
-    )
+        context = LLMContext(messages)
+        context_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
+        )
 
-    @transport.event_handler("on_client_connected")
-    async def on_client_connected(transport, client):
-        logger.info(f"Client connected")
-        # Kick off the conversation.
-        messages.append({"role": "system", "content": "Say a short hello to the user."})
-        await task.queue_frames([LLMRunFrame()])
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
 
-    @transport.event_handler("on_client_disconnected")
-    async def on_client_disconnected(transport, client):
-        logger.info(f"Client disconnected")
-        await task.cancel()
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
 
-    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info(f"Client connected")
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Say a short hello to the user."})
+            await task.queue_frames([LLMRunFrame()])
 
-    await runner.run(task)
+        @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):

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

@@ -6,6 +6,7 @@
 
 import os
 
+import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
@@ -24,10 +25,10 @@ from pipecat.processors.aggregators.llm_response import (
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
 from pipecat.services.openai.base_llm import BaseOpenAILLMService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
+from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
@@ -61,100 +62,106 @@ transport_params = {
 
 
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
-    """Run example using Speechmatics STT.
+    """Run example using Speechmatics STT and TTS.
 
-    This example will use diarization within our STT service and output the words spoken by
-    each individual speaker and wrap them with XML tags for the LLM to process. Note the
-    instructions in the system context for the LLM. This greatly improves the conversation
-    experience by allowing the LLM to understand who is speaking in a multi-party call.
+    This example demonstrates a complete Speechmatics integration with both Speech-to-Text
+    and Text-to-Speech services:
 
-    By default, this example will use our ENHANCED operating point, which is optimized for
-    high accuracy. You can change this by setting the `operating_point` parameter to a different
-    value.
+    STT Features:
+    - Diarization to identify and distinguish between different speakers
+    - Words spoken by each speaker are wrapped with XML tags for LLM processing
+    - System context instructions help the LLM understand multi-party conversations
+    - ENHANCED operating point by default for optimal accuracy
 
-    For more information on operating points, see the Speechmatics documentation:
-    https://docs.speechmatics.com/rt-api-ref
+    TTS Features:
+    - Low latency streaming audio synthesis
+    - Multiple voice options available including `sarah`, `theo`, and `megan`
+
+    For more information:
+    - STT: https://docs.speechmatics.com/rt-api-ref
+    - TTS: https://docs.speechmatics.com/text-to-speech/quickstart
     """
     logger.info(f"Starting bot")
 
-    stt = SpeechmaticsSTTService(
-        api_key=os.getenv("SPEECHMATICS_API_KEY"),
-        params=SpeechmaticsSTTService.InputParams(
-            language=Language.EN,
-            enable_diarization=True,
-            end_of_utterance_silence_trigger=0.5,
-            speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
-        ),
-    )
-
-    tts = ElevenLabsTTSService(
-        api_key=os.getenv("ELEVENLABS_API_KEY"),
-        voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
-        model="eleven_turbo_v2_5",
-    )
-
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        params=BaseOpenAILLMService.InputParams(temperature=0.75),
-    )
-
-    messages = [
-        {
-            "role": "system",
-            "content": (
-                "You are a helpful British assistant called Alfred. "
-                "Your goal is to demonstrate your capabilities in a succinct way. "
-                "Your output will be converted to audio so don't include special characters in your answers. "
-                "Always include punctuation in your responses. "
-                "Give very short replies - do not give longer replies unless strictly necessary. "
-                "Respond to what the user said in a concise, funny, creative and helpful way. "
-                "Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
+    async with aiohttp.ClientSession() as session:
+        stt = SpeechmaticsSTTService(
+            api_key=os.getenv("SPEECHMATICS_API_KEY"),
+            params=SpeechmaticsSTTService.InputParams(
+                language=Language.EN,
+                enable_diarization=True,
+                end_of_utterance_silence_trigger=0.5,
+                speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
             ),
-        },
-    ]
+        )
 
-    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
-    )
+        tts = SpeechmaticsTTSService(
+            api_key=os.getenv("SPEECHMATICS_API_KEY"),
+            voice_id="sarah",
+            aiohttp_session=session,
+        )
 
-    pipeline = Pipeline(
-        [
-            transport.input(),  # Transport user input
-            stt,  # STT
-            context_aggregator.user(),  # User responses
-            llm,  # LLM
-            tts,  # TTS
-            transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            params=BaseOpenAILLMService.InputParams(temperature=0.75),
+        )
+
+        messages = [
+            {
+                "role": "system",
+                "content": (
+                    "You are a helpful British assistant called Sarah. "
+                    "Your goal is to demonstrate your capabilities in a succinct way. "
+                    "Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. "
+                    "Always include punctuation in your responses. "
+                    "Give very short replies - do not give longer replies unless strictly necessary. "
+                    "Respond to what the user said in a concise, funny, creative and helpful way. "
+                    "Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
+                ),
+            },
         ]
-    )
 
-    task = PipelineTask(
-        pipeline,
-        params=PipelineParams(
-            enable_metrics=True,
-            enable_usage_metrics=True,
-        ),
-        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
-    )
+        context = LLMContext(messages)
+        context_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
+        )
 
-    @transport.event_handler("on_client_connected")
-    async def on_client_connected(transport, client):
-        logger.info(f"Client connected")
-        # Kick off the conversation.
-        messages.append({"role": "system", "content": "Say a short hello to the user."})
-        await task.queue_frames([LLMRunFrame()])
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
 
-    @transport.event_handler("on_client_disconnected")
-    async def on_client_disconnected(transport, client):
-        logger.info(f"Client disconnected")
-        await task.cancel()
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
 
-    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info(f"Client connected")
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Say a short hello to the user."})
+            await task.queue_frames([LLMRunFrame()])
 
-    await runner.run(task)
+        @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):

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

@@ -70,7 +70,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -4,7 +4,6 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-
 import os
 
 import aiohttp
@@ -15,26 +14,26 @@ from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import LLMRunFrame
+from pipecat.frames.frames import LLMRunFrame, TTSTextFrame
+from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.frameworks.rtvi import RTVIObserver, RTVIProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
-from pipecat.services.inworld.tts import InworldTTSService
+from pipecat.services.inworld.tts import InworldHttpTTSService
 from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_output import BaseOutputTransport
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# 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,
@@ -58,22 +57,18 @@ transport_params = {
 
 
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
-    logger.info(f"Starting bot")
+    logger.info("Starting bot")
 
-    # Create an HTTP session
     async with aiohttp.ClientSession() as session:
         stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        # Inworld TTS Service - Unified streaming and non-streaming
-        # Set streaming=True for real-time audio, streaming=False for complete audio generation
-        streaming = True  # Toggle this to switch between modes
-
-        tts = InworldTTSService(
+        tts = InworldHttpTTSService(
             api_key=os.getenv("INWORLD_API_KEY", ""),
             aiohttp_session=session,
             voice_id="Ashley",
             model="inworld-tts-1",
-            streaming=streaming,  # True: real-time chunks, False: complete audio then playback
+            # Set to False for non-streaming mode or True for streaming mode.
+            streaming=True,
         )
 
         llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
@@ -81,22 +76,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are very knowledgable about dogs. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful AI demonstrating Inworld AI's TTS. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a friendly and helpful way.",
             },
         ]
 
         context = LLMContext(messages)
         context_aggregator = LLMContextAggregatorPair(context)
 
+        rtvi = RTVIProcessor()
+
         pipeline = Pipeline(
             [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                transport.input(),
+                rtvi,
+                stt,
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
             ]
         )
 
@@ -106,19 +104,27 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 enable_metrics=True,
                 enable_usage_metrics=True,
             ),
+            observers=[
+                RTVIObserver(rtvi),
+                DebugLogObserver(
+                    frame_types={
+                        TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
+                    }
+                ),
+            ],
             idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )
 
         @transport.event_handler("on_client_connected")
         async def on_client_connected(transport, client):
-            logger.info(f"Client connected")
+            logger.info("Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):
-            logger.info(f"Client disconnected")
+            logger.info("Client disconnected")
             await task.cancel()
 
         runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)

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

@@ -0,0 +1,141 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame, TTSTextFrame
+from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.inworld.tts import InworldTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_output import BaseOutputTransport
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info("Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = InworldTTSService(
+        api_key=os.getenv("INWORLD_API_KEY", ""),
+        voice_id="Ashley",
+        model="inworld-tts-1",
+        temperature=1.1,
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful AI demonstrating Inworld AI's TTS. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a friendly and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            rtvi,
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        observers=[
+            RTVIObserver(rtvi),
+            DebugLogObserver(
+                frame_types={
+                    TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
+                }
+            ),
+        ],
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info("Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info("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/07ac-interruptible-asyncai-http.py

