TimeoutBotTurnStartStrategy: new timeout bot turn start strategy

MinWordsUserTurnStartStrategy: single word interrupt if bot not speaking

.github/workflows/build.yaml

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

.github/workflows/format.yaml

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

.github/workflows/generate-changelog.yml

@@ -0,0 +1,174 @@
+name: Generate Changelog for Release
+
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: "Release version (e.g., 0.0.97)"
+        required: true
+        type: string
+      date:
+        description: "Release date (YYYY-MM-DD format, defaults to today)"
+        required: false
+        type: string
+        default: ""
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  generate-changelog:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Install dependencies
+        run: |
+          uv sync --group dev
+
+      - name: Set release date
+        id: set_date
+        run: |
+          if [ -z "${{ inputs.date }}" ]; then
+            RELEASE_DATE=$(date +%Y-%m-%d)
+            echo "Using today's date: $RELEASE_DATE"
+          else
+            RELEASE_DATE="${{ inputs.date }}"
+            echo "Using provided date: $RELEASE_DATE"
+          fi
+          echo "release_date=$RELEASE_DATE" >> $GITHUB_OUTPUT
+
+      - name: Validate inputs
+        run: |
+          # Validate version format (basic check)
+          if ! [[ "${{ inputs.version }}" =~ ^[0-9]+\.[0-9]+\.[0-9]+.*$ ]]; then
+            echo "Error: Version must be in format X.Y.Z (e.g., 0.0.97)"
+            exit 1
+          fi
+
+          # Validate date format if provided
+          if [ -n "${{ inputs.date }}" ]; then
+            if ! date -d "${{ inputs.date }}" >/dev/null 2>&1; then
+              # Try macOS date format
+              if ! date -j -f "%Y-%m-%d" "${{ inputs.date }}" >/dev/null 2>&1; then
+                echo "Error: Date must be in YYYY-MM-DD format (e.g., 2025-12-04)"
+                exit 1
+              fi
+            fi
+          fi
+
+      - name: Check for changelog fragments
+        id: check_fragments
+        run: |
+          FRAGMENT_COUNT=$(find changelog -name "*.md" ! -name "_template.md.j2" | wc -l | tr -d ' ')
+          echo "fragment_count=$FRAGMENT_COUNT" >> $GITHUB_OUTPUT
+
+          if [ "$FRAGMENT_COUNT" -eq "0" ]; then
+            echo "❌ Error: No changelog fragments found in changelog/"
+            echo ""
+            echo "Cannot create a release without changelog entries."
+            echo "Add changelog fragments to the changelog/ directory (e.g., 1234.added.md) and try again."
+            exit 1
+          fi
+
+          # Validate fragment types
+          VALID_TYPES="added changed deprecated removed fixed 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/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

@@ -79,7 +79,7 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel
 
 **Examples:**
 
-- [RivaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/riva/stt.py)
+- [NvidiaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/nvidia/stt.py)
 - [FalSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/fal/stt.py)
 
 #### Key requirements:

CONTRIBUTING.md

@@ -17,24 +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

@@ -3,7 +3,6 @@
 </div></h1>
 
 [![PyPI](https://img.shields.io/pypi/v/pipecat-ai)](https://pypi.org/project/pipecat-ai) ![Tests](https://github.com/pipecat-ai/pipecat/actions/workflows/tests.yaml/badge.svg) [![codecov](https://codecov.io/gh/pipecat-ai/pipecat/graph/badge.svg?token=LNVUIVO4Y9)](https://codecov.io/gh/pipecat-ai/pipecat) [![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.pipecat.ai) [![Discord](https://img.shields.io/discord/1239284677165056021)](https://discord.gg/pipecat) [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/pipecat-ai/pipecat)
-[![](https://getmanta.ai/api/badges?text=Manta%20Graph&link=manta)](https://getmanta.ai/pipecat)
 
