Add example for getting just recording links

base output transport cleanup

.github/workflows/publish.yaml

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

.github/workflows/publish_test.yaml

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

CHANGELOG.md

@@ -5,6 +5,243 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Added
+
+- Added support for `bulbul:v3` model in `SarvamTTSService` and `SarvamHttpTTSService`.
+
+- Added `keyterms_prompt` parameter to `AssemblyAIConnectionParams`.
+
+- Added `speech_model` parameter to `AssemblyAIConnectionParams` to access the multilingual model.
+- 
+- Added support for trickle ICE to the `SmallWebRTCTransport`.
+
+- Added support for updating `OpenAITTSService` settings (`instructions` and
+  `speed`) at runtime via `TTSUpdateSettingsFrame`.
+
+- Added `--whatsapp` flag to runner to better surface WhatsApp transport logs.
+
+- Added `on_connected` and `on_disconnected` events to TTS and STT
+  websocket-based services.
+
+- Added an `aggregate_sentences` arg in `ElevenLabsHttpTTSService`, where the
+  default value is True.
+
+- Added a `room_properties` arg to the Daily runner's `configure()` method,
+  allowing `DailyRoomProperties` to be provided.
+
+- The runner `--folder` argument now supports downloading files from
+  subdirectories.
+
+### Changed
+
+- `CartesiaSTTService` now inherits from `WebsocketSTTService`.
+
+- Package upgrades:
+
+  - `openai` upgraded to support up to 2.x.x.
+  - `openpipe` upgraded to support up to 5.x.x.
+
+- `SpeechmaticsSTTService` updated dependencies for `speechmatics-rt>=0.5.0`.
+
+### Fixed
+
+- Fixed an issue in `RivaSegmentedSTTService` where a runtime error occurred due
+  to a mismatch in the _handle_transcription method's signature.
+
+- Fixed multiple pipeline task cancellation issues. `asyncio.CancelledError` is
+  now handled properly in `PipelineTask` making it possible to cancel an asyncio
+  task that it's executing a `PipelineRunner` cleanly. Also,
+  `PipelineTask.cancel()` does not block anymore waiting for the `CancelFrame`
+  to reach the end of the pipeline (going back to the behavior in < 0.0.83).
+
+- Fixed an issue in `ElevenLabsTTSService` and `ElevenLabsHttpTTSService` where
+  the Flash models would split words, resulting in a space being inserted
+  between words.
+
+- Fixed an issue where audio filters' `stop()` would not be called when using
+  `CancelFrame`.
+
+- Fixed an issue in `ElevenLabsHttpTTSService`, where
+  `apply_text_normalization` was incorrectly set as a query parameter. It's now
+  being added as a request parameter.
+
+- Fixed an issue where `RimeHttpTTSService` and `PiperTTSService` could generate
+  incorrectly 16-bit aligned audio frames, potentially leading to internal
+  errors or static audio.
+
+- Fixed an issue in `SpeechmaticsSTTService` where `AdditionalVocabEntry` items
+  needed to have `sounds_like` for the session to start.
+
+### Other
+
+- Added foundational example `47-sentry-metrics.py`, demonstrating how to use the
+  `SentryMetrics` processor.
+
+- Added foundational example `14x-function-calling-openpipe.py`.
+
+## [0.0.90] - 2025-10-10
+
+### Added
+
+- Added audio filter `KrispVivaFilter` using the Krisp VIVA SDK.
+
+- Added `--folder` argument to the runner, allowing files saved in that folder
+  to be downloaded from `http://HOST:PORT/file/FILE`.
+
+- Added `GeminiLiveVertexLLMService`, for accessing Gemini Live via Google
+  Vertex AI.
+
+- Added some new configuration options to `GeminiLiveLLMService`:
+
+  - `thinking`
+  - `enable_affective_dialog`
+  - `proactivity`
+
+  Note that these new configuration options require using a newer model than
+  the default, like "gemini-2.5-flash-native-audio-preview-09-2025". The last
+  two require specifying `http_options=HttpOptions(api_version="v1alpha")`.
+
+- Added `on_pipeline_error` event to `PipelineTask`. This event will get fired
+  when an `ErrorFrame` is pushed (use `FrameProcessor.push_error()`).
+
+  ```python
+  @task.event_handler("on_pipeline_error")
+  async def on_pipeline_error(task: PipelineTask, frame: ErrorFrame):
+      ...
+  ```
+
+- Added a `service_tier` `InputParam` to the `BaseOpenAILLMService`. This
+  parameter can influence the latency of the response. For example `"priority"`
+  will result in faster completions, but in exchange for a higher price.
+
+### Changed
+
+- Updated `GeminiLiveLLMService` to use the `google-genai` library rather than
+  use WebSockets directly.
+
+### Deprecated
+
+- `LivekitFrameSerializer` is now deprecated. Use `LiveKitTransport` instead.
+
+- `pipecat.service.openai_realtime` is now deprecated, use
+  `pipecat.services.openai.realtime` instead or
+  `pipecat.services.azure.realtime` for Azure Realtime.
+
+- `pipecat.service.aws_nova_sonic` is now deprecated, use
+  `pipecat.services.aws.nova_sonic` instead.
+
+- `GeminiMultimodalLiveLLMService` is now deprecated, use
+  `GeminiLiveLLMService`.
+
+### Fixed
+
+- Fixed a `GoogleVertexLLMService` issue that would generate an error if no
+  token information was returned.
+
+- `GeminiLiveLLMService` will now end gracefully (i.e. after the bot has
+  finished) upon receiving an `EndFrame`.
+
+- `GeminiLiveLLMService` will try to seamlessly reconnect when it loses its
+  connection.
+
+## [0.0.89] - 2025-10-07
+
+### Fixed
+
+- Reverted a change introduced in 0.0.88 that was causing pipelines to be frozen
+  when using interruption strategies and processors that block interruption
+  frames (e.g. `STTMuteFilter`).
+
+## [0.0.88] - 2025-10-07
+
+### Added
+
+- Added support for Nano Banana models to `GoogleLLMService`. For example, you
+  can now use the `gemini-2.5-flash-image` model to generate images.
+
+- Added `HumeTTSService` for text-to-speech synthesis using Hume AI's expressive
+  voice models. Provides high-quality, emotionally expressive speech synthesis
+  with support for various voice models. Includes example in
+  `examples/foundational/07ad-interruptible-hume.py`. Use with:
+  `uv pip install pipecat-ai[hume]`.
+
+### Changed
+
+- Updated default `GoogleLLMService` model to `gemini-2.5-flash`.
+
+### Deprecated
+
+- PlayHT is shutting down their API on December 31st, 2025. As a result,
+  `PlayHTTTSService` and `PlayHTHttpTTSService` are deprecated and will be
+  removed in a future version.
+
+### Fixed
+
+- Fixed an issue with `AWSNovaSonicLLMService` where the client wouldn't
+  connect due to a breaking change in the AWS dependency chain.
+
+- `PermissionError` is now caught if NLTK's `punkt_tab` can't be downloaded.
+
+- Fixed an issue that would cause wrong user/assistant context ordering when
+  using interruption strategies.
+
+- Fixed RTVI incoming message handling, broken in 0.0.87.
+
+## [0.0.87] - 2025-10-02
+
+### Added
+
+- Added `WebsocketSTTService` base class for websocket-based STT services.
+  Combines STT functionality with websocket connectivity, providing automatic
+  error handling and reconnection capabilities with exponential backoff.
+
+- Added `DeepgramFluxSTTService` for real-time speech recognition using
+  Deepgram's Flux WebSocket API. Flux understands conversational flow and
+  automatically handles turn-taking.
+
+- Added RTVI messages for user/bot audio levels and system logs.
+
+- Include OpenAI-based LLM services cached tokens to `MetricsFrame`.
+
+### Changed
+
+- Updated the default model for `AnthropicLLMService` to
+  `claude-sonnet-4-5-20250929`.
+
+### Deprecated
+
+- `DailyTransportMessageFrame` and `DailyTransportMessageUrgentFrame` are
+  deprecated, use `DailyOutputTransportMessageFrame` and
+  `DailyOutputTransportMessageUrgentFrame` respectively instead.
+
+- `LiveKitTransportMessageFrame` and `LiveKitTransportMessageUrgentFrame` are
+  deprecated, use `LiveKitOutputTransportMessageFrame` and
+  `LiveKitOutputTransportMessageUrgentFrame` respectively instead.
+
+- `TransportMessageFrame` and `TransportMessageUrgentFrame` are deprecated, use
+  `OutputTransportMessageFrame` and `OutputTransportMessageUrgentFrame`
+  respectively instead.
+
+- `InputTransportMessageUrgentFrame` is deprecated, use
+  `InputTransportMessageFrame` instead.
+
+- `DailyUpdateRemoteParticipantsFrame` is deprecated and will be removed in a
+  future version. Instead, create your own custom frame and handle it in the
+  `@transport.output().event_handler("on_after_push_frame")` event handler or a
+  custom processor.
+
+## Fixed
+
+- Fixed an issue in `AWSBedrockLLMService` where timeout exceptions weren't
+  being detected.
+
+- Fixed a `PipelineTask` issue that could prevent the application to exit if
+  `task.cancel()` was called when the task was already finished.
+
+- Fixed an issue where local SmartTurn was not being ran in a separate thread.
+
 ## [0.0.86] - 2025-09-24
 
 ### Added
@@ -1326,7 +1563,7 @@ quality and critical bugs impacting `ParallelPipelines` functionality.**
 - Added `session_token` parameter to `AWSNovaSonicLLMService`.
 
 - Added Gemini Multimodal Live File API for uploading, fetching, listing, and
-  deleting files. See `26f-gemini-multimodal-live-files-api.py` for example usage.
+  deleting files. See `26f-gemini-live-files-api.py` for example usage.
 
 ### Changed
 
@@ -3332,7 +3569,7 @@ stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
 - Added the new modalities option and helper function to set Gemini output
   modalities.
 
-- Added `examples/foundational/26d-gemini-multimodal-live-text.py` which is
+- Added `examples/foundational/26d-gemini-live-text.py` which is
   using Gemini as TEXT modality and using another TTS provider for TTS process.
 
 ### Changed
@@ -3519,9 +3756,9 @@ stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
 - Added new foundational examples for `GeminiMultimodalLiveLLMService`:
 
   - `26-gemini-multimodal-live.py`
-  - `26a-gemini-multimodal-live-transcription.py`
-  - `26b-gemini-multimodal-live-video.py`
-  - `26c-gemini-multimodal-live-video.py`
+  - `26a-gemini-live-transcription.py`
+  - `26b-gemini-live-video.py`
+  - `26c-gemini-live-video.py`
 
 - Added `SimliVideoService`. This is an integration for Simli AI avatars.
   (see https://www.simli.com)

COMMUNITY_INTEGRATIONS.md

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

CONTRIBUTING.md

@@ -1,5 +1,9 @@
 ## Contributing to Pipecat
 
+**Want to add a new service integration?**
+We encourage community-maintained integrations! Please see our [Community Integration Guide](COMMUNITY_INTEGRATIONS.md) for the process and requirements.
+
+**Want to contribute to Pipecat core?**
 We welcome contributions of all kinds! Your help is appreciated. Follow these steps to get involved:
 
 1. **Fork this repository**: Start by forking the Pipecat Documentation repository to your GitHub account.

README.md

@@ -3,6 +3,7 @@
 </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
 
@@ -19,10 +20,6 @@
 - **Business Agents** – customer intake, support bots, guided flows
 - **Complex Dialog Systems** – design logic with structured conversations
 
-🧭 Looking to build structured conversations? Check out [Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) for managing complex conversational states and transitions.
-
-🔍 Looking for help debugging your pipeline and processors? Check out [Whisker](https://github.com/pipecat-ai/whisker), a real-time Pipecat debugger.
-
 ## 🧠 Why Pipecat?
 