@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "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.",
             },
         ]
 

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

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/07ad-interruptible-aicoustics.py

@@ -15,7 +15,6 @@ from loguru import logger
 from pipecat.audio.filters.aic_filter import AICFilter
 from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
-from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -48,7 +47,7 @@ def _create_aic_filter() -> AICFilter:
 
     return AICFilter(
         license_key=license_key,
-        enhancement_level=1.0,
+        enhancement_level=0.5,
     )
 
 
@@ -56,27 +55,33 @@ def _create_aic_filter() -> AICFilter:
 # 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)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-        audio_in_filter=_create_aic_filter(),
-    ),
-    "twilio": lambda: FastAPIWebsocketParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-        audio_in_filter=_create_aic_filter(),
-    ),
-    "webrtc": lambda: TransportParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-        audio_in_filter=_create_aic_filter(),
-    ),
+    "daily": lambda: (
+        lambda aic: DailyParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_analyzer=aic.create_vad_analyzer(lookback_buffer_size=6.0, sensitivity=6.0),
+            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+            audio_in_filter=aic,
+        )
+    )(_create_aic_filter()),
+    "twilio": lambda: (
+        lambda aic: FastAPIWebsocketParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_analyzer=aic.create_vad_analyzer(lookback_buffer_size=6.0, sensitivity=6.0),
+            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+            audio_in_filter=aic,
+        )
+    )(_create_aic_filter()),
+    "webrtc": lambda: (
+        lambda aic: TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_analyzer=aic.create_vad_analyzer(lookback_buffer_size=6.0, sensitivity=6.0),
+            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+            audio_in_filter=aic,
+        )
+    )(_create_aic_filter()),
 }
 
 
@@ -95,7 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/07ae-interruptible-hume.py

@@ -0,0 +1,153 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame, TTSTextFrame
+from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+)
+from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.hume.tts import HUME_SAMPLE_RATE, HumeTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_output import BaseOutputTransport
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+# 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)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = HumeTTSService(
+        api_key=os.getenv("HUME_API_KEY"),
+        # Replace with your Hume voice ID
+        voice_id="f898a92e-685f-43fa-985b-a46920f0650b",
+    )
+
+    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)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            rtvi,
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS (HumeTTSService with word timestamps)
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            audio_out_sample_rate=HUME_SAMPLE_RATE,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        observers=[
+            RTVIObserver(rtvi),
+            DebugLogObserver(
+                frame_types={
+                    TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
+                }
+            ),
+        ],
+    )
+
+    @rtvi.event_handler("on_client_ready")
+    async def on_client_ready(rtvi):
+        await rtvi.set_bot_ready()
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        logger.info(
+            "💡 Word timestamps are enabled! Watch the console for TTSTextFrame logs showing each word with its PTS."
+        )
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    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/07af-interruptible-gradium.py

@@ -0,0 +1,127 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.gradium.stt import GradiumSTTService
+from pipecat.services.gradium.tts import GradiumTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# 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)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = GradiumSTTService(api_key=os.getenv("GRADIUM_API_KEY"))
+
+    tts = GradiumTTSService(
+        api_key=os.getenv("GRADIUM_API_KEY"),
+        voice_id="YTpq7expH9539ERJ",
+    )
+
+    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)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

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

@@ -0,0 +1,125 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+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_response_universal import (
+    LLMContext,
+    LLMContextAggregatorPair,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.flux.stt import DeepgramFluxSTTService
+from pipecat.services.deepgram.tts import DeepgramTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+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 = DeepgramFluxSTTService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        params=DeepgramFluxSTTService.InputParams(min_confidence=0.3),
+    )
+
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
+
+    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)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    @stt.event_handler("on_update")
+    async def on_deepgram_flux_update(stt, transcript):
+        logger.debug(f"On deeggram flux update: {transcript}")
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

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

@@ -0,0 +1,132 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.deepgram.tts import DeepgramHttpTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+# 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)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    async with aiohttp.ClientSession() as session:
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = DeepgramHttpTTSService(
+            api_key=os.getenv("DEEPGRAM_API_KEY"),
+            voice="aura-2-andromeda-en",
+            aiohttp_session=session,
+        )
+
+        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)
+        context_aggregator = LLMContextAggregatorPair(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
+
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info(f"Client connected")
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([LLMRunFrame()])
+
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+            await task.cancel()
+
+        runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+        await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

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

@@ -0,0 +1,137 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.aws.llm import AWSBedrockLLMService
+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
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    # Initialize Deepgram SageMaker STT Service
+    # This requires:
+    # - AWS credentials configured (via environment variables or AWS CLI)
+    # - A deployed SageMaker endpoint with Deepgram model
+    stt = DeepgramSageMakerSTTService(
+        endpoint_name=os.getenv("SAGEMAKER_ENDPOINT_NAME"),
+        region=os.getenv("AWS_REGION"),
+    )
+
+    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),
+    )
+
+    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)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

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

@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -69,7 +69,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -23,7 +23,6 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.elevenlabs.stt import ElevenLabsSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService
 from pipecat.services.openai.llm import OpenAILLMService
@@ -80,7 +79,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "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.",
             },
         ]
 

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

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.elevenlabs.stt import ElevenLabsRealtimeSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -60,7 +60,7 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = ElevenLabsRealtimeSTTService(api_key=os.getenv("ELEVENLABS_API_KEY"))
 
     tts = ElevenLabsTTSService(
         api_key=os.getenv("ELEVENLABS_API_KEY", ""),
@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -0,0 +1,135 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.azure.llm import AzureLLMService
+from pipecat.services.azure.stt import AzureSTTService
+from pipecat.services.azure.tts import AzureHttpTTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We 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)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = AzureSTTService(
+        api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+        region=os.getenv("AZURE_SPEECH_REGION"),
+    )
+
+    tts = AzureHttpTTSService(
+        api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+        region=os.getenv("AZURE_SPEECH_REGION"),
+    )
+
+    llm = AzureLLMService(
+        api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+        endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+        model=os.getenv("AZURE_CHATGPT_MODEL"),
+    )
+
+    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)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

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

@@ -78,7 +78,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are very knowledgable about dogs. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -75,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "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.",
             },
         ]
 

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

@@ -81,7 +81,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "content": f"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.",
         },
     ]
 

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

@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -71,9 +71,9 @@ def build_agent(model_id: str, max_tokens: int):
     @tool
     def check_weather(location: str) -> str:
         if location.lower() == "san francisco":
-            return "The weather in San Francisco is sunny and 30 degrees."
+            return "The weather in San Francisco is sunny and 75 degrees."
         elif location.lower() == "sydney":
-            return "The weather in Sydney is cloudy and 20 degrees."
+            return "The weather in Sydney is cloudy and 60 degrees."
         else:
             return "I'm not sure about the weather in that location."
 

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

@@ -67,14 +67,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = AWSBedrockLLMService(
         aws_region="us-west-2",
-        model="us.anthropic.claude-3-5-haiku-20241022-v1:0",
-        params=AWSBedrockLLMService.InputParams(temperature=0.8, latency="optimized"),
+        model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
+        params=AWSBedrockLLMService.InputParams(temperature=0.8),
     )
 
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -0,0 +1,152 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""
+A conversational AI bot using Gemini for both LLM, STT and TTS.
+
+This example demonstrates how to use Gemini's image generation capabilities.
+
+Features showcased:
+- Gemini LLM for conversation and image generation
+- Google TTS and STT
+
+Run with:
+    python examples/foundational/07n-interruptible-gemini-image.py
+
+Make sure to set your environment variables:
+    export GOOGLE_API_KEY=your_api_key_here
+"""
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.google.llm import GoogleLLMService
+from pipecat.services.google.stt import GoogleSTTService
+from pipecat.services.google.tts import GoogleTTSService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_out_enabled=True,
+        video_out_width=1024,
+        video_out_height=1024,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_out_enabled=True,
+        video_out_width=1024,
+        video_out_height=1024,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = GoogleSTTService(
+        params=GoogleSTTService.InputParams(languages=Language.EN_US),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+    )
+
+    tts = GoogleTTSService(
+        voice_id="en-US-Chirp3-HD-Charon",
+        params=GoogleTTSService.InputParams(language=Language.EN_US),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+    )
+
+    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
+    )
+
+    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)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # Gemini TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation with a styled introduction
+        messages.append({"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/07n-interruptible-gemini.py