 # 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
 
@@ -44,6 +43,10 @@ Looking to build structured conversations? Check out [Pipecat Flows](https://git
 
 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.
@@ -63,24 +66,24 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
     <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), [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), [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)
 
@@ -150,7 +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:

changelog/3045.added.md

@@ -0,0 +1,38 @@
+- Introducing user and bot turn start strategies. Turn start strategies indicate when user and bot turns begin. In conversational agents, these are often referred to as start/stop speaking or turn-taking plans or policies.
+
+  User turn start strategies indicate when the user starts speaking (e.g. using VAD events or when a user says one or more words).
+
+  Bot turn start strategies indicate when the bot should start speaking (e.g. using an end-of-turn detection model or by observing incoming transcriptions).
+
+  A list of strategies can be specified for both the user and the bot; strategies are evaluated in order until one evaluates to true.
+
+  Available user turn start strategies:
+    - VADUserTurnStartStrategy
+    - TranscriptionUserTurnStartStrategy
+    - MinWordsUserTurnStartStrategy
+
+  Available bot turn start strategies:
+    - TimeoutBotTurnStartStrategy
+    - TranscriptionBotTurnStartStrategy
+    - TurnAnalyzerBotTurnStartStrategy
+
+  The default strategies are:
+
+    - user: [VADUserTurnStartStrategy, TranscriptionUserTurnStartStrategy]
+    - bot: [TranscriptionBotTurnStartStrategy, TimeoutBotTurnStartStrategy]
+
+  Turn start strategies are configured when setting up a `PipelineTask`. For example:
+
+  ```python
+  task = PipelineTask(..., params=PipelineParams(
+      turn_start_strategies=TurnStartStrategies(
+          bot=[
+              TurnAnalyzerBotTurnStartStrategy(
+                  turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams())
+              )
+          ],
+      ),
+  ))
+  ```
+
+  In order to use the turn start strategies you should update to the new universal `LLMContext` and `LLMContextAggregatorPair`.

changelog/3045.deprecated.2.md

@@ -0,0 +1 @@
+- ⚠️ `TransportParams.turn_analyzer` is deprecated and might result in unexpected behavior, use `PipelineTask`'s new `turn_start_strategies` parameter instead.

changelog/3045.deprecated.3.md

@@ -0,0 +1 @@
+- `FrameProcessor.interruption_strategies` is deprecated, use `PipelineTask`'s new `turn_start_strategies` parameter instead.

changelog/3045.deprecated.4.md

@@ -0,0 +1 @@
+- `EmulateUserStartedSpeakingFrame` and `EmulateUserStoppedSpeakingFrame` frames are deprecated.

changelog/3045.deprecated.5.md

@@ -0,0 +1 @@
+- Deprecated the `emulated` field in the `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` frames.

changelog/3045.deprecated.6.md

@@ -0,0 +1 @@
+- The `LLMUserAggregatorParams` and `LLMAssistantAggregatorParams` classes in `pipecat.processors.aggregators.llm_response` are now deprecated. Use the new universal `LLMContext` and `LLMContextAggregatorPair` instead.

changelog/3045.deprecated.md

@@ -0,0 +1 @@
+- `pipecat.audio.interruptions.MinWordsInterruptionStrategy` is deprecated. Use `pipecat.turns.user.MinWordsUserTurnStartStrategy` with `PipelineTask`'s new `turn_start_strategies` parameter instead.

changelog/3205.added.md

@@ -0,0 +1 @@
+- Added `RNNoiseFilter` for real-time noise suppression using RNNoise neural network via pyrnnoise library.