 - **Voice-first**: Integrates speech recognition, text-to-speech, and conversation handling
@@ -30,40 +27,34 @@
 - **Composable Pipelines**: Build complex behavior from modular components
 - **Real-Time**: Ultra-low latency interaction with different transports (e.g. WebSockets or WebRTC)
 
-## 📱 Client SDKs
+## 🌐 Pipecat Ecosystem
 
-You can connect to Pipecat from any platform using our official SDKs:
+### 📱 Client SDKs
 
-<table>
-  <tr>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/javascript/javascript-original.svg" width="40" height="40" alt="JavaScript"/>
-      <a href="https://docs.pipecat.ai/client/js/introduction">JavaScript</a>
-    </td>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/react/react-original.svg" width="40" height="40" alt="React"/>
-      <a href="https://docs.pipecat.ai/client/react/introduction">React</a>
-    </td>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/react/react-original.svg" width="40" height="40" alt="React Native"/>
-      <a href="https://docs.pipecat.ai/client/react-native/introduction">React Native</a>
-    </td>
-  </tr>
-  <tr>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/swift/swift-original.svg" width="40" height="40" alt="Swift"/>
-      <a href="https://docs.pipecat.ai/client/ios/introduction">Swift</a>
-    </td>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/kotlin/kotlin-original.svg" width="40" height="40" alt="Kotlin"/>
-      <a href="https://docs.pipecat.ai/client/android/introduction">Kotlin</a>
-    </td>
-    <td>
-      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/cplusplus/cplusplus-original.svg" width="40" height="40" alt="JavaScript"/>
-      <a href="https://docs.pipecat.ai/client/c++/introduction">C++</a>
-    </td>
-  </tr>
-</table>
+Building client applications? You can connect to Pipecat from any platform using our official SDKs:
+
+<a href="https://docs.pipecat.ai/client/js/introduction">JavaScript</a> | <a href="https://docs.pipecat.ai/client/react/introduction">React</a> | <a href="https://docs.pipecat.ai/client/react-native/introduction">React Native</a> |
+<a href="https://docs.pipecat.ai/client/ios/introduction">Swift</a> | <a href="https://docs.pipecat.ai/client/android/introduction">Kotlin</a> | <a href="https://docs.pipecat.ai/client/c++/introduction">C++</a> | <a href="https://github.com/pipecat-ai/pipecat-esp32">ESP32</a>
+
+### 🧭 Structured conversations
+
+Looking to build structured conversations? Check out [Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) for managing complex conversational states and transitions.
+
+### 🪄 Beautiful UIs
+
+Want to build beautiful and engaging experiences? Checkout the [Voice UI Kit](https://github.com/pipecat-ai/voice-ui-kit), a collection of components, hooks and templates for building voice AI applications quickly.
+
+### 🔍 Debugging
+
+Looking for help debugging your pipeline and processors? Check out [Whisker](https://github.com/pipecat-ai/whisker), a real-time Pipecat debugger.
+
+### 🖥️ Terminal
+
+Love terminal applications? Check out [Tail](https://github.com/pipecat-ai/tail), a terminal dashboard for Pipecat.
+
+### 📺️ Pipecat TV Channel
+
+Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.youtube.com/playlist?list=PLzU2zoMTQIHjqC3v4q2XVSR3hGSzwKFwH) channel.
 
 ## 🎬 See it in action
 
@@ -72,24 +63,24 @@ You can connect to Pipecat from any platform using our official SDKs:
     <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/storytelling-chatbot/image.png" width="400" /></a>
     <br/>
     <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/translation-chatbot/image.png" width="400" /></a>&nbsp;
-    <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/moondream-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/moondream-chatbot/image.png" width="400" /></a>
+    <a href="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/12-describe-video.py"><img src="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/assets/moondream.png" width="400" /></a>
 </p>
 