@@ -4,24 +4,6 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""
-A conversational AI bot using Gemini for both LLM and TTS.
-
-This example demonstrates how to use Gemini's TTS capabilities with the new
-GeminiTTSService, which uses Gemini's TTS-specific models instead of Google Cloud TTS.
-
-Features showcased:
-- Gemini LLM for conversation
-- Gemini TTS with natural voice control
-- Support for different voice personalities
-- Style and tone control through natural language prompts
-
-Run with:
-    python examples/foundational/gemini-tts.py
-
-Make sure to set your environment variables:
-    export GOOGLE_API_KEY=your_api_key_here
-"""
 
 import os
 
@@ -84,10 +66,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tts = GeminiTTSService(
-        api_key=os.getenv("GOOGLE_API_KEY"),
-        model="gemini-2.5-flash-preview-tts",  # TTS-specific model
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+        model="gemini-2.5-flash-tts",
         voice_id="Charon",
-        params=GeminiTTSService.InputParams(language=Language.EN_US),
+        params=GeminiTTSService.InputParams(
+            language=Language.EN_US,
+            prompt="You are a helpful AI assistant. Speak in a natural, conversational tone.",
+        ),
     )
 
     llm = GoogleLLMService(
@@ -101,15 +86,22 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             "role": "system",
             "content": """You are a helpful AI assistant in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
 
-            IMPORTANT: Since you're using Gemini TTS which supports natural voice control, you can include speaking instructions in your responses. For example:
-            - "Say cheerfully: Welcome to our conversation!"
-            - "Read this in a calm, professional tone: Here are the details you requested."
-            - "Speak in an excited whisper: I have some great news to share!"
-            - "Say slowly and clearly: Let me explain this step by step."
+            IMPORTANT: You're using Gemini TTS which supports expressive markup tags. You can use these tags in your responses:
+            - [sigh] - Insert a sigh sound
+            - [laughing] - Insert a laugh
+            - [uhm] - Insert a hesitation sound
+            - [whispering] - Speak the next part in a whisper
+            - [shouting] - Speak the next part louder
+            - [extremely fast] - Speak the next part very quickly
+            - [short pause], [medium pause], [long pause] - Add pauses for dramatic effect
 
-            Feel free to use natural language instructions to control your voice style, tone, pace, and emotion. The TTS system will interpret these instructions and adjust the speech accordingly.
+            Examples:
+            - "Well [sigh] that's a tricky question."
+            - "[laughing] That's a great joke!"
+            - "[whispering] Let me tell you a secret."
+            - "The answer is... [long pause] ...42!"
 
-            Your output will be converted to audio, so avoid special characters in your answers. Respond to what the user said in a creative and helpful way.""",
+            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.""",
         },
     ]
 
@@ -140,11 +132,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
-        # Kick off the conversation with a styled introduction
+        # Kick off the conversation
         messages.append(
             {
                 "role": "system",
-                "content": "Say cheerfully and warmly: Hello! I'm your AI assistant powered by Gemini's new TTS technology. I can speak with different voices, tones, and styles. How can I help you today?",
+                "content": "You are an AI assistant. You can help with a variety of tasks. Introduce yourself and ask the user what they would like to know.",
             }
         )
         await task.queue_frames([LLMRunFrame()])

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

@@ -0,0 +1,141 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.google.llm import GoogleLLMService
+from pipecat.services.google.stt import GoogleSTTService
+from pipecat.services.google.tts import GoogleHttpTTSService, GoogleTTSService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = GoogleSTTService(
+        params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+        location="us",
+    )
+
+    tts = GoogleHttpTTSService(
+        voice_id="en-US-Chirp3-HD-Charon",
+        params=GoogleHttpTTSService.InputParams(language=Language.EN_US),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+    )
+
+    llm = GoogleLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        model="gemini-2.5-flash",
+        # force a certain amount of thinking if you want it
+        # params=GoogleLLMService.InputParams(
+        #     thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
+        # ),
+    )
+
+    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)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User respones
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

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

@@ -61,8 +61,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
     stt = GoogleSTTService(
-        params=GoogleSTTService.InputParams(languages=Language.EN_US),
+        params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+        location="us",
     )
 
     tts = GoogleTTSService(
@@ -74,14 +75,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         model="gemini-2.5-flash",
-        # turn on thinking if you want it
-        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),)
+        # force a certain amount of thinking if you want it
+        # params=GoogleLLMService.InputParams(
+        #     thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
+        # ),
     )
 
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -0,0 +1,129 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.filters.krisp_viva_filter import KrispVivaFilter
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.deepgram.tts import DeepgramTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+        audio_in_filter=KrispVivaFilter(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+        audio_in_filter=KrispVivaFilter(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+        audio_in_filter=KrispVivaFilter(),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
+
+    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)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    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/07p-interruptible-krisp.py

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "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.",
             },
         ]
 

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

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.nim.llm import NimLLMService
-from pipecat.services.riva.stt import RivaSTTService
-from pipecat.services.riva.tts import RivaTTSService
+from pipecat.services.nvidia.llm import NvidiaLLMService
+from pipecat.services.nvidia.stt import NvidiaSTTService
+from pipecat.services.nvidia.tts import NvidiaTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,16 +59,18 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = RivaSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
+    stt = NvidiaSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
 
-    llm = NimLLMService(api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct")
+    llm = NvidiaLLMService(
+        api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct"
+    )
 
-    tts = RivaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+    tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
 
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -53,7 +53,7 @@ You are a helpful LLM in a WebRTC call. Your goals are to be helpful and brief i
 You are expert at transcribing audio to text. You will receive a mixture of audio and text input. When
 asked to transcribe what the user said, output an exact, word-for-word transcription.
 
-Your output will be converted to audio so don't include special characters in your answers.
+Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points.
 
 Each time you answer, you should respond in three parts.
 
@@ -224,8 +224,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         model="gemini-2.5-flash",
-        # turn on thinking if you want it
-        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),
+        # force a certain amount of thinking if you want it
+        # params=GoogleLLMService.InputParams(
+        #     thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
+        # ),
     )
 
     tts = GoogleTTSService(

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

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "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.",
             },
         ]
 

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

@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -56,7 +56,7 @@ async def main():
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

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

@@ -78,7 +78,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "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.",
             },
         ]
 

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

@@ -15,6 +15,7 @@ from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.sarvam.stt import SarvamSTTService
 from pipecat.services.sarvam.tts import SarvamHttpTTSService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -63,7 +64,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     # Create an HTTP session
     async with aiohttp.ClientSession() as session:
-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+        stt = SarvamSTTService(
+            api_key=os.getenv("SARVAM_API_KEY"),
+            model="saarika:v2.5",
+        )
 
         tts = SarvamHttpTTSService(
             api_key=os.getenv("SARVAM_API_KEY"),
@@ -76,7 +80,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "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.",
             },
         ]
 
@@ -109,7 +113,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):

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

@@ -24,8 +24,8 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.sarvam.stt import SarvamSTTService
 from pipecat.services.sarvam.tts import SarvamTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
@@ -62,7 +62,10 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = SarvamSTTService(
+        api_key=os.getenv("SARVAM_API_KEY"),
+        model="saarika:v2.5",
+    )
 
     tts = SarvamTTSService(
         api_key=os.getenv("SARVAM_API_KEY"),
@@ -74,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/08-bots-arguing.py