changelog/3225.changed.md

@@ -0,0 +1,15 @@
+- Updated `SpeechmaticsSTTService` to use new Python Voice SDK with improved VAD,
+  Smart Turn capabilities, and brings dramatic improvements to latency without
+  any impact on accuracy. Use the `turn_detection_mode` parameter to control the
+  endpointing of speech, with `TurnDetectionMode.EXTERNAL` (default),
+  `TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`.
+  ```python
+    stt = SpeechmaticsSTTService(
+        api_key=os.getenv("SPEECHMATICS_API_KEY"),
+        params=SpeechmaticsSTTService.InputParams(
+            language=Language.EN,
+            turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
+            speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
+        ),
+    )
+  ```

changelog/3225.deprecated.md

@@ -0,0 +1,4 @@
+- For `SpeechmaticsSTTService`, the `end_of_utterance_mode` parameter is deprecated.
+  Use the new `turn_detection_mode` parameter instead, with `TurnDetectionMode.EXTERNAL`,
+  `TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`. The `enable_vad`
+  parameter is also deprecated and is inferred from the `turn_detection_mode`.

changelog/3233.fixed.md

@@ -0,0 +1,2 @@
+- Improved error handling in `ElevenLabsRealtimeSTTService`
+- Fixed an issue in `ElevenLabsRealtimeSTTService` causing an infinite loop that blocks the process if the websocket disconnects due to an error

changelog/3257.changed.2.md

@@ -0,0 +1 @@
+- `TranscriptionFrame` and `InterimTranscriptionFrame` produced by `DailyTransport` now include the transport source (i.e., the originating audio track).

changelog/3257.changed.md

@@ -0,0 +1 @@
+- `daily-python` updated to 0.23.0.

changelog/3263.deprecated.md

@@ -0,0 +1,15 @@
+- `OpenAILLMContext` and its associated things (context aggregators, etc.) are now deprecated in favor of the universal `LLMContext` and its associated things.
+
+  From the developer's point of view, switching to using `LLMContext` machinery will usually be a matter of going from this:
+
+  ```python
+  context = OpenAILLMContext(messages, tools)
+  context_aggregator = llm.create_context_aggregator(context)
+  ```
+
+  To this:
+
+  ```
+  context = LLMContext(messages, tools)
+  context_aggregator = LLMContextAggregatorPair(context)
+  ```

changelog/3267.added.md

@@ -0,0 +1,8 @@
+- Added `GrokRealtimeLLMService` for xAI's Grok Voice Agent API with real-time voice conversations:
+
+  - Support for real-time audio streaming with WebSocket connection
+  - Built-in server-side VAD (Voice Activity Detection)
+  - Multiple voice options: Ara, Rex, Sal, Eve, Leo
+  - Built-in tools support: web_search, x_search, file_search
+  - Custom function calling with standard Pipecat tools schema
+  - Configurable audio formats (PCM at 8kHz-48kHz)

changelog/XXX.added.md

@@ -0,0 +1 @@
+- Added an approximation of TTFB for Ultravox.

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

@@ -61,9 +61,6 @@ autodoc_mock_imports = [
     # OpenCV - sometimes has import issues during docs build
     "cv2",
     # Heavy ML packages excluded from ReadTheDocs
-    # ultravox dependencies
-    "vllm",
-    "vllm.engine.arg_utils",
     # local-smart-turn dependencies
     "coremltools",
     "coremltools.models",
@@ -119,7 +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=...
@@ -34,58 +44,54 @@ 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=...
 
-# LMNT
-LMNT_API_KEY=...
-LMNT_VOICE_ID=...
-
-# Perplexity
-PERPLEXITY_API_KEY=...
-
-# PlayHT
-PLAYHT_USER_ID=...
-PLAYHT_API_KEY=...
-
-# OpenAI
-OPENAI_API_KEY=...
-
-# OpenPipe
-OPENPIPE_API_KEY=...
-
-# Tavus
-TAVUS_API_KEY=...
-TAVUS_REPLICA_ID=...
-TAVUS_PERSONA_ID=...
-
-# Simli
-SIMLI_API_KEY=...
-SIMLI_FACE_ID=...
+# Inworld
+INWORLD_API_KEY=...
 