 ## 🧩 Available services
 
-| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
-| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                    |
-| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                          |
-| Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
-| Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
-| Serializers         | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
-| Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
-| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
-| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
+| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [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)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 
@@ -184,54 +175,6 @@ Run a specific test suite:
 uv run pytest tests/test_name.py
 ```
 
-### Setting up your editor
-
-This project uses strict [PEP 8](https://peps.python.org/pep-0008/) formatting via [Ruff](https://github.com/astral-sh/ruff).
-
-#### Emacs
-
-You can use [use-package](https://github.com/jwiegley/use-package) to install [emacs-lazy-ruff](https://github.com/christophermadsen/emacs-lazy-ruff) package and configure `ruff` arguments:
-
-```elisp
-(use-package lazy-ruff
-  :ensure t
-  :hook ((python-mode . lazy-ruff-mode))
-  :config
-  (setq lazy-ruff-format-command "ruff format")
-  (setq lazy-ruff-check-command "ruff check --select I"))
-```
-
-`ruff` was installed in the `venv` environment described before, so you should be able to use [pyvenv-auto](https://github.com/ryotaro612/pyvenv-auto) to automatically load that environment inside Emacs.
-
-```elisp
-(use-package pyvenv-auto
-  :ensure t
-  :defer t
-  :hook ((python-mode . pyvenv-auto-run)))
-```
-
-#### Visual Studio Code
-
-Install the
-[Ruff](https://marketplace.visualstudio.com/items?itemName=charliermarsh.ruff) extension. Then edit the user settings (_Ctrl-Shift-P_ `Open User Settings (JSON)`) and set it as the default Python formatter, and enable formatting on save:
-
-```json
-"[python]": {
-    "editor.defaultFormatter": "charliermarsh.ruff",
-    "editor.formatOnSave": true
-}
-```
-
-#### PyCharm
-
-`ruff` was installed in the `venv` environment described before, now to enable autoformatting on save, go to `File` -> `Settings` -> `Tools` -> `File Watchers` and add a new watcher with the following settings:
-
-1. **Name**: `Ruff formatter`
-2. **File type**: `Python`
-3. **Working directory**: `$ContentRoot$`
-4. **Arguments**: `format $FilePath$`
-5. **Program**: `$PyInterpreterDirectory$/ruff`
-
 ## 🤝 Contributing
 
 We welcome contributions from the community! Whether you're fixing bugs, improving documentation, or adding new features, here's how you can help:

SECURITY.md

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

create_daily_room.py

@@ -0,0 +1,250 @@
+#!/usr/bin/env -S uv run
+"""Utilities for creating Daily.co rooms with retry logic.
+
+This module provides functions to create Daily rooms via REST API
+with robust error handling, rate limiting, and exponential backoff retry logic.
+"""
+
+import asyncio
+import os
+import time
+from typing import Dict, Optional
+
+from httpx import AsyncClient, HTTPStatusError
+from loguru import logger
+from tenacity import (
+    AsyncRetrying,
+    RetryError,
+    retry_if_exception_type,
+    stop_after_attempt,
+    wait_exponential,
+)
+
+
+async def periodic_progress_logger(
+    progress_dict: Dict[str, int],
+    total: int,
+    interval_seconds: float = 5.0,
+    stop_event: Optional[asyncio.Event] = None,
+):
+    """Log progress periodically in the background.
+
+    Args:
+        progress_dict: Shared dict with 'completed' and 'failed' counts
+        total: Total number of items being processed
+        interval_seconds: How often to log progress (default 5 seconds)
+        stop_event: Event to signal when to stop logging
+    """
+    if stop_event is None:
+        stop_event = asyncio.Event()
+
+    while not stop_event.is_set():
+        await asyncio.sleep(interval_seconds)
+
+        if stop_event.is_set():
+            break
+
+        total_processed = progress_dict["completed"] + progress_dict["failed"]
+        if total_processed > 0:
+            percentage = (total_processed / total) * 100
+            rate = total_processed / interval_seconds if interval_seconds > 0 else 0
+
+            logger.info(
+                f"⏳ Progress: {total_processed}/{total} ({percentage:.1f}%) - "
+                f"✅ {progress_dict['completed']} succeeded, "
+                f"❌ {progress_dict['failed']} failed"
+            )
+
+
+async def create_daily_room(
+    name: Optional[str] = None,
+    privacy: str = "public",
+    exp_minutes: int = 10,
+    max_retries: int = 5,
+) -> Optional[Dict]:
+    """Create a Daily room with automatic retry on rate limit errors.
+
+    Uses tenacity library to handle rate limiting (429 errors) with
+    exponential backoff and automatic retries.
+
+    Args:
+        name: Room name (auto-generated if None). Must match /[A-Za-z0-9_-]+/ and be <= 128 chars
+        privacy: Room privacy setting ("public" or "private")
+        exp_minutes: Minutes until room expires (default 10)
+        max_retries: Maximum number of retry attempts on rate limit (default 5)
+
+    Returns:
+        Room object dict with 'name', 'url', 'id', 'config', etc., or None on failure
+    """
+    # Calculate expiration timestamp (unix timestamp in seconds)
+    exp_timestamp = int(time.time()) + (exp_minutes * 60)
+
+    # Build request body
+    body = {
+        "privacy": privacy,
+        "properties": {
+            "exp": exp_timestamp,
+        },
+    }
+
+    if name:
+        body["name"] = name
+
+    headers = {
+        "Authorization": f"Bearer {os.getenv('DAILY_API_KEY')}",
+        "Content-Type": "application/json",
+    }
+
+    try:
+        # Use tenacity's AsyncRetrying for automatic retry with exponential backoff
+        async for attempt in AsyncRetrying(
+            retry=retry_if_exception_type(HTTPStatusError),
+            stop=stop_after_attempt(max_retries),
+            wait=wait_exponential(multiplier=1, min=1, max=60),
+            reraise=True,
+        ):
+            with attempt:
+                async with AsyncClient(timeout=30) as client:
+                    response = await client.post(
+                        url="https://api.daily.co/v1/rooms",
+                        headers=headers,
+                        json=body,
+                    )
+                    response.raise_for_status()
+                    return response.json()
+
+        # This line should never be reached due to reraise=True, but satisfies type checker
+        return None
+
+    except RetryError as e:
+        # All retries exhausted
+        last_exception = e.last_attempt.exception()
+        logger.exception(f"Failed to create room after {max_retries} retries: {last_exception}")
+        return None
+
+    except Exception as e:
+        logger.exception(f"Unexpected error creating room: {e}")
+        return None
+
+
+async def create_room_with_progress(
+    index: int, total: int, progress_dict: Dict[str, int], **kwargs
+) -> Optional[Dict]:
+    """Wrapper for create_daily_room that tracks progress.
+
+    Args:
+        index: Index of this room creation (0-based)
+        total: Total number of rooms being created
+        progress_dict: Shared dict for tracking progress {"completed": 0, "failed": 0}
+        **kwargs: Arguments passed to create_daily_room
+
+    Returns:
+        Room object dict or None
+    """
+    result = await create_daily_room(**kwargs)
+
+    # Update progress
+    if result is not None:
+        progress_dict["completed"] += 1
+    else:
+        progress_dict["failed"] += 1
+
+    return result
+
+
+async def test_create_rooms(
+    num_rooms: int = 1000,
+    progress_interval: float = 5.0,
+) -> Dict[str, int | float]:
+    """Attempt to create multiple Daily rooms concurrently.
+
+    This function demonstrates concurrent room creation and tracks
+    success/failure statistics. Rate limiting will likely occur when
+    creating many rooms quickly.
+
+    Args:
+        num_rooms: Number of rooms to attempt to create (default 1000)
+        progress_interval: How often to log progress in seconds (default 5.0)
+
+    Returns:
+        Dict with statistics: {'success': int, 'failed': int, 'total': int, 'elapsed_seconds': float}
+    """
+    logger.info(f"Starting bulk room creation: attempting to create {num_rooms} rooms")
+    start_time = time.time()
+
+    # Shared progress tracking dictionary
+    progress_dict = {"completed": 0, "failed": 0}
+
+    # Start background progress logger
+    stop_event = asyncio.Event()
+    progress_task = asyncio.create_task(
+        periodic_progress_logger(progress_dict, num_rooms, progress_interval, stop_event)
+    )
+
+    # Create and execute all tasks concurrently
+    logger.info(f"Executing {num_rooms} concurrent room creation requests...")
+    tasks = [
+        create_room_with_progress(
+            index=i,
+            total=num_rooms,
+            progress_dict=progress_dict,
+            name=None,  # Auto-generate names
+            privacy="public",
+            exp_minutes=10,
+            max_retries=5,
+        )
+        for i in range(num_rooms)
+    ]
+
+    try:
+        results = await asyncio.gather(*tasks, return_exceptions=True)
+    finally:
+        # Stop the progress logger
+        stop_event.set()
+        await progress_task
+
+    # Count successes and failures
+    success_count = sum(1 for r in results if r is not None and not isinstance(r, Exception))
+    failed_count = num_rooms - success_count
+
+    elapsed_time = time.time() - start_time
+
+    # Log statistics
+    logger.info("=" * 60)
+    logger.info("BULK ROOM CREATION SUMMARY")
+    logger.info("=" * 60)
+    logger.info(f"Total rooms attempted: {num_rooms}")
+    logger.info(f"Successfully created: {success_count}")
+    logger.info(f"Failed to create: {failed_count}")
+    logger.info(f"Success rate: {(success_count / num_rooms * 100):.2f}%")
+    logger.info(f"Total time: {elapsed_time:.2f} seconds")
+    logger.info(f"Average time per room: {(elapsed_time / num_rooms):.3f} seconds")
+    logger.info("=" * 60)
+
+    return {
+        "success": success_count,
+        "failed": failed_count,
+        "total": num_rooms,
+        "elapsed_seconds": elapsed_time,
+    }
+
+
+# Example usage
+async def main():
+    """Example usage of the room creation functions."""
+    # Test creating a single room
+    logger.info("Testing single room creation...")
+    room = await create_daily_room(exp_minutes=10)
+    if room:
+        logger.info(f"Created room: {room['name']} at {room['url']}")
+    else:
+        logger.error("Failed to create room")
+
+    # Uncomment to test bulk creation (warning: may hit rate limits!)
+    logger.info("\nTesting bulk room creation...")
+    stats = await test_create_rooms(num_rooms=1000)
+    logger.info(f"Final stats: {stats}")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

docs/api/conf.py

@@ -50,6 +50,7 @@ autodoc_mock_imports = [
     # Krisp - has build issues on some platforms
     "pipecat_ai_krisp",
     "krisp",
+    "krisp_audio",
     # System-specific GUI libraries
     "_tkinter",
     "tkinter",

env.example

@@ -58,6 +58,9 @@ GOOGLE_CLOUD_PROJECT_ID=...
 GOOGLE_TEST_CREDENTIALS=...
 GOOGLE_VERTEX_TEST_CREDENTIALS=...
 
+# Hume
+HUME_API_KEY=...
+
 # LMNT
 LMNT_API_KEY=...
 LMNT_VOICE_ID=...
@@ -87,6 +90,9 @@ SIMLI_FACE_ID=...
 # Krisp
 KRISP_MODEL_PATH=...
 
+# Krisp Viva
+KRISP_VIVA_MODEL_PATH=...
+
 # DeepSeek
 DEEPSEEK_API_KEY=...
 
@@ -155,3 +161,9 @@ NVIDIA_API_KEY=...
 
 # Qwen
 QWEN_API_KEY=...
+
+# WhatsApp
+WHATSAPP_TOKEN=
+WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=
+WHATSAPP_PHONE_NUMBER_ID=
+WHATSAPP_APP_SECRET=

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

@@ -25,7 +25,7 @@ from pipecat.processors.aggregators.llm_response_universal import LLMContextAggr
 from pipecat.runner.daily import configure
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.daily.transport import DailyLogLevel, DailyParams, DailyTransport
+from pipecat.transports.daily.transport import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -49,7 +49,6 @@ async def main():
                 turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
             ),
         )
-        transport.set_log_level(DailyLogLevel.Info)
 
         tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/07-interruptible.py

@@ -21,8 +21,8 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.stt import CartesiaSTTService
 from pipecat.services.cartesia.tts import 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
@@ -58,7 +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 = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/07ae-interruptible-hume.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.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.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_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = HumeTTSService(
+        api_key=os.getenv("HUME_API_KEY"),
+        # Replace with your Hume voice ID
+        voice_id="f898a92e-685f-43fa-985b-a46920f0650b",
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            rtvi,
+            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,
+            audio_out_sample_rate=HUME_SAMPLE_RATE,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        observers=[RTVIObserver(rtvi)],
+    )
+
+    @rtvi.event_handler("on_client_ready")
+    async def on_client_ready(rtvi):
+        await rtvi.set_bot_ready()
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

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

@@ -0,0 +1,118 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContext,
+    LLMContextAggregatorPair,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.flux.stt import DeepgramFluxSTTService
+from pipecat.services.deepgram.tts import DeepgramTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramFluxSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

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

@@ -23,7 +23,6 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.elevenlabs.stt import ElevenLabsSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService
 from pipecat.services.openai.llm import OpenAILLMService

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

@@ -0,0 +1,151 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""
+A conversational AI bot using Gemini for both LLM, STT and TTS.
+
+This example demonstrates how to use Gemini's image generation capabilities.
+
+Features showcased:
+- Gemini LLM for conversation and image generation
+- Google TTS and STT
+
+Run with:
+    python examples/foundational/07n-interruptible-gemini-image.py
+
+Make sure to set your environment variables:
+    export GOOGLE_API_KEY=your_api_key_here
+"""
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.google.llm import GoogleLLMService
+from pipecat.services.google.stt import GoogleSTTService
+from pipecat.services.google.tts import GoogleTTSService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_out_enabled=True,
+        video_out_width=1024,
+        video_out_height=1024,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_out_enabled=True,
+        video_out_width=1024,
+        video_out_height=1024,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = GoogleSTTService(
+        params=GoogleSTTService.InputParams(languages=Language.EN_US),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+    )
+
+    tts = GoogleTTSService(
+        voice_id="en-US-Chirp3-HD-Charon",
+        params=GoogleTTSService.InputParams(language=Language.EN_US),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+    )
+
+    llm = GoogleLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        model="gemini-2.5-flash-image",
+    )
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # Gemini TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation with a styled introduction
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

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

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

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

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

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

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

examples/foundational/14x-function-calling-openpipe.py

@@ -0,0 +1,182 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+import time
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame, TTSSpeakFrame
+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.llm_service import FunctionCallParams
+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