@@ -1,147 +0,0 @@
-import asyncio
-import logging
-import os
-from typing import Tuple
-
-import aiohttp
-from dotenv import load_dotenv
-
-from pipecat.frames.frames import AudioFrame, EndFrame, ImageFrame, LLMContextFrame, TextFrame
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.processors.aggregators import SentenceAggregator
-from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
-from pipecat.runner.daily import configure
-from pipecat.services.azure import AzureLLMService, AzureTTSService
-from pipecat.services.elevenlabs import ElevenLabsTTSService
-from pipecat.services.fal import FalImageGenService
-from pipecat.transports.daily.transport import DailyTransport
-
-load_dotenv(override=True)
-
-logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
-logger = logging.getLogger("pipecat")
-logger.setLevel(logging.DEBUG)
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            None,
-            "Respond bot",
-            duration_minutes=10,
-            mic_enabled=True,
-            mic_sample_rate=16000,
-            camera_enabled=True,
-            camera_width=1024,
-            camera_height=1024,
-        )
-
-        llm = AzureLLMService(
-            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
-            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
-            model=os.getenv("AZURE_CHATGPT_MODEL"),
-        )
-        tts1 = AzureTTSService(
-            api_key=os.getenv("AZURE_SPEECH_API_KEY"),
-            region=os.getenv("AZURE_SPEECH_REGION"),
-        )
-        tts2 = ElevenLabsTTSService(
-            api_key=os.getenv("ELEVENLABS_API_KEY"),
-            voice_id="jBpfuIE2acCO8z3wKNLl",
-        )
-        dalle = FalImageGenService(
-            params=FalImageGenService.InputParams(image_size="1024x1024"),
-            aiohttp_session=session,
-            key=os.getenv("FAL_KEY"),
-        )
-
-        bot1_messages = [
-            {
-                "role": "system",
-                "content": "You are a stern librarian. You strongly believe that a hot dog is a sandwich. Start by stating this fact in a few sentences, then be prepared to debate this with the user. You shouldn't ever compromise on the fundamental truth that a hot dog is a sandwich. Your responses should only be a few sentences long.",
-            },
-        ]
-        bot2_messages = [
-            {
-                "role": "system",
-                "content": "You are a silly cat, and you strongly believe that a hot dog is not a sandwich. Debate this with the user, only responding with a few sentences. Don't ever accept that a hot dog is a sandwich.",
-            },
-        ]
-
-        async def get_text_and_audio(messages) -> Tuple[str, bytearray]:
-            """This function streams text from the LLM and uses the TTS service to convert
-            that text to speech as it's received.
-            """
-            source_queue = asyncio.Queue()
-            sink_queue = asyncio.Queue()
-            sentence_aggregator = SentenceAggregator()
-            pipeline = Pipeline([llm, sentence_aggregator, tts1], source_queue, sink_queue)
-
-            await source_queue.put(LLMContextFrame(LLMContext(messages)))
-            await source_queue.put(EndFrame())
-            await pipeline.run_pipeline()
-
-            message = ""
-            all_audio = bytearray()
-            while sink_queue.qsize():
-                frame = sink_queue.get_nowait()
-                if isinstance(frame, TextFrame):
-                    message += frame.text
-                elif isinstance(frame, AudioFrame):
-                    all_audio.extend(frame.audio)
-
-            return (message, all_audio)
-
-        async def get_bot1_statement():
-            message, audio = await get_text_and_audio(bot1_messages)
-
-            bot1_messages.append({"role": "assistant", "content": message})
-            bot2_messages.append({"role": "user", "content": message})
-
-            return audio
-
-        async def get_bot2_statement():
-            message, audio = await get_text_and_audio(bot2_messages)
-
-            bot2_messages.append({"role": "assistant", "content": message})
-            bot1_messages.append({"role": "user", "content": message})
-
-            return audio
-
-        async def argue():
-            for i in range(100):
-                print(f"In iteration {i}")
-
-                bot1_description = "A woman conservatively dressed as a librarian in a library surrounded by books, cartoon, serious, highly detailed"
-
-                (audio1, image_data1) = await asyncio.gather(
-                    get_bot1_statement(), dalle.run_image_gen(bot1_description)
-                )
-                await transport.send_queue.put(
-                    [
-                        ImageFrame(image_data1[1], image_data1[2]),
-                        AudioFrame(audio1),
-                    ]
-                )
-
-                bot2_description = "A cat dressed in a hot dog costume, cartoon, bright colors, funny, highly detailed"
-
-                (audio2, image_data2) = await asyncio.gather(
-                    get_bot2_statement(), dalle.run_image_gen(bot2_description)
-                )
-                await transport.send_queue.put(
-                    [
-                        ImageFrame(image_data2[1], image_data2[2]),
-                        AudioFrame(audio2),
-                    ]
-                )
-
-        await asyncio.gather(transport.run(), argue())
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

examples/foundational/08-custom-frame-processor.py

@@ -4,8 +4,9 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
+import io
 import os
-from typing import Optional
+import re
 
 from dotenv import load_dotenv
 from loguru import logger
@@ -16,24 +17,17 @@ from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import (
     Frame,
-    LLMContextFrame,
-    TextFrame,
-    TTSSpeakFrame,
-    UserImageRawFrame,
-    UserImageRequestFrame,
+    LLMRunFrame,
+    MetricsFrame,
 )
 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.user_response import UserResponseAggregator
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
-from pipecat.runner.utils import (
-    create_transport,
-    get_transport_client_id,
-    maybe_capture_participant_camera,
-)
+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
@@ -43,46 +37,41 @@ from pipecat.transports.daily.transport import DailyParams
 load_dotenv(override=True)
 
 
-class UserImageRequester(FrameProcessor):
-    """Converts incoming text into requests for user images."""
+def format_metrics(metrics, indent=0):
+    lines = []
+    tab = "\t" * indent
 
-    def __init__(self, participant_id: Optional[str] = None):
-        super().__init__()
-        self._participant_id = participant_id
+    for metric in metrics:
+        lines.append(tab + type(metric).__name__)
+        for field, value in vars(metric).items():
+            if hasattr(value, "__dict__") and not isinstance(
+                value, (str, int, float, bool, type(None))
+            ):
+                lines.append(f"{tab}\t{field}={type(value).__name__}")
+                for k, v in vars(value).items():
+                    lines.append(f"{tab}\t\t{k}={repr(v)}")
+            else:
+                lines.append(f"{tab}\t{field}={repr(value)}")
 
-    def set_participant_id(self, participant_id: str):
-        self._participant_id = participant_id
+    return "\n".join(lines)
+
+
+class MetricsFrameLogger(FrameProcessor):
+    """MetricsFrameLogger formats and logs all MetericsFrames"""
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         await super().process_frame(frame, direction)
 
-        if self._participant_id and isinstance(frame, TextFrame):
-            await self.push_frame(
-                UserImageRequestFrame(self._participant_id, context=frame.text),
-                FrameDirection.UPSTREAM,
-            )
-        else:
+        if isinstance(frame, MetricsFrame):
+            logger.info(f"{frame.name}\n    {format_metrics(frame.data)}")
             await self.push_frame(frame, direction)
 
-
-class UserImageProcessor(FrameProcessor):
-    """Converts incoming user images into context frames."""
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        if isinstance(frame, UserImageRawFrame):
-            if frame.request and frame.request.context:
-                context = LLMContext()
-                context.add_image_frame_message(
-                    image=frame.image,
-                    text=frame.request.context,
-                    size=frame.size,
-                    format=frame.format,
-                )
-                frame = LLMContextFrame(context)
-                await self.push_frame(frame)
+        # ALWAYS push all frames
         else:
+            # SUPER IMPORTANT: always push every frame!
             await self.push_frame(frame, direction)
 
 
@@ -93,14 +82,13 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        video_in_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
         turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        video_in_enabled=True,
+        video_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
         turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
@@ -110,33 +98,37 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    user_response = UserResponseAggregator()
-
-    # Initialize the image requester without setting the participant ID yet
-    image_requester = UserImageRequester()
-
-    image_processor = UserImageProcessor()
-
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    # OpenAI GPT-4o for vision analysis
-    openai = 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
     )
 
+    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)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    metrics_frame_processor = MetricsFrameLogger()
+
     pipeline = Pipeline(
         [
             transport.input(),
             stt,
-            user_response,
-            image_requester,
-            image_processor,
-            openai,
+            context_aggregator.user(),
+            llm,
             tts,
             transport.output(),
+            context_aggregator.assistant(),
+            metrics_frame_processor,  # pretty print metrics frames
         ]
     )
 
@@ -152,15 +144,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected: {client}")
-
-        await maybe_capture_participant_camera(transport, client)
-
-        # Set the participant ID in the image requester
-        client_id = get_transport_client_id(transport, client)
-        image_requester.set_participant_id(client_id)
-
-        # Welcome message
-        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/11-sound-effects.py

@@ -121,7 +121,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/12-describe-image-openai.py

@@ -0,0 +1,141 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+from PIL import Image
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
+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
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    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. You are also able to describe images.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+
+        if not runner_args.body:
+            script_dir = os.path.dirname(__file__)
+            runner_args.body = {
+                "image_path": os.path.join(script_dir, "assets", "cat.jpg"),
+                "question": "Describe this image",
+            }
+
+        image_path = runner_args.body["image_path"]
+        question = runner_args.body["question"]
+
+        # Kick off the conversation.
+        image = Image.open(image_path)
+        message = await LLMContext.create_image_message(
+            image=image.tobytes(),
+            format="RGB",
+            size=image.size,
+            text=question,
+        )
+        messages.append(message)
+        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/12-describe-video.py