 # Krisp
 KRISP_MODEL_PATH=...
@@ -93,77 +99,103 @@ KRISP_MODEL_PATH=...
 # Krisp Viva
 KRISP_VIVA_MODEL_PATH=...
 
-# DeepSeek
-DEEPSEEK_API_KEY=...
+# LiveKit
+LIVEKIT_API_KEY=...
+LIVEKIT_API_SECRET=...
 
-# 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=...
-
-# Twilio
-TWILIO_ACCOUNT_SID=...
-TWILIO_AUTH_TOKEN=...
+# LMNT
+LMNT_API_KEY=...
+LMNT_VOICE_ID=...
 
 # MiniMax
 MINIMAX_API_KEY=...
 MINIMAX_GROUP_ID=...
 
-# 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=...
 
+# Neuphonic
+NEUPHONIC_API_KEY=...
+
 # NVIDIA
 NVIDIA_API_KEY=...
 
+# OpenAI
+OPENAI_API_KEY=...
+
+# OpenPipe
+OPENPIPE_API_KEY=...
+
+# 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=...
+
+# 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=...
+
+# Ultravox Realtime
+ULTRAVOX_API_KEY=...
+
 # WhatsApp
-WHATSAPP_TOKEN=
-WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=
-WHATSAPP_PHONE_NUMBER_ID=
-WHATSAPP_APP_SECRET=
+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

@@ -17,7 +17,6 @@ from fastapi.responses import RedirectResponse
 from loguru import logger
 from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
@@ -33,6 +32,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.smallwebrtc.connection import IceServer, SmallWebRTCConnection
 from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -61,7 +62,6 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
             audio_in_enabled=True,
             audio_out_enabled=True,
             vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         ),
     )
 
@@ -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.",
         },
     ]
 
@@ -101,6 +101,9 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
     )
 

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

@@ -12,7 +12,6 @@ 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
@@ -26,6 +25,8 @@ from pipecat.runner.daily import configure
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.daily.transport import DailyParams, DailyTransport
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -46,7 +47,6 @@ async def main():
                 audio_out_enabled=True,
                 transcription_enabled=True,
                 vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-                turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
             ),
         )
 
@@ -60,7 +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.",
             },
         ]
 
@@ -83,6 +83,9 @@ async def main():
             params=PipelineParams(
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                turn_start_strategies=TurnStartStrategies(
+                    bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                ),
             ),
         )
 

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

@@ -12,7 +12,6 @@ import sys
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
@@ -33,6 +32,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -51,7 +52,6 @@ async def main():
             audio_in_enabled=True,
             audio_out_enabled=True,
             vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         ),
     )
 
@@ -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.",
         },
     ]
@@ -94,6 +94,9 @@ async def main():
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
     )
 

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

@@ -9,7 +9,6 @@ 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
@@ -34,6 +33,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -66,19 +67,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -100,7 +98,7 @@ 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.",
         },
     ]
 
@@ -125,6 +123,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -10,7 +10,6 @@ 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
@@ -34,6 +33,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -84,7 +85,6 @@ transport_params = {
         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,
@@ -93,7 +93,6 @@ transport_params = {
         video_out_width=1024,
         video_out_height=1024,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -113,7 +112,7 @@ 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.",
         },
     ]
 
@@ -143,6 +142,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -9,7 +9,6 @@ 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
@@ -21,12 +20,14 @@ 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
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -39,19 +40,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -59,7 +57,7 @@ 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 +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.",
         },
     ]
 
@@ -95,6 +93,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

examples/foundational/07-interruptible.py

@@ -9,7 +9,6 @@ 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
@@ -27,6 +26,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -38,19 +39,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -70,7 +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.",
         },
     ]
 