+
+load_dotenv(override=True)
+
+
+async def fetch_weather_from_api(params: FunctionCallParams):
+    await params.result_callback({"conditions": "nice", "temperature": "75"})
+
+
+async def fetch_restaurant_recommendation(params: FunctionCallParams):
+    await params.result_callback({"name": "The Golden Dragon"})
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    timestamp = int(time.time())
+    llm = OpenPipeLLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
+        tags={"conversation_id": f"pipecat-{timestamp}"},
+    )
+
+    # You can also register a function_name of None to get all functions
+    # sent to the same callback with an additional function_name parameter.
+    llm.register_function("get_current_weather", fetch_weather_from_api)
+    llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
+
+    @llm.event_handler("on_function_calls_started")
+    async def on_function_calls_started(service, function_calls):
+        await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
+
+    weather_function = FunctionSchema(
+        name="get_current_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
+            },
+        },
+        required=["location", "format"],
+    )
+    restaurant_function = FunctionSchema(
+        name="get_restaurant_recommendation",
+        description="Get a restaurant recommendation",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+        },
+        required=["location"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages, tools)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        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/16-gpu-container-local-bot.py

@@ -26,7 +26,11 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.deepgram.tts import DeepgramTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.daily.transport import DailyParams, DailyTransportMessageFrame
+from pipecat.transports.daily.transport import (
+    DailyOutputTransportMessageFrame,
+    DailyOutputTransportMessageUrgentFrame,
+    DailyParams,
+)
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
@@ -128,14 +132,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                 logger.debug(f"Received latency ping app message: {message}")
                 ts = message["latency-ping"]["ts"]
                 # Send immediately
-                transport.output().send_message(
-                    DailyTransportMessageFrame(
+                await task.queue_frame(
+                    DailyOutputTransportMessageUrgentFrame(
                         message={"latency-pong-msg-handler": {"ts": ts}}, participant_id=sender
                     )
                 )
                 # And push to the pipeline for the Daily transport.output to send
                 await task.queue_frame(
-                    DailyTransportMessageFrame(
+                    DailyOutputTransportMessageFrame(
                         message={"latency-pong-pipeline-delivery": {"ts": ts}},
                         participant_id=sender,
                     )

examples/foundational/19-openai-realtime.py

@@ -24,14 +24,15 @@ from pipecat.processors.transcript_processor import TranscriptProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.llm_service import FunctionCallParams
-from pipecat.services.openai_realtime import (
+from pipecat.services.openai.realtime.events import (
+    AudioConfiguration,
+    AudioInput,
     InputAudioNoiseReduction,
     InputAudioTranscription,
-    OpenAIRealtimeLLMService,
     SemanticTurnDetection,
     SessionProperties,
 )
-from pipecat.services.openai_realtime.events import AudioConfiguration, AudioInput
+from pipecat.services.openai.realtime.llm import OpenAIRealtimeLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams

examples/foundational/19a-azure-realtime.py

@@ -21,13 +21,14 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
+from pipecat.services.azure.realtime.llm import AzureRealtimeLLMService
 from pipecat.services.llm_service import FunctionCallParams
-from pipecat.services.openai_realtime import (
-    AzureRealtimeLLMService,
+from pipecat.services.openai.realtime.events import (
+    AudioConfiguration,
+    AudioInput,
     InputAudioTranscription,
     SessionProperties,
 )
-from pipecat.services.openai_realtime.events import AudioConfiguration, AudioInput
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams

examples/foundational/19b-openai-realtime-text.py

@@ -22,16 +22,17 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.transcript_processor import TranscriptProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.llm_service import FunctionCallParams
-from pipecat.services.openai_realtime import (
+from pipecat.services.openai.realtime.events import (
+    AudioConfiguration,
+    AudioInput,
     InputAudioNoiseReduction,
     InputAudioTranscription,
-    OpenAIRealtimeLLMService,
     SemanticTurnDetection,
     SessionProperties,
 )
-from pipecat.services.openai_realtime.events import AudioConfiguration, AudioInput
+from pipecat.services.openai.realtime.llm import OpenAIRealtimeLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams

examples/foundational/20b-persistent-context-openai-realtime.py

@@ -25,13 +25,14 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.llm_service import FunctionCallParams
-from pipecat.services.openai_realtime import (
+from pipecat.services.openai.realtime.events import (
+    AudioConfiguration,
+    AudioInput,
     InputAudioTranscription,
-    OpenAIRealtimeLLMService,
     SessionProperties,
     TurnDetection,
 )
-from pipecat.services.openai_realtime.events import AudioConfiguration, AudioInput
+from pipecat.services.openai.realtime.llm import OpenAIRealtimeLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams

examples/foundational/20e-persistent-context-aws-nova-sonic.py

@@ -23,7 +23,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.aws_nova_sonic.aws import AWSNovaSonicLLMService
+from pipecat.services.aws.nova_sonic.llm import AWSNovaSonicLLMService
 from pipecat.services.llm_service import FunctionCallParams
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams

examples/foundational/26-gemini-live.py

@@ -17,7 +17,7 @@ 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.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -65,7 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     Respond to what the user said in a creative and helpful way.
     """
 
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         system_instruction=system_instruction,
         voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck

examples/foundational/26a-gemini-live-transcription.py

@@ -20,7 +20,7 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.transcript_processor import TranscriptProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -65,7 +65,7 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Aoede",  # Puck, Charon, Kore, Fenrir, Aoede
         # system_instruction="Talk like a pirate."

examples/foundational/26b-gemini-live-function-calling.py

@@ -22,7 +22,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.services.llm_service import FunctionCallParams
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
@@ -122,12 +122,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         required=["location"],
     )
     search_tool = {"google_search": {}}
+    # KNOWN ISSUE: If using GeminiVertexLiveLLMService, it appears
+    # you cannot use the "google_search" tool alongside other tools.
+    # See https://github.com/googleapis/python-genai/issues/941.
     tools = ToolsSchema(
         standard_tools=[weather_function, restaurant_function],
         custom_tools={AdapterType.GEMINI: [search_tool]},
     )
 
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         system_instruction=system_instruction,
         tools=tools,

examples/foundational/26c-gemini-live-video.py

@@ -24,7 +24,7 @@ from pipecat.runner.utils import (
     maybe_capture_participant_camera,
     maybe_capture_participant_screen,
 )
-from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 
@@ -58,7 +58,7 @@ transport_params = {
 
 
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Aoede",  # Puck, Charon, Kore, Fenrir, Aoede
         # system_instruction="Talk like a pirate."

examples/foundational/26d-gemini-live-text.py

@@ -20,9 +20,9 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.gemini_multimodal_live.gemini import (
-    GeminiMultimodalLiveLLMService,
-    GeminiMultimodalModalities,
+from pipecat.services.google.gemini_live.llm import (
+    GeminiLiveLLMService,
+    GeminiModalities,
     InputParams,
 )
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -80,11 +80,15 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    llm = GeminiMultimodalLiveLLMService(
+    # KNOWN ISSUE: If using GeminiLiveVertexLLMService, you cannot specify a
+    # modality other than AUDIO (at least not if using the service's default
+    # model, which is a native audio model:
+    # https://cloud.google.com/vertex-ai/generative-ai/docs/live-api/tools#native-audio).
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         system_instruction=SYSTEM_INSTRUCTION,
         tools=[{"google_search": {}}, {"code_execution": {}}],
-        params=InputParams(modalities=GeminiMultimodalModalities.TEXT),
+        params=InputParams(modalities=GeminiModalities.TEXT),
     )
 
     # Optionally, you can set the response modalities via a function

examples/foundational/26e-gemini-live-google-search.py

@@ -19,7 +19,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -83,7 +83,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
     # Initialize the Gemini Multimodal Live model
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
         system_instruction=system_instruction,

examples/foundational/26f-gemini-live-files-api.py

@@ -19,9 +19,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.gemini_multimodal_live.gemini import (
-    GeminiMultimodalLiveLLMService,
-)
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -110,7 +108,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     """
 
     # Initialize Gemini service with File API support
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         system_instruction=system_instruction,
         voice_id="Charon",  # Aoede, Charon, Fenrir, Kore, Puck

examples/foundational/26g-gemini-live-groundingMetadata.py

@@ -9,13 +9,13 @@ from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import Frame, LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
 from pipecat.services.google.frames import LLMSearchResponseFrame
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -105,7 +105,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         custom_tools={AdapterType.GEMINI: [{"google_search": {}}, {"code_execution": {}}]},
     )
 
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         system_instruction=SYSTEM_INSTRUCTION,
         voice_id="Charon",  # Aoede, Charon, Fenrir, Kore, Puck

examples/foundational/26h-gemini-live-vertex-function-calling.py

@@ -0,0 +1,191 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+from datetime import datetime
+
+from dotenv import load_dotenv
+from google.genai.types import HttpOptions
+from loguru import logger
+
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import AdapterType, ToolsSchema
+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.openai_llm_context import OpenAILLMContext
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
+from pipecat.services.google.gemini_live.llm_vertex import GeminiLiveVertexLLMService
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+async def fetch_weather_from_api(params: FunctionCallParams):
+    temperature = 75 if params.arguments["format"] == "fahrenheit" else 24
+    await params.result_callback(
+        {
+            "conditions": "nice",
+            "temperature": temperature,
+            "format": params.arguments["format"],
+            "timestamp": datetime.now().strftime("%Y%m%d_%H%M%S"),
+        }
+    )
+
+
+async def fetch_restaurant_recommendation(params: FunctionCallParams):
+    await params.result_callback({"name": "The Golden Dragon"})
+
+
+system_instruction = """
+You are a helpful assistant who can answer questions and use tools.
+
+You have three tools available to you:
+1. get_current_weather: Use this tool to get the current weather in a specific location.
+2. get_restaurant_recommendation: Use this tool to get a restaurant recommendation in a specific location.
+"""
+
+
+# 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,
+        # set stop_secs to something roughly similar to the internal setting
+        # of the Multimodal Live api, just to align events. This doesn't really
+        # matter because we can only use the Multimodal Live API's phrase
+        # endpointing, for now.
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        # set stop_secs to something roughly similar to the internal setting
+        # of the Multimodal Live api, just to align events. This doesn't really
+        # matter because we can only use the Multimodal Live API's phrase
+        # endpointing, for now.
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        # set stop_secs to something roughly similar to the internal setting
+        # of the Multimodal Live api, just to align events. This doesn't really
+        # matter because we can only use the Multimodal Live API's phrase
+        # endpointing, for now.
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    weather_function = FunctionSchema(
+        name="get_current_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
+            },
+        },
+        required=["location", "format"],
+    )
+    restaurant_function = FunctionSchema(
+        name="get_restaurant_recommendation",
+        description="Get a restaurant recommendation",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+        },
+        required=["location"],
+    )
+    # KNOWN ISSUE: If using GeminiVertexLiveLLMService, it appears
+    # you cannot use the "google_search" tool alongside other tools.
+    # See https://github.com/googleapis/python-genai/issues/941.
+    tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])
+
+    llm = GeminiLiveVertexLLMService(
+        credentials=os.getenv("GOOGLE_VERTEX_TEST_CREDENTIALS"),
+        project_id=os.getenv("GOOGLE_CLOUD_PROJECT_ID"),
+        location=os.getenv("GOOGLE_CLOUD_LOCATION"),
+        system_instruction=system_instruction,
+        voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
+        tools=tools,
+    )
+
+    llm.register_function("get_current_weather", fetch_weather_from_api)
+    llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
+
+    context = OpenAILLMContext(
+        [{"role": "user", "content": "Say hello."}],
+    )
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            context_aggregator.user(),
+            llm,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        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/26i-gemini-live-graceful-end.py

@@ -0,0 +1,204 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+from datetime import datetime
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import AdapterType, ToolsSchema
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import EndTaskFrame, LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.frame_processor import FrameDirection
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+async def fetch_weather_from_api(params: FunctionCallParams):
+    temperature = 75 if params.arguments["format"] == "fahrenheit" else 24
+    await params.result_callback(
+        {
+            "conditions": "nice",
+            "temperature": temperature,
+            "format": params.arguments["format"],
+            "timestamp": datetime.now().strftime("%Y%m%d_%H%M%S"),
+        }
+    )
+
+
+async def fetch_restaurant_recommendation(params: FunctionCallParams):
+    await params.result_callback({"name": "The Golden Dragon"})
+
+
+async def end_conversation(params: FunctionCallParams):
+    await params.result_callback({"success": True})
+    await params.llm.push_frame(EndTaskFrame(), FrameDirection.UPSTREAM)
+
+
+system_instruction = """
+You are a helpful assistant who can answer questions and use tools.
+
+You have three tools available to you:
+1. get_current_weather: Use this tool to get the current weather in a specific location.
+2. get_restaurant_recommendation: Use this tool to get a restaurant recommendation in a specific location.
+3. end_conversation: Use this tool to gracefully end the conversation.
+
+After you've responded to the user three times, do two things, in order:
+1. Politely let them know that that's all the time you have today and say goodbye.
+2. Call the end_conversation tool to gracefully end the conversation.