@@ -1,180 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import os
-from typing import Optional
-
-from dotenv import load_dotenv
-from loguru import logger
-
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import (
-    Frame,
-    LLMContextFrame,
-    TextFrame,
-    TTSSpeakFrame,
-    UserImageRawFrame,
-    UserImageRequestFrame,
-)
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.user_response import UserResponseAggregator
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.runner.types import RunnerArguments
-from pipecat.runner.utils import (
-    create_transport,
-    get_transport_client_id,
-    maybe_capture_participant_camera,
-)
-from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.deepgram.stt import DeepgramSTTService
-from pipecat.services.moondream.vision import MoondreamService
-from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.daily.transport import DailyParams
-
-load_dotenv(override=True)
-
-
-class UserImageRequester(FrameProcessor):
-    """Converts incoming text into requests for user images."""
-
-    def __init__(self, participant_id: Optional[str] = None):
-        super().__init__()
-        self._participant_id = participant_id
-
-    def set_participant_id(self, participant_id: str):
-        self._participant_id = participant_id
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        if self._participant_id and isinstance(frame, TextFrame):
-            await self.push_frame(
-                UserImageRequestFrame(self._participant_id, context=frame.text),
-                FrameDirection.UPSTREAM,
-            )
-        else:
-            await self.push_frame(frame, direction)
-
-
-class UserImageProcessor(FrameProcessor):
-    """Converts incoming user images into context frames."""
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        if isinstance(frame, UserImageRawFrame):
-            if frame.request and frame.request.context:
-                context = LLMContext()
-                context.add_image_frame_message(
-                    image=frame.image,
-                    text=frame.request.context,
-                    size=frame.size,
-                    format=frame.format,
-                )
-                frame = LLMContextFrame(context)
-                await self.push_frame(frame)
-        else:
-            await self.push_frame(frame, direction)
-
-
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
-transport_params = {
-    "daily": lambda: DailyParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        video_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-    ),
-    "webrtc": lambda: TransportParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        video_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-    ),
-}
-
-
-async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
-    logger.info(f"Starting bot")
-
-    user_response = UserResponseAggregator()
-
-    # Initialize the image requester without setting the participant ID yet
-    image_requester = UserImageRequester()
-
-    image_processor = UserImageProcessor()
-
-    # If you run into weird description, try with use_cpu=True
-    moondream = MoondreamService()
-
-    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",  # British Reading Lady
-    )
-
-    pipeline = Pipeline(
-        [
-            transport.input(),
-            stt,
-            user_response,
-            image_requester,
-            image_processor,
-            moondream,
-            tts,
-            transport.output(),
-        ]
-    )
-
-    task = PipelineTask(
-        pipeline,
-        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: {client}")
-
-        await maybe_capture_participant_camera(transport, client)
-
-        # Set the participant ID in the image requester
-        client_id = get_transport_client_id(transport, client)
-        image_requester.set_participant_id(client_id)
-
-        # Welcome message
-        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
-
-    @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/12a-describe-image-anthropic.py

@@ -0,0 +1,141 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+from PIL import Image
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.anthropic.llm import AnthropicLLMService
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_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. You are also able to describe images.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+
+        if not runner_args.body:
+            script_dir = os.path.dirname(__file__)
+            runner_args.body = {
+                "image_path": os.path.join(script_dir, "assets", "cat.jpg"),
+                "question": "Describe this image",
+            }
+
+        image_path = runner_args.body["image_path"]
+        question = runner_args.body["question"]
+
+        # Kick off the conversation.
+        image = Image.open(image_path)
+        message = await LLMContext.create_image_message(
+            image=image.tobytes(),
+            format="RGB",
+            size=image.size,
+            text=question,
+        )
+        messages.append(message)
+        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/12a-describe-video-gemini-flash.py

@@ -1,184 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import os
-from typing import Optional
-
-from dotenv import load_dotenv
-from loguru import logger
-
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import (
-    Frame,
-    LLMContextFrame,
-    TextFrame,
-    TTSSpeakFrame,
-    UserImageRawFrame,
-    UserImageRequestFrame,
-)
-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.user_response import UserResponseAggregator
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.runner.types import RunnerArguments
-from pipecat.runner.utils import (
-    create_transport,
-    get_transport_client_id,
-    maybe_capture_participant_camera,
-)
-from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.deepgram.stt import DeepgramSTTService
-from pipecat.services.google.llm import GoogleLLMService
-from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.daily.transport import DailyParams
-
-load_dotenv(override=True)
-
-
-class UserImageRequester(FrameProcessor):
-    """Converts incoming text into requests for user images."""
-
-    def __init__(self, participant_id: Optional[str] = None):
-        super().__init__()
-        self._participant_id = participant_id
-
-    def set_participant_id(self, participant_id: str):
-        self._participant_id = participant_id
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        if self._participant_id and isinstance(frame, TextFrame):
-            await self.push_frame(
-                UserImageRequestFrame(self._participant_id, context=frame.text),
-                FrameDirection.UPSTREAM,
-            )
-        else:
-            await self.push_frame(frame, direction)
-
-
-class UserImageProcessor(FrameProcessor):
-    """Converts incoming user images into context frames."""
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        if isinstance(frame, UserImageRawFrame):
-            if frame.request and frame.request.context:
-                context = LLMContext()
-                context.add_image_frame_message(
-                    image=frame.image,
-                    text=frame.request.context,
-                    size=frame.size,
-                    format=frame.format,
-                )
-                frame = LLMContextFrame(context)
-                await self.push_frame(frame)
-        else:
-            await self.push_frame(frame, direction)
-
-
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
-transport_params = {
-    "daily": lambda: DailyParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        video_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-    ),
-    "webrtc": lambda: TransportParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        video_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-    ),
-}
-
-
-async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
-    logger.info(f"Starting bot")
-
-    user_response = UserResponseAggregator()
-
-    # Initialize the image requester without setting the participant ID yet
-    image_requester = UserImageRequester()
-
-    image_processor = UserImageProcessor()
-
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
-
-    # Google Gemini model for vision analysis
-    google = GoogleLLMService(model="gemini-2.0-flash-001", api_key=os.getenv("GOOGLE_API_KEY"))
-
-    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-    )
-
-    pipeline = Pipeline(
-        [
-            transport.input(),
-            stt,
-            user_response,
-            image_requester,
-            image_processor,
-            google,
-            tts,
-            transport.output(),
-        ]
-    )
-
-    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: {client}")
-
-        await maybe_capture_participant_camera(transport, client)
-
-        # Set the participant ID in the image requester
-        client_id = get_transport_client_id(transport, client)
-        image_requester.set_participant_id(client_id)
-
-        # Welcome message
-        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
-
-    @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/12b-describe-image-aws.py

@@ -0,0 +1,148 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+from PIL import Image
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.aws.llm import AWSBedrockLLMService
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = AWSBedrockLLMService(
+        aws_region="us-west-2",
+        model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+        # Note: usually, prefer providing latency="optimized" param.
+        # Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
+        # which we need for image input.
+        params=AWSBedrockLLMService.InputParams(temperature=0.8),
+    )
+
+    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. You are also able to describe images.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+
+        if not runner_args.body:
+            script_dir = os.path.dirname(__file__)
+            runner_args.body = {
+                "image_path": os.path.join(script_dir, "assets", "cat.jpg"),
+                "question": "Describe this image",
+            }
+
+        image_path = runner_args.body["image_path"]
+        question = runner_args.body["question"]
+
+        # Kick off the conversation.
+        image = Image.open(image_path)
+        message = await LLMContext.create_image_message(
+            image=image.tobytes(),
+            format="RGB",
+            size=image.size,
+            text=question,
+        )
+        messages.append(message)
+        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/12c-describe-image-gemini-flash.py

@@ -0,0 +1,141 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+from PIL import Image
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.google.llm import GoogleLLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_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. You are also able to describe images.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+
+        if not runner_args.body:
+            script_dir = os.path.dirname(__file__)
+            runner_args.body = {
+                "image_path": os.path.join(script_dir, "assets", "cat.jpg"),
+                "question": "Describe this image",
+            }
+
+        image_path = runner_args.body["image_path"]
+        question = runner_args.body["question"]
+
+        # Kick off the conversation.
+        image = Image.open(image_path)
+        message = await LLMContext.create_image_message(
+            image=image.tobytes(),
+            format="RGB",
+            size=image.size,
+            text=question,
+        )
+        messages.append(message)
+        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/12c-describe-video-anthropic.py