@@ -94,6 +92,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -6,6 +6,7 @@
 
 import os
 
+import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
@@ -14,16 +15,13 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response import (
-    LLMUserAggregatorParams,
-)
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.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 +49,122 @@ 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`, `megan` and `jack`
+
+    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,
+                turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
+                # focus_speakers=["S1"],
+                speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
+                speaker_passive_format="<PASSIVE><{speaker_id}>{text}</{speaker_id}></PASSIVE>",
             ),
-        },
-    ]
+        )
 
-    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)
 
-    @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

@@ -6,10 +6,10 @@
 
 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
@@ -18,20 +18,19 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response import (
-    LLMUserAggregatorParams,
-)
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.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
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -43,118 +42,119 @@ transport_params = {
         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):
-    """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`, `megan` and `jack`
+
+    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,
+                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)
 
-    @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,
+                turn_start_strategies=TurnStartStrategies(
+                    bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                ),
+            ),
+            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

@@ -10,7 +10,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.soniox.stt import SonioxSTTService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -36,19 +37,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -70,7 +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.",
         },
     ]
 
@@ -93,6 +91,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -4,76 +4,69 @@
 # 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.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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 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")
+    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 +74,25 @@ 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(),
             ]
         )
 
@@ -105,20 +101,31 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             params=PipelineParams(
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                turn_start_strategies=TurnStartStrategies(
+                    bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                ),
             ),
+            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 +1,142 @@
+#
+# 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.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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
+
+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)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+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,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
+        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

@@ -11,7 +11,6 @@ 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
@@ -29,6 +28,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -41,19 +42,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -76,7 +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.",
             },
         ]
 
@@ -100,6 +98,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             params=PipelineParams(
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                turn_start_strategies=TurnStartStrategies(
+                    bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                ),
             ),
             idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )

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

@@ -10,7 +10,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,19 +41,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -72,7 +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.",
         },
     ]
 
@@ -96,6 +94,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -13,10 +13,7 @@ from dotenv import load_dotenv
 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
 from pipecat.pipeline.runner import PipelineRunner
@@ -32,6 +29,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -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 +55,30 @@ 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),
+            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),
+            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),
+            audio_in_filter=aic,
+        )
+    )(_create_aic_filter()),
 }
 
 
@@ -95,7 +97,7 @@ 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.",
         },
     ]
 
@@ -120,6 +122,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -9,28 +9,34 @@ 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.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.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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 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.
@@ -39,19 +45,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -72,7 +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.",
         },
     ]
 
@@ -88,7 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             stt,
             context_aggregator.user(),  # User responses
             llm,  # LLM
-            tts,  # TTS
+            tts,  # TTS (HumeTTSService with word timestamps)
             transport.output(),  # Transport bot output
             context_aggregator.assistant(),  # Assistant spoken responses
         ]
@@ -100,9 +103,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
             audio_out_sample_rate=HUME_SAMPLE_RATE,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
-        observers=[RTVIObserver(rtvi)],
+        observers=[
+            RTVIObserver(rtvi),
+            DebugLogObserver(
+                frame_types={
+                    TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
+                }
+            ),
+        ],
     )
 
     @rtvi.event_handler("on_client_ready")
@@ -112,6 +125,9 @@ 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")
+        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()])

examples/foundational/07af-interruptible-gradium.py

@@ -0,0 +1,128 @@
+#
+# 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.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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
+
+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)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+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,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
+        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/07b-interruptible-langchain.py

@@ -15,7 +15,6 @@ from langchain_core.runnables.history import RunnableWithMessageHistory
 from langchain_openai import ChatOpenAI
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
@@ -33,6 +32,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -54,19 +55,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -121,6 +119,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -17,6 +17,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_response_universal import (
     LLMContext,
     LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -52,7 +53,10 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = DeepgramFluxSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = DeepgramFluxSTTService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        params=DeepgramFluxSTTService.InputParams(min_confidence=0.3),
+    )
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
 