+"""
+
+
+# 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,
+        # set stop_secs to something roughly similar to the internal setting
+        # of the Multimodal Live api, just to align events. This doesn't really
+        # matter because we can only use the Multimodal Live API's phrase
+        # endpointing, for now.
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        # set stop_secs to something roughly similar to the internal setting
+        # of the Multimodal Live api, just to align events. This doesn't really
+        # matter because we can only use the Multimodal Live API's phrase
+        # endpointing, for now.
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        # set stop_secs to something roughly similar to the internal setting
+        # of the Multimodal Live api, just to align events. This doesn't really
+        # matter because we can only use the Multimodal Live API's phrase
+        # endpointing, for now.
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    weather_function = FunctionSchema(
+        name="get_current_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
+            },
+        },
+        required=["location", "format"],
+    )
+    restaurant_function = FunctionSchema(
+        name="get_restaurant_recommendation",
+        description="Get a restaurant recommendation",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+        },
+        required=["location"],
+    )
+    end_conversation_function = FunctionSchema(
+        name="end_conversation",
+        description="Gracefully end the conversation",
+        properties={},
+        required=[],
+    )
+    search_tool = {"google_search": {}}
+    tools = ToolsSchema(
+        standard_tools=[weather_function, restaurant_function, end_conversation_function],
+        custom_tools={AdapterType.GEMINI: [search_tool]},
+    )
+
+    llm = GeminiLiveLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        system_instruction=system_instruction,
+        tools=tools,
+    )
+
+    llm.register_function("get_current_weather", fetch_weather_from_api)
+    llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
+    llm.register_function("end_conversation", end_conversation)
+
+    context = OpenAILLMContext(
+        [{"role": "user", "content": "Say hello."}],
+    )
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            context_aggregator.user(),
+            llm,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        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/39-mcp-stdio.py

@@ -206,6 +206,14 @@ async def bot(runner_args: RunnerArguments):
 
 
 if __name__ == "__main__":
+    if not os.getenv("NASA_API_KEY"):
+        logger.error(
+            f"Please set NASA_API_KEY environment variable for this example. See https://api.nasa.gov"
+        )
+        import sys
+
+        sys.exit(1)
+
     from pipecat.runner.run import main
 
     main()

examples/foundational/39a-mcp-run-sse.py

@@ -141,6 +141,14 @@ async def bot(runner_args: RunnerArguments):
 
 
 if __name__ == "__main__":
+    if not os.getenv("MCP_RUN_SSE_URL"):
+        logger.error(
+            f"Please set MCP_RUN_SSE_URL environment variable for this example. See https://mcp.run"
+        )
+        import sys
+
+        sys.exit(1)
+
     from pipecat.runner.run import main
 
     main()

examples/foundational/39b-multiple-mcp.py

@@ -219,6 +219,14 @@ async def bot(runner_args: RunnerArguments):
 
 
 if __name__ == "__main__":
+    if not os.getenv("NASA_API_KEY") or not os.getenv("MCP_RUN_SSE_URL"):
+        logger.error(
+            f"Please set NASA_API_KEY and MCP_RUN_SSE_URL environment variables. See https://api.nasa.gov and https://mcp.run"
+        )
+        import sys
+
+        sys.exit(1)
+
     from pipecat.runner.run import main
 
     main()

examples/foundational/39c-mcp-run-http.py

@@ -145,6 +145,14 @@ async def bot(runner_args: RunnerArguments):
 
 
 if __name__ == "__main__":
+    if not os.getenv("GITHUB_PERSONAL_ACCESS_TOKEN"):
+        logger.error(
+            f"Please set GITHUB_PERSONAL_ACCESS_TOKEN environment variable for this example."
+        )
+        import sys
+
+        sys.exit(1)
+
     from pipecat.runner.run import main
 
     main()

examples/foundational/40-aws-nova-sonic.py

@@ -21,7 +21,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.aws_nova_sonic import AWSNovaSonicLLMService
+from pipecat.services.aws.nova_sonic.llm import AWSNovaSonicLLMService
 from pipecat.services.llm_service import FunctionCallParams
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams

examples/foundational/46-video-processing.py

@@ -20,7 +20,7 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.frameworks.rtvi import RTVIObserver, RTVIProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.gemini_multimodal_live import GeminiMultimodalLiveLLMService
+from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.daily.transport import DailyParams, DailyTransport
 
@@ -94,7 +94,7 @@ Respond to what the user said in a creative and helpful way. Keep your responses
 
 
 async def run_bot(pipecat_transport):
-    llm = GeminiMultimodalLiveLLMService(
+    llm = GeminiLiveLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
         transcribe_user_audio=True,

examples/foundational/47-sentry-metrics.py

@@ -0,0 +1,142 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+import sentry_sdk
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
+from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.metrics.sentry import SentryMetrics
+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.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    # Initialize Sentry
+    sentry_sdk.init(
+        dsn=os.getenv("SENTRY_DSN"),
+        traces_sample_rate=1.0,
+    )
+
+    stt = DeepgramSTTService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        metrics=SentryMetrics(),
+    )
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        metrics=SentryMetrics(),
+    )
+
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        metrics=SentryMetrics(),
+    )
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    context_aggregator = LLMContextAggregatorPair(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/README.md

@@ -105,7 +105,7 @@ uv run 07-interruptible.py -t twilio -x NGROK_HOST_NAME
 ### Vision & Multimodal
 
 - **[12a-describe-video-gemini-flash.py](./12a-describe-video-gemini-flash.py)**: Bot describes user's video (Video input, Multimodal LLMs)
-- **[26c-gemini-multimodal-live-video.py](./26c-gemini-multimodal-live-video.py)**: Gemini with video input (Streaming video, Function calls)
+- **[26c-gemini-live-video.py](./26c-gemini-live-video.py)**: Gemini with video input (Streaming video, Function calls)
 
 ### Voice & Language
 

examples/quickstart/pyproject.toml

@@ -4,7 +4,7 @@ version = "0.1.0"
 description = "Quickstart example for building voice AI bots with Pipecat"
 requires-python = ">=3.10"
 dependencies = [
-    "pipecat-ai[webrtc,daily,silero,deepgram,openai,cartesia,local-smart-turn-v3,runner]>=0.0.85",
+    "pipecat-ai[webrtc,daily,silero,deepgram,openai,cartesia,local-smart-turn-v3,runner]>=0.0.86",
     "pipecatcloud>=0.2.4"
 ]
 

fetch_s3_recording.py

@@ -0,0 +1,267 @@
+#!/usr/bin/env -S uv run
+"""Utilities for fetching Daily.co recording URLs with retry logic.
+
+This module provides functions to retrieve recording download links from Daily's REST API
+with robust error handling, rate limiting, and exponential backoff retry logic.
+"""
+
+import asyncio
+import os
+from typing import Optional, Tuple
+
+from httpx import AsyncClient, HTTPStatusError
+from loguru import logger
+from tenacity import (
+    AsyncRetrying,
+    RetryError,
+    retry_if_exception_type,
+    stop_after_attempt,
+    wait_exponential,
+)
+
+
+async def get_recording_s3_url_with_retry(
+    room_id: str,
+    max_retries: int = 5,
+) -> Tuple[Optional[str], Optional[str]]:
+    """Retrieve recording URL with exponential backoff and retry logic.
+
+    Uses tenacity library to handle rate limiting (429 errors) and other
+    transient errors with automatic exponential backoff.
+
+    Args:
+        room_id: Daily.co room identifier
+        max_retries: Maximum number of retry attempts (default 5)
+
+    Returns:
+        Tuple of (recording_url, recording_signed_url)
+        Returns (None, None) if no recording exists for the room.
+    """
+    try:
+        # Use tenacity's AsyncRetrying for automatic retry with exponential backoff
+        async for attempt in AsyncRetrying(
+            retry=retry_if_exception_type((HTTPStatusError, Exception)),
+            stop=stop_after_attempt(max_retries),
+            wait=wait_exponential(multiplier=1, min=1, max=60),
+            reraise=True,
+        ):
+            with attempt:
+                recording_url, recording_signed_url, status = await get_recording_s3_url(
+                    room_id=room_id
+                )
+
+                # If no recording exists (status is None), return immediately - no retry
+                if status is None:
+                    logger.debug(f"No recording found for room {room_id}")
+                    return None, None
+
+                # If recording exists but is not finished yet, retry
+                if status != "finished":
+                    logger.warning(
+                        f"Recording not finished for room {room_id}, status: {status} "
+                        f"(attempt {attempt.retry_state.attempt_number}/{max_retries})"
+                    )
+                    raise Exception(f"Recording not ready, status: {status}")
+
+                # Recording is finished, return the URLs
+                return recording_url, recording_signed_url
+
+        # This line should never be reached due to reraise=True, but satisfies type checker
+        return None, None
+
+    except RetryError as e:
+        # All retries exhausted
+        last_exception = e.last_attempt.exception()
+        logger.error(
+            f"Failed to retrieve recording URL for room {room_id} after {max_retries} attempts: "
+            f"{last_exception}"
+        )
+        return None, None
+
+    except Exception as e:
+        logger.exception(f"Unexpected error retrieving recording for room {room_id}: {e}")
+        return None, None
+
+
+async def get_recording_s3_url(
+    room_id: str,
+) -> Tuple[Optional[str], Optional[str], Optional[str]]:
+    """Get recording URL using Daily's REST API.
+
+    Args:
+        room_id: Daily.co room identifier
+
+    Returns:
+        Tuple of (recording_url, recording_signed_url, status)
+        - recording_url: The download link for the recording
+        - recording_signed_url: Same as recording_url (kept for backward compatibility)
+        - status: Recording status from Daily API
+
+    Raises:
+        HTTPStatusError: When HTTP errors occur (including rate limits)
+    """
+    headers = {
+        "Authorization": f"Bearer {os.getenv('DAILY_API_KEY')}",
+        "Content-Type": "application/json",
+    }
+
+    async with AsyncClient(timeout=180) as client:
+        # List recordings for the room
+        list_response = await client.get(
+            url=f"https://api.daily.co/v1/recordings?room_name={room_id}",
+            headers=headers,
+        )
+        list_response.raise_for_status()
+        list_data = list_response.json()
+
+        # Check if recording exists and is finished
+        if not list_data.get("data") or len(list_data["data"]) == 0:
+            return (None, None, None)
+
+        recording_id = list_data["data"][0].get("id")
+        status = list_data["data"][0].get("status")
+
+        if not recording_id or status != "finished":
+            return (None, None, status)
+
+        # Get the recording access link
+        link_response = await client.get(
+            url=f"https://api.daily.co/v1/recordings/{recording_id}/access-link",
+            headers=headers,
+        )
+        link_response.raise_for_status()
+        link_data = link_response.json()
+
+    recording_url = link_data.get("download_link")
+    if not recording_url:
+        logger.warning(f"No download link found for recording {recording_id}")
+        return (None, None, status)
+
+    # Return the same URL for both fields for backward compatibility
+    return (recording_url, recording_url, status)
+
+
+async def get_recent_recordings(limit: int = 100) -> list[str]:
+    """Get list of recent recording IDs from Daily API.
+
+    Args:
+        limit: Maximum number of recordings to retrieve (default 100)
+
+    Returns:
+        List of recording IDs (strings)
+    """
+    try:
+        async with AsyncClient() as client:
+            response = await client.get(
+                url="https://api.daily.co/v1/recordings",
+                headers={
+                    "Authorization": f"Bearer {os.getenv('DAILY_API_KEY')}",
+                    "Content-Type": "application/json",
+                },
+                timeout=30,
+            )
+            response.raise_for_status()
+
+        data = response.json()
+        recordings = data.get("data", [])
+        recording_ids = [rec.get("id") for rec in recordings[:limit] if rec.get("id")]
+
+        logger.info(f"Retrieved {len(recording_ids)} recording IDs from Daily API")
+        return recording_ids
+
+    except Exception as e:
+        logger.exception(f"Failed to get recordings from Daily API: {e}")
+        return []
+
+
+async def main():
+    """Test get_recording_s3_url_with_retry with recent recordings."""
+    logger.info("Starting recording fetch test...")
+
+    # Step 1: Get the most recent 100 recordings
+    logger.info("Fetching recent recordings...")
+    recording_ids = await get_recent_recordings(limit=100)
+
+    if not recording_ids:
+        logger.error("No recordings found. Cannot proceed with test.")
+        return
+
+    logger.info(f"Found {len(recording_ids)} recordings to fetch")
+
+    # Fetch access links for each recording concurrently
+    logger.info(
+        f"Attempting to fetch access links for {len(recording_ids)} recordings concurrently..."
+    )
+
+    # Create tasks for all recordings
+    async def get_recording_link(recording_id: str) -> Tuple[Optional[str], Optional[str]]:
+        """Get download link for a specific recording ID."""
+        try:
+            headers = {
+                "Authorization": f"Bearer {os.getenv('DAILY_API_KEY')}",
+                "Content-Type": "application/json",
+            }
+
+            async with AsyncClient(timeout=180) as client:
+                # Get the recording access link
+                link_response = await client.get(
+                    url=f"https://api.daily.co/v1/recordings/{recording_id}/access-link",
+                    headers=headers,
+                )
+                link_response.raise_for_status()
+                link_data = link_response.json()
+
+            recording_url = link_data.get("download_link")
+            if not recording_url:
+                logger.warning(f"No download link found for recording {recording_id}")
+                return (None, None)
+
+            return (recording_url, recording_url)
+
+        except Exception as e:
+            logger.exception(f"Failed to get access link for recording {recording_id}: {e}")
+            return (None, None)
+
+    tasks = [get_recording_link(recording_id) for recording_id in recording_ids]
+
+    # Execute all tasks concurrently
+    results = await asyncio.gather(*tasks, return_exceptions=True)
+
+    # Process results
+    success_count = 0
+    not_found_count = 0
+    failed_count = 0
+
+    for i, (recording_id, result) in enumerate(zip(recording_ids, results), 1):
+        if isinstance(result, Exception):
+            failed_count += 1
+            logger.error(f"❌ [{i}/{len(recording_ids)}] Failed for {recording_id}: {result}")
+        elif isinstance(result, tuple) and len(result) == 2:
+            recording_url, recording_signed_url = result
+            if recording_url:
+                success_count += 1
+                logger.info(
+                    f"✅ [{i}/{len(recording_ids)}] Found recording link for {recording_id}"
+                )
+                logger.debug(f"   URL: {recording_url}")
+            else:
+                not_found_count += 1
+                logger.debug(f"ℹ️  [{i}/{len(recording_ids)}] No link for {recording_id}")
+        else:
+            failed_count += 1
+            logger.error(f"❌ [{i}/{len(recording_ids)}] Unexpected result type for {recording_id}")
+
+    # Summary
+    logger.info("\n" + "=" * 60)
+    logger.info("RECORDING FETCH TEST SUMMARY")
+    logger.info("=" * 60)
+    logger.info(f"Total recordings checked: {len(recording_ids)}")
+    logger.info(f"✅ Recordings found: {success_count}")