@@ -1,184 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import os
-from typing import Optional
-
-from dotenv import load_dotenv
-from loguru import logger
-
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import (
-    Frame,
-    LLMContextFrame,
-    TextFrame,
-    TTSSpeakFrame,
-    UserImageRawFrame,
-    UserImageRequestFrame,
-)
-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.user_response import UserResponseAggregator
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.runner.types import RunnerArguments
-from pipecat.runner.utils import (
-    create_transport,
-    get_transport_client_id,
-    maybe_capture_participant_camera,
-)
-from pipecat.services.anthropic.llm import AnthropicLLMService
-from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.deepgram.stt import DeepgramSTTService
-from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.daily.transport import DailyParams
-
-load_dotenv(override=True)
-
-
-class UserImageRequester(FrameProcessor):
-    """Converts incoming text into requests for user images."""
-
-    def __init__(self, participant_id: Optional[str] = None):
-        super().__init__()
-        self._participant_id = participant_id
-
-    def set_participant_id(self, participant_id: str):
-        self._participant_id = participant_id
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        if self._participant_id and isinstance(frame, TextFrame):
-            await self.push_frame(
-                UserImageRequestFrame(self._participant_id, context=frame.text),
-                FrameDirection.UPSTREAM,
-            )
-        else:
-            await self.push_frame(frame, direction)
-
-
-class UserImageProcessor(FrameProcessor):
-    """Converts incoming user images into context frames."""
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        if isinstance(frame, UserImageRawFrame):
-            if frame.request and frame.request.context:
-                context = LLMContext()
-                context.add_image_frame_message(
-                    image=frame.image,
-                    text=frame.request.context,
-                    size=frame.size,
-                    format=frame.format,
-                )
-                frame = LLMContextFrame(context)
-                await self.push_frame(frame)
-        else:
-            await self.push_frame(frame, direction)
-
-
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
-# instantiated. The function will be called when the desired transport gets
-# selected.
-transport_params = {
-    "daily": lambda: DailyParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        video_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-    ),
-    "webrtc": lambda: TransportParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        video_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-    ),
-}
-
-
-async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
-    logger.info(f"Starting bot")
-
-    user_response = UserResponseAggregator()
-
-    # Initialize the image requester without setting the participant ID yet
-    image_requester = UserImageRequester()
-
-    image_processor = UserImageProcessor()
-
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
-
-    # Anthropic for vision analysis
-    anthropic = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY"))
-
-    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-    )
-
-    pipeline = Pipeline(
-        [
-            transport.input(),
-            stt,
-            user_response,
-            image_requester,
-            image_processor,
-            anthropic,
-            tts,
-            transport.output(),
-        ]
-    )
-
-    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: {client}")
-
-        await maybe_capture_participant_camera(transport, client)
-
-        # Set the participant ID in the image requester
-        client_id = get_transport_client_id(transport, client)
-        image_requester.set_participant_id(client_id)
-
-        # Welcome message
-        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
-
-    @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/12d-describe-image-moondream.py

@@ -9,55 +9,36 @@ import os
 
 from dotenv import load_dotenv
 from loguru import logger
+from PIL import Image
 
 from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import UserImageRawFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.ultravox.stt import UltravoxSTTService
+from pipecat.services.moondream.vision import MoondreamService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
-from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# NOTE: This example requires GPU resources to run efficiently.
-# The Ultravox model is compute-intensive and performs best with GPU acceleration.
-# This can be deployed on cloud GPU providers like Cerebrium.ai for optimal performance.
-
-
-# Want to initialize the ultravox processor since it takes time to load the model and dont
-# want to load it every time the pipeline is run
-ultravox_processor = UltravoxSTTService(
-    model_name="fixie-ai/ultravox-v0_5-llama-3_1-8b",
-    hf_token=os.getenv("HF_TOKEN"),
-)
-
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
 # instantiated. The function will be called when the desired transport gets
 # selected.
 transport_params = {
     "daily": lambda: DailyParams(
-        audio_in_enabled=True,
-        audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
-    ),
-    "twilio": lambda: FastAPIWebsocketParams(
-        audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
         turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
-        audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
         turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
@@ -69,14 +50,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
     tts = CartesiaTTSService(
-        api_key=os.environ.get("CARTESIA_API_KEY"),
-        voice_id="97f4b8fb-f2fe-444b-bb9a-c109783a857a",
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
+    vision = MoondreamService()
+
     pipeline = Pipeline(
         [
-            transport.input(),  # Transport user input
-            ultravox_processor,
+            vision,  # Vision
             tts,  # TTS
             transport.output(),  # Transport bot output
         ]
@@ -95,6 +77,29 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
 
+        if not runner_args.body:
+            script_dir = os.path.dirname(__file__)
+            runner_args.body = {
+                "image_path": os.path.join(script_dir, "assets", "cat.jpg"),
+                "question": "Describe this image",
+            }
+
+        image_path = runner_args.body["image_path"]
+        question = runner_args.body["question"]
+
+        # Describe the image.
+        image = Image.open(image_path)
+        await task.queue_frames(
+            [
+                UserImageRawFrame(
+                    image=image.tobytes(),
+                    format="RGB",
+                    size=image.size,
+                    text=question,
+                )
+            ]
+        )
+
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):
         logger.info(f"Client disconnected")

examples/foundational/13f-cartesia-transcription.py

@@ -48,10 +48,7 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = CartesiaSTTService(
-        api_key=os.getenv("CARTESIA_API_KEY"),
-        base_url=os.getenv("CARTESIA_BASE_URL"),
-    )
+    stt = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
 
     tl = TranscriptionLogger()
 

examples/foundational/14-function-calling.py

@@ -120,7 +120,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/14c-function-calling-together.py

@@ -106,7 +106,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/14d-function-calling-anthropic-video.py

@@ -4,8 +4,6 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-
-import asyncio
 import os
 
 from dotenv import load_dotenv
@@ -17,12 +15,13 @@ from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import LLMRunFrame
+from pipecat.frames.frames import LLMRunFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.frame_processor import FrameDirection
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import (
     create_transport,
@@ -39,34 +38,30 @@ from pipecat.transports.daily.transport import DailyParams
 load_dotenv(override=True)
 
 
-# Global variable to store the client ID
-client_id = ""
+async def fetch_user_image(params: FunctionCallParams):
+    """Fetch the user image and push it to the LLM.
 
-
-async def get_weather(params: FunctionCallParams):
-    location = params.arguments["location"]
-    await params.result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
-
-
-async def get_image(params: FunctionCallParams):
+    When called, this function pushes a UserImageRequestFrame upstream to the
+    transport. As a result, the transport will request the user image and push a
+    UserImageRawFrame downstream which will be added to the context by the LLM
+    assistant aggregator.
+    """
+    user_id = params.arguments["user_id"]
     question = params.arguments["question"]
-    logger.debug(f"Requesting image with user_id={client_id}, question={question}")
+    logger.debug(f"Requesting image with user_id={user_id}, question={question}")
 
-    # Request the image frame
-    await params.llm.request_image_frame(
-        user_id=client_id,
-        function_name=params.function_name,
-        tool_call_id=params.tool_call_id,
-        text_content=question,
+    # Request a user image frame and indicate that it should be added to the
+    # context.
+    await params.llm.push_frame(
+        UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
+        FrameDirection.UPSTREAM,
     )
 
-    # Wait a short time for the frame to be processed
-    await asyncio.sleep(0.5)
+    await params.result_callback(None)
 
-    # Return a result to complete the function call
-    await params.result_callback(
-        f"I've captured an image from your camera and I'm analyzing what you asked about: {question}"
-    )
+    # Instead of None, it's possible to also provide a tool call answer to
+    # tell the LLM that we are grabbing the image to analyze.
+    # await params.result_callback({"result": "Image is being captured."})
 
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
@@ -100,70 +95,32 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = AnthropicLLMService(
-        api_key=os.getenv("ANTHROPIC_API_KEY"),
-        model="claude-3-7-sonnet-latest",
-        params=AnthropicLLMService.InputParams(enable_prompt_caching=True),
-    )
-    llm.register_function("get_weather", get_weather)
-    llm.register_function("get_image", get_image)
+    # Anthropic for vision analysis
+    llm = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY"))
+    llm.register_function("fetch_user_image", fetch_user_image)
 
-    weather_function = FunctionSchema(
-        name="get_weather",
-        description="Get the current weather",
+    fetch_image_function = FunctionSchema(
+        name="fetch_user_image",
+        description="Called when the user requests a description of their camera feed",
         properties={
-            "location": {
+            "user_id": {
                 "type": "string",
-                "description": "The city and state, e.g. San Francisco, CA",
+                "description": "The ID of the user to grab the image from",
             },
-        },
-        required=["location"],
-    )
-    get_image_function = FunctionSchema(
-        name="get_image",
-        description="Get an image from the video stream.",
-        properties={
             "question": {
                 "type": "string",
-                "description": "The question that the user is asking about the image.",
-            }
+                "description": "The question that the user is asking about the image",
+            },
         },
-        required=["question"],
+        required=["user_id", "question"],
     )
-    tools = ToolsSchema(standard_tools=[weather_function, get_image_function])
-
-    system_prompt = """\
-You are a helpful assistant who converses with a user and answers questions. Respond concisely to general questions.
-
-Your response will be turned into speech so use only simple words and punctuation.
-
-You have access to two tools: get_weather and get_image.
-
-You can respond to questions about the weather using the get_weather tool.
-
-You can answer questions about the user's video stream using the get_image tool. Some examples of phrases that \
-indicate you should use the get_image tool are:
-- What do you see?
-- What's in the video?
-- Can you describe the video?
-- Tell me about what you see.
-- Tell me something interesting about what you see.
-- What's happening in the video?
-
-If you need to use a tool, simply use the tool. Do not tell the user the tool you are using. Be brief and concise.
-    """
+    tools = ToolsSchema(standard_tools=[fetch_image_function])
 
     messages = [
         {
             "role": "system",
-            "content": [
-                {
-                    "type": "text",
-                    "text": system_prompt,
-                }
-            ],
+            "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. You are able to describe images from the user camera.",
         },
-        {"role": "user", "content": "Start the conversation by introducing yourself."},
     ]
 
     context = LLMContext(messages, tools)
@@ -173,11 +130,11 @@ If you need to use a tool, simply use the tool. Do not tell the user the tool yo
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User speech to text
+            context_aggregator.user(),  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses and tool context
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
     )
 