@@ -61,12 +65,14 @@ 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.",
         },
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context_aggregator = LLMContextAggregatorPair(
+        context, user_params=LLMUserAggregatorParams(enable_user_speaking_frames=False)
+    )
 
     pipeline = Pipeline(
         [
@@ -101,6 +107,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         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)

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

@@ -0,0 +1,133 @@
+#
+# 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.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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
+
+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)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+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,
+                turn_start_strategies=TurnStartStrategies(
+                    bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                ),
+            ),
+            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 +1,138 @@
+#
+# 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.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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
+
+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)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+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,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
+        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

@@ -10,7 +10,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,19 +41,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -69,7 +67,7 @@ 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.",
         },
     ]
 
@@ -93,6 +91,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -11,7 +11,6 @@ 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
@@ -29,6 +28,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -41,19 +42,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -79,7 +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.",
             },
         ]
 
@@ -103,6 +101,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             params=PipelineParams(
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                turn_start_strategies=TurnStartStrategies(
+                    bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                ),
             ),
             idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )

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

@@ -10,7 +10,6 @@ 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
@@ -22,12 +21,14 @@ 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
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,19 +41,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -60,7 +58,7 @@ 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 +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.",
         },
     ]
 
@@ -96,6 +94,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -10,7 +10,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.playht.tts import PlayHTHttpTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -39,19 +40,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -72,7 +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.",
         },
     ]
 
@@ -96,6 +94,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -10,7 +10,6 @@ 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
@@ -29,6 +28,8 @@ from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,19 +41,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -74,7 +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.",
         },
     ]
 
@@ -98,6 +96,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -0,0 +1,136 @@
+#
+# 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.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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
+
+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)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+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,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
+        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

@@ -10,7 +10,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.azure.tts import AzureTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -39,19 +40,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -78,7 +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.",
         },
     ]
 
@@ -102,6 +100,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -10,7 +10,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.openai.tts import OpenAITTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -39,19 +40,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -72,7 +70,7 @@ 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.",
         },
     ]
 
@@ -97,6 +95,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             audio_out_sample_rate=24000,
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -11,7 +11,6 @@ import time
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
@@ -29,6 +28,8 @@ from pipecat.services.openpipe.llm import OpenPipeLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,19 +41,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -77,7 +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.",
         },
     ]
 
@@ -101,6 +99,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -11,7 +11,6 @@ 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
@@ -29,6 +28,8 @@ from pipecat.services.xtts.tts import XTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,19 +41,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -75,7 +73,7 @@ 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.",
             },
         ]
 
@@ -99,6 +97,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             params=PipelineParams(
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                turn_start_strategies=TurnStartStrategies(
+                    bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                ),
             ),
             idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )

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

@@ -10,7 +10,6 @@ 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
@@ -30,6 +29,8 @@ from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -41,19 +42,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -81,7 +79,7 @@ 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.",
         },
     ]
 
@@ -105,6 +103,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -28,6 +28,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -39,19 +41,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -68,7 +67,7 @@ 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.",
         },
     ]
 
@@ -92,6 +91,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -10,7 +10,6 @@ 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
@@ -19,7 +18,6 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response import LLMUserAggregatorParams
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -29,6 +27,8 @@ from pipecat.services.groq.tts import GroqTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,19 +40,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -71,14 +68,12 @@ 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.",
         },
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
-        context, user_params=LLMUserAggregatorParams(aggregation_timeout=0.05)
-    )
+    context_aggregator = LLMContextAggregatorPair(context)
 
     pipeline = Pipeline(
         [
@@ -97,6 +92,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -8,7 +8,6 @@
 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
@@ -26,6 +25,8 @@ from pipecat.services.aws.tts import AWSPollyTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -37,19 +38,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -67,14 +65,14 @@ 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.",
         },
     ]
 