+    logger.info(f"ℹ️  No recordings: {not_found_count}")
+    logger.info(f"❌ Failed: {failed_count}")
+    logger.info(f"Success rate: {(success_count / len(recording_ids) * 100):.2f}%")
+    logger.info("=" * 60)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

fetch_s3_recording_by_room.py

@@ -0,0 +1,238 @@
+#!/usr/bin/env -S uv run
+"""Utilities for fetching Daily.co recording URLs with retry logic.
+
+This module provides functions to retrieve recording download links from Daily's REST API
+with robust error handling, rate limiting, and exponential backoff retry logic.
+"""
+
+import asyncio
+import os
+from typing import Optional, Tuple
+
+from httpx import AsyncClient, HTTPStatusError
+from loguru import logger
+from tenacity import (
+    AsyncRetrying,
+    RetryError,
+    retry_if_exception_type,
+    stop_after_attempt,
+    wait_exponential,
+)
+
+
+async def get_recording_s3_url_with_retry(
+    room_id: str,
+    max_retries: int = 5,
+) -> Tuple[Optional[str], Optional[str]]:
+    """Retrieve recording URL with exponential backoff and retry logic.
+
+    Uses tenacity library to handle rate limiting (429 errors) and other
+    transient errors with automatic exponential backoff.
+
+    Args:
+        room_id: Daily.co room identifier
+        max_retries: Maximum number of retry attempts (default 5)
+
+    Returns:
+        Tuple of (recording_url, recording_signed_url)
+        Returns (None, None) if no recording exists for the room.
+    """
+    try:
+        # Use tenacity's AsyncRetrying for automatic retry with exponential backoff
+        async for attempt in AsyncRetrying(
+            retry=retry_if_exception_type((HTTPStatusError, Exception)),
+            stop=stop_after_attempt(max_retries),
+            wait=wait_exponential(multiplier=1, min=1, max=60),
+            reraise=True,
+        ):
+            with attempt:
+                recording_url, recording_signed_url, status = await get_recording_s3_url(
+                    room_id=room_id
+                )
+
+                # If no recording exists (status is None), return immediately - no retry
+                if status is None:
+                    logger.debug(f"No recording found for room {room_id}")
+                    return None, None
+
+                # If recording exists but is not finished yet, retry
+                if status != "finished":
+                    logger.warning(
+                        f"Recording not finished for room {room_id}, status: {status} "
+                        f"(attempt {attempt.retry_state.attempt_number}/{max_retries})"
+                    )
+                    raise Exception(f"Recording not ready, status: {status}")
+
+                # Recording is finished, return the URLs
+                return recording_url, recording_signed_url
+
+        # This line should never be reached due to reraise=True, but satisfies type checker
+        return None, None
+
+    except RetryError as e:
+        # All retries exhausted
+        last_exception = e.last_attempt.exception()
+        logger.error(
+            f"Failed to retrieve recording URL for room {room_id} after {max_retries} attempts: "
+            f"{last_exception}"
+        )
+        return None, None
+
+    except Exception as e:
+        logger.exception(f"Unexpected error retrieving recording for room {room_id}: {e}")
+        return None, None
+
+
+async def get_recording_s3_url(
+    room_id: str,
+) -> Tuple[Optional[str], Optional[str], Optional[str]]:
+    """Get recording URL using Daily's REST API.
+
+    Args:
+        room_id: Daily.co room identifier
+
+    Returns:
+        Tuple of (recording_url, recording_signed_url, status)
+        - recording_url: The download link for the recording
+        - recording_signed_url: Same as recording_url (kept for backward compatibility)
+        - status: Recording status from Daily API
+
+    Raises:
+        HTTPStatusError: When HTTP errors occur (including rate limits)
+    """
+    headers = {
+        "Authorization": f"Bearer {os.getenv('DAILY_API_KEY')}",
+        "Content-Type": "application/json",
+    }
+
+    async with AsyncClient(timeout=180) as client:
+        # List recordings for the room
+        list_response = await client.get(
+            url=f"https://api.daily.co/v1/recordings?room_name={room_id}",
+            headers=headers,
+        )
+        list_response.raise_for_status()
+        list_data = list_response.json()
+
+        # Check if recording exists and is finished
+        if not list_data.get("data") or len(list_data["data"]) == 0:
+            return (None, None, None)
+
+        recording_id = list_data["data"][0].get("id")
+        status = list_data["data"][0].get("status")
+
+        if not recording_id or status != "finished":
+            return (None, None, status)
+
+        # Get the recording access link
+        link_response = await client.get(
+            url=f"https://api.daily.co/v1/recordings/{recording_id}/access-link",
+            headers=headers,
+        )
+        link_response.raise_for_status()
+        link_data = link_response.json()
+
+    recording_url = link_data.get("download_link")
+    if not recording_url:
+        logger.warning(f"No download link found for recording {recording_id}")
+        return (None, None, status)
+
+    # Return the same URL for both fields for backward compatibility
+    return (recording_url, recording_url, status)
+
+
+async def get_recent_rooms(limit: int = 100) -> list[str]:
+    """Get list of recent room names from Daily API.
+
+    Args:
+        limit: Maximum number of rooms to retrieve (default 100, max 100)
+
+    Returns:
+        List of room names (strings)
+    """
+    try:
+        async with AsyncClient() as client:
+            response = await client.get(
+                url=f"https://api.daily.co/v1/rooms?limit={min(limit, 100)}",
+                headers={
+                    "Authorization": f"Bearer {os.getenv('DAILY_API_KEY')}",
+                    "Content-Type": "application/json",
+                },
+                timeout=30,
+            )
+            response.raise_for_status()
+
+        data = response.json()
+        rooms = data.get("data", [])
+        room_names = [room.get("name") for room in rooms if room.get("name")]
+
+        logger.info(f"Retrieved {len(room_names)} room names from Daily API")
+        return room_names
+
+    except Exception as e:
+        logger.exception(f"Failed to get rooms from Daily API: {e}")
+        return []
+
+
+async def main():
+    """Test get_recording_s3_url_with_retry with recent rooms."""
+    logger.info("Starting recording fetch test...")
+
+    # Step 1: Get the most recent 100 rooms
+    logger.info("Fetching recent rooms...")
+    room_names = await get_recent_rooms(limit=100)
+
+    if not room_names:
+        logger.error("No rooms found. Cannot proceed with test.")
+        return
+
+    logger.info(f"Found {len(room_names)} rooms to check for recordings")
+
+    # Call get_recording_s3_url_with_retry on each room concurrently
+    logger.info(f"Attempting to fetch recordings for {len(room_names)} rooms concurrently...")
+
+    # Create tasks for all rooms
+    tasks = [
+        get_recording_s3_url_with_retry(room_id=room_name, max_retries=3)
+        for room_name in room_names
+    ]
+
+    # Execute all tasks concurrently
+    results = await asyncio.gather(*tasks, return_exceptions=True)
+
+    # Process results
+    success_count = 0
+    not_found_count = 0
+    failed_count = 0
+
+    for i, (room_name, result) in enumerate(zip(room_names, results), 1):
+        if isinstance(result, Exception):
+            failed_count += 1
+            logger.error(f"❌ [{i}/{len(room_names)}] Failed for {room_name}: {result}")
+        elif isinstance(result, tuple) and len(result) == 2:
+            recording_url, recording_signed_url = result
+            if recording_url:
+                success_count += 1
+                logger.info(f"✅ [{i}/{len(room_names)}] Found recording for {room_name}")
+                logger.debug(f"   URL: {recording_url[:80]}...")
+            else:
+                not_found_count += 1
+                logger.debug(f"ℹ️  [{i}/{len(room_names)}] No recording for {room_name}")
+        else:
+            failed_count += 1
+            logger.error(f"❌ [{i}/{len(room_names)}] Unexpected result type for {room_name}")
+
+    # Summary
+    logger.info("\n" + "=" * 60)
+    logger.info("RECORDING FETCH TEST SUMMARY")
+    logger.info("=" * 60)
+    logger.info(f"Total rooms checked: {len(room_names)}")
+    logger.info(f"✅ Recordings found: {success_count}")
+    logger.info(f"ℹ️  No recordings: {not_found_count}")
+    logger.info(f"❌ Failed: {failed_count}")
+    logger.info(f"Success rate: {(success_count / len(room_names) * 100):.2f}%")
+    logger.info("=" * 60)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

pyproject.toml

@@ -34,7 +34,7 @@ dependencies = [
     "pyloudnorm~=0.1.1",
     "resampy~=0.4.3",
     "soxr~=0.5.0",
-    "openai>=1.74.0,<=1.99.1",
+    "openai>=1.74.0,<3",
     # Pinning numba to resolve package dependencies
     "numba==0.61.2",
     "wait_for2>=0.4.1; python_version<'3.12'",
@@ -50,7 +50,7 @@ anthropic = [ "anthropic~=0.49.0" ]
 assemblyai = [ "pipecat-ai[websockets-base]" ]
 asyncai = [ "pipecat-ai[websockets-base]" ]
 aws = [ "aioboto3~=15.0.0", "pipecat-ai[websockets-base]" ]
-aws-nova-sonic = [ "aws_sdk_bedrock_runtime~=0.0.2; python_version>='3.12'" ]
+aws-nova-sonic = [ "aws_sdk_bedrock_runtime~=0.1.0; python_version>='3.12'" ]
 azure = [ "azure-cognitiveservices-speech~=1.42.0"]
 cartesia = [ "cartesia~=2.0.3", "pipecat-ai[websockets-base]" ]
 cerebras = []
@@ -62,11 +62,12 @@ fal = [ "fal-client~=0.5.9" ]
 fireworks = []
 fish = [ "ormsgpack~=1.7.0", "pipecat-ai[websockets-base]" ]
 gladia = [ "pipecat-ai[websockets-base]" ]
-google = [ "google-cloud-speech~=2.32.0", "google-cloud-texttospeech~=2.26.0", "google-genai~=1.24.0", "pipecat-ai[websockets-base]" ]
+google = [ "google-cloud-speech>=2.33.0,<3", "google-cloud-texttospeech>=2.31.0,<3", "google-genai>=1.41.0,<2", "pipecat-ai[websockets-base]" ]
 grok = []
 groq = [ "groq~=0.23.0" ]
 gstreamer = [ "pygobject~=3.50.0" ]
 heygen = [ "livekit>=1.0.13", "pipecat-ai[websockets-base]" ]
+hume = [ "hume>=0.11.2" ]
 inworld = []
 krisp = [ "pipecat-ai-krisp~=0.4.0" ]
 koala = [ "pvkoala~=2.0.3" ]
@@ -83,7 +84,7 @@ nim = []
 neuphonic = [ "pipecat-ai[websockets-base]" ]
 noisereduce = [ "noisereduce~=3.0.3" ]
 openai = [ "pipecat-ai[websockets-base]" ]
-openpipe = [ "openpipe~=4.50.0" ]
+openpipe = [ "openpipe>=4.50.0,<6" ]
 openrouter = []
 perplexity = []
 playht = [ "pipecat-ai[websockets-base]" ]
@@ -101,7 +102,7 @@ silero = [ "onnxruntime>=1.20.1,<2" ]
 simli = [ "simli-ai~=0.1.10"]
 soniox = [ "pipecat-ai[websockets-base]" ]
 soundfile = [ "soundfile~=0.13.0" ]
-speechmatics = [ "speechmatics-rt>=0.4.0" ]
+speechmatics = [ "speechmatics-rt>=0.5.0" ]
 strands = [ "strands-agents>=1.9.1,<2" ]
 tavus=[]
 together = []

scripts/evals/eval.py

@@ -34,7 +34,8 @@ from pipecat.frames.frames import EndTaskFrame, LLMRunFrame, OutputImageRawFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.processors.audio.audio_buffer_processor import AudioBufferProcessor
 from pipecat.processors.frame_processor import FrameDirection
 from pipecat.runner.types import RunnerArguments
@@ -283,8 +284,8 @@ async def run_eval_pipeline(
         },
     ]
 
-    context = OpenAILLMContext(messages, tools)
-    context_aggregator = llm.create_context_aggregator(context)
+    context = LLMContext(messages, tools)
+    context_aggregator = LLMContextAggregatorPair(context)
 
     audio_buffer = AudioBufferProcessor()
 

scripts/evals/run-release-evals.py

@@ -67,6 +67,7 @@ TESTS_07 = [
     ("07ac-interruptible-asyncai-http.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     ("07b-interruptible-langchain.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     ("07c-interruptible-deepgram.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
+    ("07c-interruptible-deepgram-flux.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     ("07d-interruptible-elevenlabs.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     (
         "07d-interruptible-elevenlabs-http.py",
@@ -74,8 +75,6 @@ TESTS_07 = [
         EVAL_SIMPLE_MATH,
         BOT_SPEAKS_FIRST,
     ),
-    ("07e-interruptible-playht.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
-    ("07e-interruptible-playht-http.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     ("07f-interruptible-azure.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     ("07g-interruptible-openai.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     ("07h-interruptible-openpipe.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
@@ -102,6 +101,7 @@ TESTS_07 = [
     ("07w-interruptible-fal.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     ("07y-interruptible-minimax.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     ("07z-interruptible-sarvam.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
+    ("07ae-interruptible-hume.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     # Needs a local XTTS docker instance running.
     # ("07i-interruptible-xtts.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     # Needs a Krisp license.
@@ -136,6 +136,7 @@ TESTS_14 = [
     ("14r-function-calling-aws.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     ("14v-function-calling-openai.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     ("14w-function-calling-mistral.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
+    ("14x-function-calling-openpipe.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     # Currently not working.
     # ("14c-function-calling-together.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     # ("14l-function-calling-deepseek.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
@@ -147,7 +148,10 @@ TESTS_15 = [
 ]
 
 TESTS_19 = [
+    ("19-openai-realtime.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     ("19-openai-realtime-beta.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
+    # OpenAI Realtime not released on Azure yet
+    # ("19a-azure-realtime.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     ("19a-azure-realtime-beta.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     ("19b-openai-realtime-text.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
     ("19b-openai-realtime-beta-text.py", PROMPT_WEATHER, EVAL_WEATHER, BOT_SPEAKS_FIRST),
@@ -160,18 +164,18 @@ TESTS_21 = [
 TESTS_26 = [
     ("26-gemini-multimodal-live.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     (
-        "26a-gemini-multimodal-live-transcription.py",
+        "26a-gemini-live-transcription.py",
         PROMPT_SIMPLE_MATH,
         EVAL_SIMPLE_MATH,
         BOT_SPEAKS_FIRST,
     ),
     (
-        "26b-gemini-multimodal-live-function-calling.py",
+        "26b-gemini-live-function-calling.py",
         PROMPT_WEATHER,
         EVAL_WEATHER,
         BOT_SPEAKS_FIRST,
     ),
-    ("26c-gemini-multimodal-live-video.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
+    ("26c-gemini-live-video.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
     (
         "26e-gemini-multimodal-google-search.py",
         PROMPT_ONLINE_SEARCH,
@@ -179,7 +183,13 @@ TESTS_26 = [
         BOT_SPEAKS_FIRST,
     ),
     # Currently not working.
-    # ("26d-gemini-multimodal-live-text.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
+    # ("26d-gemini-live-text.py", PROMPT_SIMPLE_MATH, EVAL_SIMPLE_MATH, BOT_SPEAKS_FIRST),
+    (
+        "26h-gemini-live-vertex-function-calling.py",
+        PROMPT_WEATHER,
+        EVAL_WEATHER,
+        BOT_SPEAKS_FIRST,
+    ),
 ]
 
 TESTS_27 = [

src/pipecat/adapters/services/gemini_adapter.py

@@ -87,9 +87,11 @@ class GeminiLLMAdapter(BaseLLMAdapter[GeminiLLMInvocationParams]):
             Includes both converted standard tools and any custom Gemini-specific tools.
         """
         functions_schema = tools_schema.standard_tools
-        formatted_standard_tools = [
-            {"function_declarations": [func.to_default_dict() for func in functions_schema]}
-        ]
+        formatted_standard_tools = (
+            [{"function_declarations": [func.to_default_dict() for func in functions_schema]}]
+            if functions_schema
+            else []
+        )
         custom_gemini_tools = []
         if tools_schema.custom_tools:
             custom_gemini_tools = tools_schema.custom_tools.get(AdapterType.GEMINI, [])

src/pipecat/audio/filters/krisp_viva_filter.py

@@ -0,0 +1,193 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Krisp noise reduction audio filter for Pipecat.
+
+This module provides an audio filter implementation using Krisp VIVA SDK.
+"""
+