@@ -196,10 +153,16 @@ If you need to use a tool, simply use the tool. Do not tell the user the tool yo
 
         await maybe_capture_participant_camera(transport, client)
 
-        global client_id
+        # Set the participant ID in the image requester
         client_id = get_transport_client_id(transport, client)
 
         # Kick off the conversation.
+        messages.append(
+            {
+                "role": "system",
+                "content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
+            }
+        )
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/14d-function-calling-aws-video.py

@@ -5,29 +5,23 @@
 #
 
 import os
-from typing import Optional
 
 from dotenv import load_dotenv
 from loguru import logger
 
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
 from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import (
-    Frame,
-    LLMContextFrame,
-    TextFrame,
-    TTSSpeakFrame,
-    UserImageRawFrame,
-    UserImageRequestFrame,
-)
+from pipecat.frames.frames import LLMRunFrame, UserImageRequestFrame
 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.user_response import UserResponseAggregator
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.frame_processor import FrameDirection
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import (
     create_transport,
@@ -37,54 +31,37 @@ from pipecat.runner.utils import (
 from pipecat.services.aws.llm import AWSBedrockLLMService
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.llm_service import FunctionCallParams
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 
 load_dotenv(override=True)
 
 
-class UserImageRequester(FrameProcessor):
-    """Converts incoming text into requests for user images."""
+async def fetch_user_image(params: FunctionCallParams):
+    """Fetch the user image and push it to the LLM.
 
-    def __init__(self, participant_id: Optional[str] = None):
-        super().__init__()
-        self._participant_id = participant_id
+    When called, this function pushes a UserImageRequestFrame upstream to the
+    transport. As a result, the transport will request the user image and push a
+    UserImageRawFrame downstream which will be added to the context by the LLM
+    assistant aggregator.
+    """
+    user_id = params.arguments["user_id"]
+    question = params.arguments["question"]
+    logger.debug(f"Requesting image with user_id={user_id}, question={question}")
 
-    def set_participant_id(self, participant_id: str):
-        self._participant_id = participant_id
+    # Request a user image frame and indicate that it should be added to the
+    # context.
+    await params.llm.push_frame(
+        UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
+        FrameDirection.UPSTREAM,
+    )
 
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
+    await params.result_callback(None)
 
-        if self._participant_id and isinstance(frame, TextFrame):
-            await self.push_frame(
-                UserImageRequestFrame(self._participant_id, context=frame.text),
-                FrameDirection.UPSTREAM,
-            )
-        else:
-            await self.push_frame(frame, direction)
-
-
-class UserImageProcessor(FrameProcessor):
-    """Converts incoming user images into context frames."""
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        if isinstance(frame, UserImageRawFrame):
-            if frame.request and frame.request.context:
-                # Note: AWS Bedrock does not yet support the universal LLMContext
-                context = LLMContext()
-                context.add_image_frame_message(
-                    image=frame.image,
-                    text=frame.request.context,
-                    size=frame.size,
-                    format=frame.format,
-                )
-                frame = LLMContextFrame(context)
-                await self.push_frame(frame)
-        else:
-            await self.push_frame(frame, direction)
+    # Instead of None, it's possible to also provide a tool call answer to
+    # tell the LLM that we are grabbing the image to analyze.
+    # await params.result_callback({"result": "Image is being captured."})
 
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
@@ -111,17 +88,15 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    user_response = UserResponseAggregator()
-
-    # Initialize the image requester without setting the participant ID yet
-    image_requester = UserImageRequester()
-
-    image_processor = UserImageProcessor()
-
     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",  # British Reading Lady
+    )
+
     # AWS for vision analysis
-    aws = AWSBedrockLLMService(
+    llm = AWSBedrockLLMService(
         aws_region="us-west-2",
         model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
         # Note: usually, prefer providing latency="optimized" param.
@@ -129,22 +104,44 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         # which we need for image input.
         params=AWSBedrockLLMService.InputParams(temperature=0.8),
     )
+    llm.register_function("fetch_user_image", fetch_user_image)
 
-    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    fetch_image_function = FunctionSchema(
+        name="fetch_user_image",
+        description="Called when the user requests a description of their camera feed",
+        properties={
+            "user_id": {
+                "type": "string",
+                "description": "The ID of the user to grab the image from",
+            },
+            "question": {
+                "type": "string",
+                "description": "The question that the user is asking about the image",
+            },
+        },
+        required=["user_id", "question"],
     )
+    tools = ToolsSchema(standard_tools=[fetch_image_function])
+
+    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. You are able to describe images from the user camera.",
+        },
+    ]
+
+    context = LLMContext(messages, tools)
+    context_aggregator = LLMContextAggregatorPair(context)
 
     pipeline = Pipeline(
         [
-            transport.input(),
-            stt,
-            user_response,
-            image_requester,
-            image_processor,
-            aws,
-            tts,
-            transport.output(),
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
     )
 
@@ -165,10 +162,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         # Set the participant ID in the image requester
         client_id = get_transport_client_id(transport, client)
-        image_requester.set_participant_id(client_id)
 
-        # Welcome message
-        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
+        # Kick off the conversation.
+        messages.append(
+            {
+                "role": "system",
+                "content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
+            }
+        )
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/14d-function-calling-gemini-flash-video.py

@@ -0,0 +1,187 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame, UserImageRequestFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.frame_processor import FrameDirection
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import (
+    create_transport,
+    get_transport_client_id,
+    maybe_capture_participant_camera,
+)
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.google.llm import GoogleLLMService
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+
+load_dotenv(override=True)
+
+
+async def fetch_user_image(params: FunctionCallParams):
+    """Fetch the user image and push it to the LLM.
+
+    When called, this function pushes a UserImageRequestFrame upstream to the
+    transport. As a result, the transport will request the user image and push a
+    UserImageRawFrame downstream which will be added to the context by the LLM
+    assistant aggregator.
+    """
+    user_id = params.arguments["user_id"]
+    question = params.arguments["question"]
+    logger.debug(f"Requesting image with user_id={user_id}, question={question}")
+
+    # Request a user image frame and indicate that it should be added to the
+    # context.
+    await params.llm.push_frame(
+        UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
+        FrameDirection.UPSTREAM,
+    )
+
+    await params.result_callback(None)
+
+    # Instead of None, it's possible to also provide a tool call answer to
+    # tell the LLM that we are grabbing the image to analyze.
+    # await params.result_callback({"result": "Image is being captured."})
+
+
+# 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,
+        video_in_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    # Google Gemini model for vision analysis
+    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
+    llm.register_function("fetch_user_image", fetch_user_image)
+
+    fetch_image_function = FunctionSchema(
+        name="fetch_user_image",
+        description="Called when the user requests a description of their camera feed",
+        properties={
+            "user_id": {
+                "type": "string",
+                "description": "The ID of the user to grab the image from",
+            },
+            "question": {
+                "type": "string",
+                "description": "The question that the user is asking about the image",
+            },
+        },
+        required=["user_id", "question"],
+    )
+    tools = ToolsSchema(standard_tools=[fetch_image_function])
+
+    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. You are able to describe images from the user camera.",
+        },
+    ]
+
+    context = LLMContext(messages, tools)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+
+        await maybe_capture_participant_camera(transport, client)
+
+        # Set the participant ID in the image requester
+        client_id = get_transport_client_id(transport, client)
+
+        # Kick off the conversation.
+        messages.append(
+            {
+                "role": "system",
+                "content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
+            }
+        )
+        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/14d-function-calling-moondream-video.py