@@ -98,6 +96,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -25,7 +25,6 @@ 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
@@ -44,6 +43,8 @@ from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -58,7 +59,6 @@ transport_params = {
         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,
@@ -67,7 +67,6 @@ transport_params = {
         video_out_width=1024,
         video_out_height=1024,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -89,12 +88,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         model="gemini-2.5-flash-image",
+        # model="gemini-3-pro-image-preview", # A more powerful model, but slower
     )
 
     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.",
         },
     ]
 
@@ -118,6 +118,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -4,31 +4,12 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""
-A conversational AI bot using Gemini for both LLM and TTS.
-
-This example demonstrates how to use Gemini's TTS capabilities with the new
-GeminiTTSService, which uses Gemini's TTS-specific models instead of Google Cloud TTS.
-
-Features showcased:
-- Gemini LLM for conversation
-- Gemini TTS with natural voice control
-- Support for different voice personalities
-- Style and tone control through natural language prompts
-
-Run with:
-    python examples/foundational/gemini-tts.py
-
-Make sure to set your environment variables:
-    export GOOGLE_API_KEY=your_api_key_here
-"""
 
 import os
 
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
@@ -47,6 +28,8 @@ from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -58,19 +41,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -84,10 +64,13 @@ 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 +84,22 @@ 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.""",
         },
     ]
 
@@ -133,6 +123,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
@@ -140,11 +133,11 @@ 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 +1,142 @@
+#
+# 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.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
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
+
+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)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+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,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
+        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

@@ -10,7 +10,6 @@ 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
@@ -29,6 +28,8 @@ from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,19 +41,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -61,8 +59,9 @@ 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 +73,16 @@ 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.",
         },
     ]
 
@@ -105,6 +106,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -10,7 +10,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,19 +41,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -74,7 +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.",
         },
     ]
 
@@ -98,6 +96,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -11,7 +11,6 @@ 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
@@ -29,6 +28,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,21 +41,18 @@ transport_params = {
         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(),
     ),
 }
@@ -72,7 +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.",
         },
     ]
 
@@ -96,6 +94,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -11,7 +11,6 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.filters.krisp_filter import KrispFilter
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
@@ -29,6 +28,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,21 +41,18 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         audio_in_filter=KrispFilter(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         audio_in_filter=KrispFilter(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         audio_in_filter=KrispFilter(),
     ),
 }
@@ -72,7 +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.",
         },
     ]
 
@@ -96,6 +94,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -11,7 +11,6 @@ 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
@@ -29,6 +28,8 @@ from pipecat.services.rime.tts import RimeHttpTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -41,19 +42,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -77,7 +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.",
             },
         ]
 
@@ -101,6 +99,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             params=PipelineParams(
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                turn_start_strategies=TurnStartStrategies(
+                    bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                ),
             ),
             idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )

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

@@ -10,7 +10,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.rime.tts import RimeTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -39,19 +40,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -71,7 +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.",
         },
     ]
 
@@ -95,6 +93,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -10,7 +10,6 @@ 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
@@ -22,12 +21,14 @@ 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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -39,19 +40,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -59,16 +57,18 @@ 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.",
         },
     ]
 
@@ -92,6 +92,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -12,7 +12,6 @@ from dotenv import load_dotenv
 from google.genai.types import Content, Part
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
@@ -42,6 +41,8 @@ from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -53,7 +54,7 @@ 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.
 
@@ -201,19 +202,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -224,8 +222,10 @@ 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(
@@ -270,6 +270,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -10,7 +10,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,19 +41,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -72,7 +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.",
         },
     ]
 
@@ -96,6 +94,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -11,7 +11,6 @@ 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
@@ -29,6 +28,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -41,19 +42,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -76,7 +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.",
             },
         ]
 
@@ -100,6 +98,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             params=PipelineParams(
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                turn_start_strategies=TurnStartStrategies(
+                    bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                ),
             ),
             idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )

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

@@ -10,7 +10,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -39,19 +40,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -71,7 +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.",
         },
     ]
 