+import os
+
+import numpy as np
+from loguru import logger
+
+from pipecat.audio.filters.base_audio_filter import BaseAudioFilter
+from pipecat.frames.frames import FilterControlFrame, FilterEnableFrame
+
+try:
+    import krisp_audio
+except ModuleNotFoundError as e:
+    logger.error(f"Exception: {e}")
+    logger.error("In order to use the Krisp filter, you need to install krisp_audio.")
+    raise Exception(f"Missing module: {e}")
+
+
+def _log_callback(log_message, log_level):
+    logger.info(f"[{log_level}] {log_message}")
+
+
+class KrispVivaFilter(BaseAudioFilter):
+    """Audio filter using the Krisp VIVA SDK.
+
+    Provides real-time noise reduction for audio streams using Krisp's
+    proprietary noise suppression algorithms. This filter requires a
+    valid Krisp model file to operate.
+
+    Supported sample rates:
+        - 8000 Hz
+        - 16000 Hz
+        - 24000 Hz
+        - 32000 Hz
+        - 44100 Hz
+        - 48000 Hz
+    """
+
+    # Initialize Krisp Audio SDK globally
+    krisp_audio.globalInit("", _log_callback, krisp_audio.LogLevel.Off)
+    SDK_VERSION = krisp_audio.getVersion()
+    logger.debug(
+        f"Krisp Audio Python SDK Version: {SDK_VERSION.major}."
+        f"{SDK_VERSION.minor}.{SDK_VERSION.patch}"
+    )
+
+    SAMPLE_RATES = {
+        8000: krisp_audio.SamplingRate.Sr8000Hz,
+        16000: krisp_audio.SamplingRate.Sr16000Hz,
+        24000: krisp_audio.SamplingRate.Sr24000Hz,
+        32000: krisp_audio.SamplingRate.Sr32000Hz,
+        44100: krisp_audio.SamplingRate.Sr44100Hz,
+        48000: krisp_audio.SamplingRate.Sr48000Hz,
+    }
+
+    FRAME_SIZE_MS = 10  # Krisp requires audio frames of 10ms duration for processing.
+
+    def __init__(self, model_path: str = None, noise_suppression_level: int = 100) -> None:
+        """Initialize the Krisp noise reduction filter.
+
+        Args:
+            model_path: Path to the Krisp model file (.kef extension).
+                If None, uses KRISP_VIVA_MODEL_PATH environment variable.
+            noise_suppression_level: Noise suppression level.
+
+        Raises:
+            ValueError: If model_path is not provided and KRISP_VIVA_MODEL_PATH is not set.
+            Exception: If model file doesn't have .kef extension.
+            FileNotFoundError: If model file doesn't exist.
+        """
+        super().__init__()
+
+        # Set model path, checking environment if not specified
+        self._model_path = model_path or os.getenv("KRISP_VIVA_MODEL_PATH")
+        if not self._model_path:
+            logger.error("Model path is not provided and KRISP_VIVA_MODEL_PATH is not set.")
+            raise ValueError("Model path for KrispAudioProcessor must be provided.")
+
+        if not self._model_path.endswith(".kef"):
+            raise Exception("Model is expected with .kef extension")
+
+        if not os.path.isfile(self._model_path):
+            raise FileNotFoundError(f"Model file not found: {self._model_path}")
+
+        self._filtering = True
+        self._session = None
+        self._samples_per_frame = None
+        self._noise_suppression_level = noise_suppression_level
+
+        # Audio buffer to accumulate samples for complete frames
+        self._audio_buffer = bytearray()
+
+    def _int_to_sample_rate(self, sample_rate):
+        """Convert integer sample rate to krisp_audio SamplingRate enum.
+
+        Args:
+            sample_rate: Sample rate as integer
+
+        Returns:
+            krisp_audio.SamplingRate enum value
+
+        Raises:
+            ValueError: If sample rate is not supported
+        """
+        if sample_rate not in self.SAMPLE_RATES:
+            raise ValueError("Unsupported sample rate")
+        return self.SAMPLE_RATES[sample_rate]
+
+    async def start(self, sample_rate: int):
+        """Initialize the Krisp processor with the transport's sample rate.
+
+        Args:
+            sample_rate: The sample rate of the input transport in Hz.
+        """
+        model_info = krisp_audio.ModelInfo()
+        model_info.path = self._model_path
+
+        nc_cfg = krisp_audio.NcSessionConfig()
+        nc_cfg.inputSampleRate = self._int_to_sample_rate(sample_rate)
+        nc_cfg.inputFrameDuration = krisp_audio.FrameDuration.Fd10ms
+        nc_cfg.outputSampleRate = nc_cfg.inputSampleRate
+        nc_cfg.modelInfo = model_info
+
+        self._samples_per_frame = int((sample_rate * self.FRAME_SIZE_MS) / 1000)
+        self._session = krisp_audio.NcInt16.create(nc_cfg)
+
+    async def stop(self):
+        """Clean up the Krisp processor when stopping."""
+        self._session = None
+
+    async def process_frame(self, frame: FilterControlFrame):
+        """Process control frames to enable/disable filtering.
+
+        Args:
+            frame: The control frame containing filter commands.
+        """
+        if isinstance(frame, FilterEnableFrame):
+            self._filtering = frame.enable
+
+    async def filter(self, audio: bytes) -> bytes:
+        """Apply Krisp noise reduction to audio data.
+
+        Args:
+            audio: Raw audio data as bytes to be filtered.
+
+        Returns:
+            Noise-reduced audio data as bytes.
+        """
+        if not self._filtering:
+            return audio
+
+        # Add incoming audio to our buffer
+        self._audio_buffer.extend(audio)
+
+        # Calculate how many complete frames we can process
+        total_samples = len(self._audio_buffer) // 2  # 2 bytes per int16 sample
+        num_complete_frames = total_samples // self._samples_per_frame
+
+        if num_complete_frames == 0:
+            # Not enough samples for a complete frame yet, return empty
+            return b""
+
+        # Calculate how many bytes we need for complete frames
+        complete_samples_count = num_complete_frames * self._samples_per_frame
+        bytes_to_process = complete_samples_count * 2  # 2 bytes per sample
+
+        # Extract the bytes we can process
+        audio_to_process = bytes(self._audio_buffer[:bytes_to_process])
+
+        # Remove processed bytes from buffer, keep the remainder
+        self._audio_buffer = self._audio_buffer[bytes_to_process:]
+
+        # Process the complete frames
+        samples = np.frombuffer(audio_to_process, dtype=np.int16)
+        frames = samples.reshape(-1, self._samples_per_frame)
+        processed_samples = np.empty_like(samples)
+
+        for i, frame in enumerate(frames):
+            cleaned_frame = self._session.process(frame, self._noise_suppression_level)
+            processed_samples[i * self._samples_per_frame : (i + 1) * self._samples_per_frame] = (
+                cleaned_frame
+            )
+
+        return processed_samples.tobytes()

src/pipecat/audio/turn/base_turn_analyzer.py

@@ -14,6 +14,8 @@ from abc import ABC, abstractmethod
 from enum import Enum
 from typing import Optional, Tuple
 
+from pydantic import BaseModel
+
 from pipecat.metrics.metrics import MetricsData
 
 
@@ -29,6 +31,12 @@ class EndOfTurnState(Enum):
     INCOMPLETE = 2
 
 
+class BaseTurnParams(BaseModel):
+    """Base class for turn analyzer parameters."""
+
+    pass
+
+
 class BaseTurnAnalyzer(ABC):
     """Abstract base class for analyzing user end of turn.
 
@@ -78,7 +86,7 @@ class BaseTurnAnalyzer(ABC):
 
     @property
     @abstractmethod
-    def params(self):
+    def params(self) -> BaseTurnParams:
         """Get the current turn analyzer parameters.
 
         Returns:

src/pipecat/audio/turn/smart_turn/base_smart_turn.py

@@ -11,15 +11,17 @@ machine learning models to determine when a user has finished speaking, going
 beyond simple silence-based detection.
 """
 
+import asyncio
 import time
 from abc import abstractmethod
+from concurrent.futures import ThreadPoolExecutor
 from typing import Any, Dict, Optional, Tuple
 
 import numpy as np
 from loguru import logger
 from pydantic import BaseModel
 
-from pipecat.audio.turn.base_turn_analyzer import BaseTurnAnalyzer, EndOfTurnState
+from pipecat.audio.turn.base_turn_analyzer import BaseTurnAnalyzer, BaseTurnParams, EndOfTurnState
 from pipecat.metrics.metrics import MetricsData, SmartTurnMetricsData
 
 # Default timing parameters
@@ -29,7 +31,7 @@ MAX_DURATION_SECONDS = 8  # Max allowed segment duration
 USE_ONLY_LAST_VAD_SEGMENT = True
 
 
-class SmartTurnParams(BaseModel):
+class SmartTurnParams(BaseTurnParams):
     """Configuration parameters for smart turn analysis.
 
     Parameters:
@@ -77,6 +79,9 @@ class BaseSmartTurn(BaseTurnAnalyzer):
         self._speech_triggered = False
         self._silence_ms = 0
         self._speech_start_time = 0
+        # Thread executor that will run the model. We only need one thread per
+        # analyzer because one analyzer just handles one audio stream.
+        self._executor = ThreadPoolExecutor(max_workers=1)
 
     @property
     def speech_triggered(self) -> bool:
@@ -151,7 +156,10 @@ class BaseSmartTurn(BaseTurnAnalyzer):
             Tuple containing the end-of-turn state and optional metrics data
             from the ML model analysis.
         """
-        state, result = await self._process_speech_segment(self._audio_buffer)
+        loop = asyncio.get_running_loop()
+        state, result = await loop.run_in_executor(
+            self._executor, self._process_speech_segment, self._audio_buffer
+        )
         if state == EndOfTurnState.COMPLETE or USE_ONLY_LAST_VAD_SEGMENT:
             self._clear(state)
         logger.debug(f"End of Turn result: {state}")
@@ -169,9 +177,7 @@ class BaseSmartTurn(BaseTurnAnalyzer):
         self._speech_start_time = 0
         self._silence_ms = 0
 
-    async def _process_speech_segment(
-        self, audio_buffer
-    ) -> Tuple[EndOfTurnState, Optional[MetricsData]]:
+    def _process_speech_segment(self, audio_buffer) -> Tuple[EndOfTurnState, Optional[MetricsData]]:
         """Process accumulated audio segment using ML model."""
         state = EndOfTurnState.INCOMPLETE
 
@@ -203,7 +209,7 @@ class BaseSmartTurn(BaseTurnAnalyzer):
         if len(segment_audio) > 0:
             start_time = time.perf_counter()
             try:
-                result = await self._predict_endpoint(segment_audio)
+                result = self._predict_endpoint(segment_audio)
                 state = (
                     EndOfTurnState.COMPLETE
                     if result["prediction"] == 1
@@ -249,6 +255,6 @@ class BaseSmartTurn(BaseTurnAnalyzer):
         return state, result_data
 
     @abstractmethod
-    async def _predict_endpoint(self, audio_array: np.ndarray) -> Dict[str, Any]:
+    def _predict_endpoint(self, audio_array: np.ndarray) -> Dict[str, Any]:
         """Predict end-of-turn using ML model from audio data."""
         pass

src/pipecat/audio/turn/smart_turn/http_smart_turn.py

@@ -104,11 +104,15 @@ class HttpSmartTurnAnalyzer(BaseSmartTurn):
             logger.error(f"Failed to send raw request to Daily Smart Turn: {e}")
             raise Exception("Failed to send raw request to Daily Smart Turn.")
 
-    async def _predict_endpoint(self, audio_array: np.ndarray) -> Dict[str, Any]:
+    def _predict_endpoint(self, audio_array: np.ndarray) -> Dict[str, Any]:
         """Predict end-of-turn using remote HTTP ML service."""
         try:
             serialized_array = self._serialize_array(audio_array)
-            return await self._send_raw_request(serialized_array)
+            loop = asyncio.get_running_loop()
+            future = asyncio.run_coroutine_threadsafe(
+                self._send_raw_request(serialized_array), loop
+            )
+            return future.result()
         except Exception as e:
             logger.error(f"Smart turn prediction failed: {str(e)}")
             # Return an incomplete prediction when a failure occurs

src/pipecat/audio/turn/smart_turn/local_smart_turn.py

@@ -64,7 +64,7 @@ class LocalSmartTurnAnalyzer(BaseSmartTurn):
         self._turn_model.eval()
         logger.debug("Loaded Local Smart Turn")
 
-    async def _predict_endpoint(self, audio_array: np.ndarray) -> Dict[str, Any]:
+    def _predict_endpoint(self, audio_array: np.ndarray) -> Dict[str, Any]:
         """Predict end-of-turn using local PyTorch model."""
         inputs = self._turn_processor(
             audio_array,

src/pipecat/audio/turn/smart_turn/local_smart_turn_v2.py

@@ -73,7 +73,7 @@ class LocalSmartTurnAnalyzerV2(BaseSmartTurn):
         self._turn_model.eval()
         logger.debug("Loaded Local Smart Turn v2")
 
-    async def _predict_endpoint(self, audio_array: np.ndarray) -> Dict[str, Any]:
+    def _predict_endpoint(self, audio_array: np.ndarray) -> Dict[str, Any]:
         """Predict end-of-turn using local PyTorch model."""
         inputs = self._turn_processor(
             audio_array,

src/pipecat/audio/turn/smart_turn/local_smart_turn_v3.py

@@ -77,7 +77,7 @@ class LocalSmartTurnAnalyzerV3(BaseSmartTurn):
 
         logger.debug("Loaded Local Smart Turn v3")
 
-    async def _predict_endpoint(self, audio_array: np.ndarray) -> Dict[str, Any]:
+    def _predict_endpoint(self, audio_array: np.ndarray) -> Dict[str, Any]:
         """Predict end-of-turn using local ONNX model."""
 
         def truncate_audio_to_last_n_seconds(audio_array, n_seconds=8, sample_rate=16000):

src/pipecat/audio/vad/vad_analyzer.py

@@ -11,7 +11,9 @@ data structures for voice activity detection in audio streams. Includes state
 management, parameter configuration, and audio analysis framework.
 """
 
+import asyncio
 from abc import ABC, abstractmethod
+from concurrent.futures import ThreadPoolExecutor
 from enum import Enum
 from typing import Optional
 
@@ -84,6 +86,10 @@ class VADAnalyzer(ABC):
         self._smoothing_factor = 0.2
         self._prev_volume = 0
 
+        # Thread executor that will run the model. We only need one thread per
+        # analyzer because one analyzer just handles one audio stream.
+        self._executor = ThreadPoolExecutor(max_workers=1)
+
     @property
     def sample_rate(self) -> int:
         """Get the current sample rate.
@@ -165,7 +171,7 @@ class VADAnalyzer(ABC):
         volume = calculate_audio_volume(audio, self.sample_rate)
         return exp_smoothing(volume, self._prev_volume, self._smoothing_factor)
 
-    def analyze_audio(self, buffer) -> VADState:
+    async def analyze_audio(self, buffer: bytes) -> VADState:
         """Analyze audio buffer and return current VAD state.
 
         Processes incoming audio data, maintains internal state, and determines
@@ -177,6 +183,12 @@ class VADAnalyzer(ABC):
         Returns:
             Current VAD state after processing the buffer.
         """
+        loop = asyncio.get_running_loop()
+        state = await loop.run_in_executor(self._executor, self._run_analyzer, buffer)
+        return state
+
+    def _run_analyzer(self, buffer: bytes) -> VADState:
+        """Analyze audio buffer and return current VAD state."""
         self._vad_buffer += buffer
 
         num_required_bytes = self._vad_frames_num_bytes

src/pipecat/frames/frames.py

@@ -672,7 +672,7 @@ class TTSSpeakFrame(DataFrame):
 
 
 @dataclass
-class TransportMessageFrame(DataFrame):
+class OutputTransportMessageFrame(DataFrame):
     """Frame containing transport-specific message data.
 
     Parameters:
@@ -685,6 +685,32 @@ class TransportMessageFrame(DataFrame):
         return f"{self.name}(message: {self.message})"
 
 
+@dataclass
+class TransportMessageFrame(OutputTransportMessageFrame):
+    """Frame containing transport-specific message data.
+
+    .. deprecated:: 0.0.87
+        This frame is deprecated and will be removed in a future version.
+        Instead, use `OutputTransportMessageFrame`.
+
+    Parameters:
+        message: The transport message payload.
+    """
+
+    def __post_init__(self):
+        super().__post_init__()
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "TransportMessageFrame is deprecated and will be removed in a future version. "
+                "Instead, use OutputTransportMessageFrame.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
+
 @dataclass
 class DTMFFrame:
     """Base class for DTMF (Dual-Tone Multi-Frequency) keypad frames.
@@ -1092,8 +1118,8 @@ class STTMuteFrame(SystemFrame):
 
 
 @dataclass
-class TransportMessageUrgentFrame(SystemFrame):
-    """Frame for urgent transport messages that need immediate processing.
+class InputTransportMessageFrame(SystemFrame):
+    """Frame for transport messages received from external sources.
 
     Parameters:
         message: The urgent transport message payload.
@@ -1106,20 +1132,69 @@ class TransportMessageUrgentFrame(SystemFrame):
 
 
 @dataclass
-class InputTransportMessageUrgentFrame(TransportMessageUrgentFrame):
+class InputTransportMessageUrgentFrame(InputTransportMessageFrame):
     """Frame for transport messages received from external sources.
 
-    This frame wraps incoming transport messages to distinguish them from outgoing