@@ -0,0 +1,224 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import (
+    Frame,
+    LLMFullResponseEndFrame,
+    LLMFullResponseStartFrame,
+    LLMRunFrame,
+    TextFrame,
+    UserImageRequestFrame,
+)
+from pipecat.pipeline.parallel_pipeline import ParallelPipeline
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import (
+    create_transport,
+    get_transport_client_id,
+    maybe_capture_participant_camera,
+)
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.services.moondream.vision import MoondreamService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+
+load_dotenv(override=True)
+
+
+async def fetch_user_image(params: FunctionCallParams):
+    """Fetch the user image.
+
+    When called, this function pushes a UserImageRequestFrame upstream to the
+    transport. As a result, the transport will request the user image and push a
+    UserImageRawFrame downstream.
+    """
+    user_id = params.arguments["user_id"]
+    question = params.arguments["question"]
+    logger.debug(f"Requesting image with user_id={user_id}, question={question}")
+
+    # Request a user image frame. In this case, we don't want the requested
+    # image to be added to the context because we will process it with
+    # Moondream.
+    await params.llm.push_frame(
+        UserImageRequestFrame(user_id=user_id, text=question, append_to_context=False),
+        FrameDirection.UPSTREAM,
+    )
+
+    await params.result_callback(None)
+
+    # Instead of None, it's possible to also provide a tool call answer to
+    # tell the LLM that we are grabbing the image to analyze.
+    # await params.result_callback({"result": "Image is being captured."})
+
+
+class MoondreamTextFrameWrapper(FrameProcessor):
+    """Wraps Moondream-provided TextFrames with LLM response start/end frames.
+
+    This processor detects TextFrames and automatically wraps them with
+    LLMFullResponseStartFrame and LLMFullResponseEndFrame to provide proper
+    response boundaries for downstream processors.
+    """
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        # If we receive a TextFrame, wrap it with response start/end frames
+        if isinstance(frame, TextFrame):
+            await self.push_frame(LLMFullResponseStartFrame(), direction)
+            await self.push_frame(frame, direction)
+            await self.push_frame(LLMFullResponseEndFrame(), direction)
+        else:
+            # For all other frames, just pass them through
+            await self.push_frame(frame, direction)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm.register_function("fetch_user_image", fetch_user_image)
+
+    fetch_image_function = FunctionSchema(
+        name="fetch_user_image",
+        description="Called when the user requests a description of their camera feed",
+        properties={
+            "user_id": {
+                "type": "string",
+                "description": "The ID of the user to grab the image from",
+            },
+            "question": {
+                "type": "string",
+                "description": "The question that the user is asking about the image",
+            },
+        },
+        required=["user_id", "question"],
+    )
+    tools = ToolsSchema(standard_tools=[fetch_image_function])
+
+    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. You are able to describe images from the user camera.",
+        },
+    ]
+
+    context = LLMContext(messages, tools)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    # If you run into weird description, try with use_cpu=True
+    moondream = MoondreamService()
+
+    # Wrap TextFrames with LLM response start/end frames, which makes Moondream
+    # output be treated like LLM responses for the purpose of context
+    # aggregation. Without this, the assistant context aggregator would ignore
+    # Moondream output (if the TTS service is disabled).
+    moondream_text_wrapper = MoondreamTextFrameWrapper()
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            ParallelPipeline(
+                [llm],  # LLM
+                [moondream, moondream_text_wrapper],
+            ),
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        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: {client}")
+
+        await maybe_capture_participant_camera(transport, client)
+
+        # Set the participant ID in the image requester
+        client_id = get_transport_client_id(transport, client)
+
+        # Kick off the conversation.
+        messages.append(
+            {
+                "role": "system",
+                "content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
+            }
+        )
+        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/14d-function-calling-openai-video.py

@@ -0,0 +1,186 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame, UserImageRequestFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.frame_processor import FrameDirection
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import (
+    create_transport,
+    get_transport_client_id,
+    maybe_capture_participant_camera,
+)
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+
+load_dotenv(override=True)
+
+
+async def fetch_user_image(params: FunctionCallParams):
+    """Fetch the user image and push it to the LLM.
+
+    When called, this function pushes a UserImageRequestFrame upstream to the
+    transport. As a result, the transport will request the user image and push a
+    UserImageRawFrame downstream which will be added to the context by the LLM
+    assistant aggregator.
+    """
+    user_id = params.arguments["user_id"]
+    question = params.arguments["question"]
+    logger.debug(f"Requesting image with user_id={user_id}, question={question}")
+
+    # Request a user image frame and indicate that it should be added to the
+    # context.
+    await params.llm.push_frame(
+        UserImageRequestFrame(user_id=user_id, text=question, append_to_context=True),
+        FrameDirection.UPSTREAM,
+    )
+
+    await params.result_callback(None)
+
+    # Instead of None, it's possible to also provide a tool call answer to
+    # tell the LLM that we are grabbing the image to analyze.
+    # await params.result_callback({"result": "Image is being captured."})
+
+
+# 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,
+        video_in_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm.register_function("fetch_user_image", fetch_user_image)
+
+    fetch_image_function = FunctionSchema(
+        name="fetch_user_image",
+        description="Called when the user requests a description of their camera feed",
+        properties={
+            "user_id": {
+                "type": "string",
+                "description": "The ID of the user to grab the image from",
+            },
+            "question": {
+                "type": "string",
+                "description": "The question that the user is asking about the image",
+            },
+        },
+        required=["user_id", "question"],
+    )
+    tools = ToolsSchema(standard_tools=[fetch_image_function])
+
+    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. You are able to describe images from the user camera.",
+        },
+    ]
+
+    context = LLMContext(messages, tools)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+
+        await maybe_capture_participant_camera(transport, client)
+
+        client_id = get_transport_client_id(transport, client)
+
+        # Kick off the conversation.
+        messages.append(
+            {
+                "role": "system",
+                "content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
+            }
+        )
+        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/14f-function-calling-groq.py

@@ -104,7 +104,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/14g-function-calling-grok.py

@@ -99,7 +99,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/14h-function-calling-azure.py

@@ -107,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/14i-function-calling-fireworks.py

@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = FireworksLLMService(
         api_key=os.getenv("FIREWORKS_API_KEY"),
-        model="accounts/fireworks/models/llama-v3p1-405b-instruct",
+        model="accounts/fireworks/models/gpt-oss-20b",
     )
     # You can also register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.
@@ -110,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way. Start by saying hello.",
+            "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. Start by saying hello.",
         },
     ]
 

examples/foundational/14j-function-calling-nvidia.py

@@ -27,7 +27,7 @@ from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.llm_service import FunctionCallParams
-from pipecat.services.nim.llm import NimLLMService
+from pipecat.services.nvidia.llm import NvidiaLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -75,7 +75,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         # text_filters=[MarkdownTextFilter()],
     )
 
-    llm = NimLLMService(api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.3-70b-instruct")
+    llm = NvidiaLLMService(
+        api_key=os.getenv("NVIDIA_API_KEY"),
+        model="nvidia/llama-3.3-nemotron-super-49b-v1.5",
+        # Recommended when turning thinking off
+        params=NvidiaLLMService.InputParams(temperature=0.0),
+    )
     # You can also register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.
     llm.register_function("get_current_weather", fetch_weather_from_api)
@@ -102,9 +107,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
     tools = ToolsSchema(standard_tools=[weather_function])
     messages = [
+        # Disable thinking by sending this message first
+        # Check the model for the corresponding "no thinking" message
+        {"role": "system", "content": "/no_think"},
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/14m-function-calling-openrouter.py

@@ -107,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/14n-function-calling-perplexity.py

@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "user",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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, but try to be brief.",
         },
     ]
 

examples/foundational/14p-function-calling-gemini-vertex-ai.py

@@ -76,9 +76,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = GoogleVertexLLMService(
         credentials=os.getenv("GOOGLE_VERTEX_TEST_CREDENTIALS"),
-        params=GoogleVertexLLMService.InputParams(
-            project_id=os.getenv("GOOGLE_CLOUD_PROJECT_ID"),
-        ),
+        project_id=os.getenv("GOOGLE_CLOUD_PROJECT_ID"),
+        location=os.getenv("GOOGLE_CLOUD_LOCATION"),
     )
     # You can aslo register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.

examples/foundational/14q-function-calling-qwen.py

@@ -105,7 +105,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]
 

examples/foundational/14r-function-calling-aws.py

@@ -79,8 +79,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = AWSBedrockLLMService(
         aws_region="us-west-2",
-        model="us.anthropic.claude-3-5-haiku-20241022-v1:0",
-        params=AWSBedrockLLMService.InputParams(temperature=0.8, latency="optimized"),
+        model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
+        params=AWSBedrockLLMService.InputParams(temperature=0.8),
     )
 
     # You can also register a function_name of None to get all functions
@@ -120,7 +120,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     messages = [
         {
             "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            "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.",
         },
     ]