@@ -95,6 +93,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -10,7 +10,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,19 +41,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -74,7 +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.",
         },
     ]
 
@@ -98,6 +96,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

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

@@ -11,7 +11,6 @@ import sys
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
@@ -21,12 +20,12 @@ 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.local.audio import LocalAudioTransport, LocalAudioTransportParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -40,7 +39,6 @@ async def main():
             audio_in_enabled=True,
             audio_out_enabled=True,
             vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-            turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
         )
     )
 
@@ -56,7 +54,7 @@ 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.",
         },
     ]
 
@@ -80,6 +78,9 @@ async def main():
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
     )
 

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

@@ -11,7 +11,6 @@ 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
@@ -30,6 +29,8 @@ from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -42,19 +43,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -78,7 +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.",
             },
         ]
 
@@ -102,6 +100,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             params=PipelineParams(
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                turn_start_strategies=TurnStartStrategies(
+                    bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                ),
             ),
             idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )

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

@@ -11,10 +11,10 @@ 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
@@ -22,13 +22,15 @@ 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
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -41,19 +43,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -63,7 +62,10 @@ 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 +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.",
             },
         ]
 
@@ -100,6 +102,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             params=PipelineParams(
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                turn_start_strategies=TurnStartStrategies(
+                    bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                ),
             ),
             idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
         )
@@ -109,7 +114,7 @@ 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

@@ -4,19 +4,15 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-
-import asyncio
 import os
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
-from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import LLMRunFrame, TTSUpdateSettingsFrame
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -24,12 +20,14 @@ 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
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -42,19 +40,16 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -62,7 +57,10 @@ 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 +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.",
         },
     ]
 
@@ -98,6 +96,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
     )
 

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

@@ -5,84 +5,72 @@
 #
 
 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,
+    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
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 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)
 
 
@@ -93,16 +81,13 @@ 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 +95,37 @@ 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
         ]
     )
 
@@ -145,6 +134,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
@@ -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/10-wake-phrase.py

@@ -9,7 +9,6 @@ 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
@@ -28,6 +27,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -39,19 +40,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -98,6 +96,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )

examples/foundational/11-sound-effects.py

@@ -10,7 +10,6 @@ import wave
 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
@@ -23,7 +22,7 @@ from pipecat.frames.frames import (
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineTask
+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, FrameProcessor
@@ -36,6 +35,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 load_dotenv(override=True)
 
@@ -89,19 +90,16 @@ transport_params = {
         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()),
     ),
 }
 
@@ -121,7 +119,7 @@ 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.",
         },
     ]
 
@@ -150,6 +148,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     task = PipelineTask(
         pipeline,
+        params=PipelineParams(
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 

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

@@ -0,0 +1,143 @@
+#
+# 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.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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
+
+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)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+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,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
+        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 +1,143 @@
+#
+# 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.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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
+
+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)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+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,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
+        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 +1,150 @@
+#
+# 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.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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
+
+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)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+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,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
+        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 +1,143 @@
+#
+# 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.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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
+
+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)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+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,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
+        ),
+        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

@@ -9,58 +9,38 @@ 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
+from pipecat.turns.bot.turn_analyzer_bot_turn_start_strategy import TurnAnalyzerBotTurnStartStrategy
+from pipecat.turns.turn_start_strategies import TurnStartStrategies
 
 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 +49,15 @@ 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
         ]
@@ -87,6 +68,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         params=PipelineParams(
             enable_metrics=True,
             enable_usage_metrics=True,
+            turn_start_strategies=TurnStartStrategies(
+                bot=[TurnAnalyzerBotTurnStartStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+            ),
         ),
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
@@ -95,6 +79,29 @@ 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/12d-describe-video-aws.py

@@ -1,192 +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.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)
-
-
-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:
-                # 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)
-
-
-# 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"))
-
-    # AWS for vision analysis
-    aws = 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),
-    )
-
-    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,
-            aws,
-            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()