-    urgent transport messages (TransportMessageUrgentFrame), preventing infinite
-    message loops in the transport layer. It inherits the message payload from
-    TransportMessageFrame while marking the message as having been received
-    rather than generated locally.
+    .. deprecated:: 0.0.87
+        This frame is deprecated and will be removed in a future version.
+        Instead, use `InputTransportMessageFrame`.
 
-    Used by transport implementations to properly handle bidirectional message
-    flow without creating feedback loops.
+    Parameters:
+        message: The urgent transport message payload.
     """
 
-    pass
+    def __post_init__(self):
+        super().__post_init__()
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "InputTransportMessageUrgentFrame is deprecated and will be removed in a future version. "
+                "Instead, use InputTransportMessageFrame.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
+
+@dataclass
+class OutputTransportMessageUrgentFrame(SystemFrame):
+    """Frame for urgent transport messages that need to be sent immediately.
+
+    Parameters:
+        message: The urgent transport message payload.
+    """
+
+    message: Any
+
+    def __str__(self):
+        return f"{self.name}(message: {self.message})"
+
+
+@dataclass
+class TransportMessageUrgentFrame(OutputTransportMessageUrgentFrame):
+    """Frame for urgent transport messages that need to be sent immediately.
+
+    .. deprecated:: 0.0.87
+        This frame is deprecated and will be removed in a future version.
+        Instead, use `OutputTransportMessageUrgentFrame`.
+
+    Parameters:
+        message: The urgent transport message payload.
+    """
+
+    def __post_init__(self):
+        super().__post_init__()
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "TransportMessageUrgentFrame is deprecated and will be removed in a future version. "
+                "Instead, use OutputTransportMessageFrame.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
 
 
 @dataclass

src/pipecat/pipeline/runner.py

@@ -70,11 +70,15 @@ class PipelineRunner(BaseObject):
         """
         logger.debug(f"Runner {self} started running {task}")
         self._tasks[task.name] = task
-        params = PipelineTaskParams(loop=self._loop)
+
+        # PipelineTask handles asyncio.CancelledError to shutdown the pipeline
+        # properly and re-raises it in case there's more cleanup to do.
         try:
+            params = PipelineTaskParams(loop=self._loop)
             await task.run(params)
         except asyncio.CancelledError:
-            await self._cancel()
+            pass
+
         del self._tasks[task.name]
 
         # Cleanup base object.

src/pipecat/pipeline/task.py

@@ -13,8 +13,7 @@ including heartbeats, idle detection, and observer integration.
 
 import asyncio
 import time
-from collections import deque
-from typing import Any, AsyncIterable, Deque, Dict, Iterable, List, Optional, Tuple, Type
+from typing import Any, AsyncIterable, Dict, Iterable, List, Optional, Tuple, Type
 
 from loguru import logger
 from pydantic import BaseModel, ConfigDict, Field
@@ -31,7 +30,6 @@ from pipecat.frames.frames import (
     ErrorFrame,
     Frame,
     HeartbeatFrame,
-    InputAudioRawFrame,
     InterruptionFrame,
     InterruptionTaskFrame,
     MetricsFrame,
@@ -132,12 +130,16 @@ class PipelineTask(BasePipelineTask):
 
     - on_pipeline_finished: Called after the pipeline has reached any terminal state.
           This includes:
+
               - StopFrame: pipeline was stopped (processors keep connections open)
               - EndFrame: pipeline ended normally
               - CancelFrame: pipeline was cancelled
+
           Use this event for cleanup, logging, or post-processing tasks. Users can inspect
           the frame if they need to handle specific cases.
 
+    - on_pipeline_error: Called when an error occurs with ErrorFrame
+
     Example::
 
         @task.event_handler("on_frame_reached_upstream")
@@ -148,9 +150,17 @@ class PipelineTask(BasePipelineTask):
         async def on_pipeline_idle_timeout(task):
             ...
 
+        @task.event_handler("on_pipeline_started")
+        async def on_pipeline_started(task, frame):
+            ...
+
         @task.event_handler("on_pipeline_finished")
         async def on_pipeline_finished(task, frame):
             ...
+
+        @task.event_handler("on_pipeline_error")
+        async def on_pipeline_error(task, frame):
+            ...
     """
 
     def __init__(
@@ -259,6 +269,9 @@ class PipelineTask(BasePipelineTask):
         # StopFrame) has been received at the end of the pipeline.
         self._pipeline_end_event = asyncio.Event()
 
+        # This event is set when the pipeline truly finishes.
+        self._pipeline_finished_event = asyncio.Event()
+
         # This is the final pipeline. It is composed of a source processor,
         # followed by the user pipeline, and ending with a sink processor. The
         # source allows us to receive and react to upstream frames, and the sink
@@ -288,6 +301,7 @@ class PipelineTask(BasePipelineTask):
         self._register_event_handler("on_pipeline_ended")
         self._register_event_handler("on_pipeline_cancelled")
         self._register_event_handler("on_pipeline_finished")
+        self._register_event_handler("on_pipeline_error")
 
     @property
     def params(self) -> PipelineParams:
@@ -390,12 +404,9 @@ class PipelineTask(BasePipelineTask):
         await self.queue_frame(EndFrame())
 
     async def cancel(self):
-        """Immediately stop the running pipeline.
-
-        Cancels all running tasks and stops frame processing without
-        waiting for completion.
-        """
-        await self._cancel()
+        """Request the running pipeline to cancel."""
+        if not self._finished:
+            await self._cancel()
 
     async def run(self, params: PipelineTaskParams):
         """Start and manage the pipeline execution until completion or cancellation.
@@ -405,51 +416,38 @@ class PipelineTask(BasePipelineTask):
         """
         if self.has_finished():
             return
-        cleanup_pipeline = True
+
+        # Setup processors.
+        await self._setup(params)
+
+        # Create all main tasks and wait for the main push task. This is the
+        # task that pushes frames to the very beginning of our pipeline (i.e. to
+        # our controlled source processor).
+        await self._create_tasks()
+
         try:
-            # Setup processors.
-            await self._setup(params)
-
-            # Create all main tasks and wait of the main push task. This is the
-            # task that pushes frames to the very beginning of our pipeline (our
-            # controlled source processor).
-            push_task = await self._create_tasks()
-            await push_task
-
-            # We have already cleaned up the pipeline inside the task.
-            cleanup_pipeline = False
-
-            # Pipeline has finished nicely.
-            self._finished = True
+            # Wait for pipeline to finish.
+            await self._wait_for_pipeline_finished()
         except asyncio.CancelledError:
-            # Raise exception back to the pipeline runner so it can cancel this
-            # task properly.
+            logger.debug(f"Pipeline task {self} got cancelled from outside...")
+            # We have been cancelled from outside, let's just cancel everything.
+            await self._cancel()
+            # Wait again for pipeline to finish. This time we have really
+            # cancelled, so it should really finish.
+            await self._wait_for_pipeline_finished()
+            # Re-raise in case there's more cleanup to do.
             raise
         finally:
             # We can reach this point for different reasons:
             #
-            # 1. The task has finished properly (e.g. `EndFrame`).
-            # 2. By calling `PipelineTask.cancel()`.
-            # 3. By asyncio task cancellation.
-            #
-            # Case (1) will execute the code below without issues because
-            # `self._finished` is true.
-            #
-            # Case (2) will execute the code below without issues because
-            # `self._cancelled` is true.
-            #
-            # Case (3) will raise the exception above (because we are cancelling
-            # the asyncio task). This will be then captured by the
-            # `PipelineRunner` which will call `PipelineTask.cancel()` and
-            # therefore becoming case (2).
-            if self._finished or self._cancelled:
-                logger.debug(f"Pipeline task {self} is finishing cleanup...")
-                await self._cancel_tasks()
-                await self._cleanup(cleanup_pipeline)
-                if self._check_dangling_tasks:
-                    self._print_dangling_tasks()
-                self._finished = True
-                logger.debug(f"Pipeline task {self} has finished")
+            # 1. The pipeline task has finished (try case).
+            # 2. By an asyncio task cancellation (except case).
+            logger.debug(f"Pipeline task {self} is finishing...")
+            await self._cancel_tasks()
+            if self._check_dangling_tasks:
+                self._print_dangling_tasks()
+            self._finished = True
+            logger.debug(f"Pipeline task {self} has finished")
 
     async def queue_frame(self, frame: Frame):
         """Queue a single frame to be pushed down the pipeline.
@@ -477,19 +475,7 @@ class PipelineTask(BasePipelineTask):
         if not self._cancelled:
             logger.debug(f"Cancelling pipeline task {self}")
             self._cancelled = True
-            cancel_frame = CancelFrame()
-            # Make sure everything is cleaned up downstream. This is sent
-            # out-of-band from the main streaming task which is what we want since
-            # we want to cancel right away.
-            await self._pipeline.queue_frame(cancel_frame)
-            # Wait for CancelFrame to make it through the pipeline.
-            await self._wait_for_pipeline_end(cancel_frame)
-            # Only cancel the push task, we don't want to be able to process any
-            # other frame after cancel. Everything else will be cancelled in
-            # run().
-            if self._process_push_task:
-                await self._task_manager.cancel_task(self._process_push_task)
-                self._process_push_task = None
+            await self.queue_frame(CancelFrame())
 
     async def _create_tasks(self):
         """Create and start all pipeline processing tasks."""
@@ -591,6 +577,17 @@ class PipelineTask(BasePipelineTask):
 
         self._pipeline_end_event.clear()
 
+        # We are really done.
+        self._pipeline_finished_event.set()
+
+    async def _wait_for_pipeline_finished(self):
+        await self._pipeline_finished_event.wait()
+        self._pipeline_finished_event.clear()
+        # Make sure we wait for the main task to complete.
+        if self._process_push_task:
+            await self._process_push_task
+            self._process_push_task = None
+
     async def _setup(self, params: PipelineTaskParams):
         """Set up the pipeline task and all processors."""
         mgr_params = TaskManagerParams(loop=params.loop)
@@ -693,12 +690,11 @@ class PipelineTask(BasePipelineTask):
             logger.debug(f"{self}: received interruption task frame {frame}")
             await self._pipeline.queue_frame(InterruptionFrame())
         elif isinstance(frame, ErrorFrame):
+            await self._call_event_handler("on_pipeline_error", frame)
             if frame.fatal:
                 logger.error(f"A fatal error occurred: {frame}")
                 # Cancel all tasks downstream.
                 await self.queue_frame(CancelFrame())
-                # Tell the task we should stop.
-                await self.queue_frame(StopTaskFrame())
             else:
                 logger.warning(f"{self}: Something went wrong: {frame}")
 

src/pipecat/processors/aggregators/llm_response_universal.py

@@ -13,6 +13,7 @@ LLM processing, and text-to-speech components in conversational AI pipelines.
 
 import asyncio
 import json
+from abc import abstractmethod
 from typing import Any, Dict, List, Literal, Optional, Set
 
 from loguru import logger
@@ -169,6 +170,11 @@ class LLMContextAggregator(FrameProcessor):
         """Reset the aggregation state."""
         self._aggregation = ""
 
+    @abstractmethod
+    async def push_aggregation(self):
+        """Push the current aggregation downstream."""
+        pass
+
 
 class LLMUserAggregator(LLMContextAggregator):
     """User LLM aggregator that processes speech-to-text transcriptions.
@@ -301,7 +307,7 @@ class LLMUserAggregator(LLMContextAggregator):
         frame = LLMContextFrame(self._context)
         await self.push_frame(frame)
 
-    async def _push_aggregation(self):
+    async def push_aggregation(self):
         """Push the current aggregation based on interruption strategies and conditions."""
         if len(self._aggregation) > 0:
             if self.interruption_strategies and self._bot_speaking:
@@ -392,7 +398,7 @@ class LLMUserAggregator(LLMContextAggregator):
         # pushing the aggregation as we will probably get a final transcription.
         if len(self._aggregation) > 0:
             if not self._seen_interim_results:
-                await self._push_aggregation()
+                await self.push_aggregation()
         # Handles the case where both the user and the bot are not speaking,
         # and the bot was previously speaking before the user interruption.
         # So in this case we are resetting the aggregation timer
@@ -471,7 +477,7 @@ class LLMUserAggregator(LLMContextAggregator):
                 await self._maybe_emulate_user_speaking()
             except asyncio.TimeoutError:
                 if not self._user_speaking:
-                    await self._push_aggregation()
+                    await self.push_aggregation()
 
                 # If we are emulating VAD we still need to send the user stopped
                 # speaking frame.
@@ -607,12 +613,12 @@ class LLMAssistantAggregator(LLMContextAggregator):
         elif isinstance(frame, UserImageRawFrame) and frame.request and frame.request.tool_call_id:
             await self._handle_user_image_frame(frame)
         elif isinstance(frame, BotStoppedSpeakingFrame):
-            await self._push_aggregation()
+            await self.push_aggregation()
             await self.push_frame(frame, direction)
         else:
             await self.push_frame(frame, direction)
 
-    async def _push_aggregation(self):
+    async def push_aggregation(self):
         """Push the current assistant aggregation with timestamp."""
         if not self._aggregation:
             return
@@ -644,7 +650,7 @@ class LLMAssistantAggregator(LLMContextAggregator):
             await self.push_context_frame(FrameDirection.UPSTREAM)
 
     async def _handle_interruptions(self, frame: InterruptionFrame):
-        await self._push_aggregation()
+        await self.push_aggregation()
         self._started = 0
         await self.reset()
 
@@ -778,7 +784,7 @@ class LLMAssistantAggregator(LLMContextAggregator):
             text=frame.request.context,
         )
 
-        await self._push_aggregation()
+        await self.push_aggregation()
         await self.push_context_frame(FrameDirection.UPSTREAM)
 
     async def _handle_llm_start(self, _: LLMFullResponseStartFrame):
@@ -786,7 +792,7 @@ class LLMAssistantAggregator(LLMContextAggregator):
 
     async def _handle_llm_end(self, _: LLMFullResponseEndFrame):
         self._started -= 1
-        await self._push_aggregation()
+        await self.push_aggregation()
 
     async def _handle_text(self, frame: TextFrame):
         if not self._started:

src/pipecat/processors/aggregators/user_response.py

@@ -12,14 +12,14 @@ in conversational pipelines.
 """
 
 from pipecat.frames.frames import TextFrame
-from pipecat.processors.aggregators.llm_response import LLMUserContextAggregator
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import LLMUserAggregator
 
 
-class UserResponseAggregator(LLMUserContextAggregator):
+class UserResponseAggregator(LLMUserAggregator):
     """Aggregates user responses into TextFrame objects.
 
-    This aggregator extends LLMUserContextAggregator to specifically handle
+    This aggregator extends LLMUserAggregator to specifically handle
     user input by collecting text responses and outputting them as TextFrame
     objects when the aggregation is complete.
     """
@@ -28,9 +28,9 @@ class UserResponseAggregator(LLMUserContextAggregator):
         """Initialize the user response aggregator.
 
         Args:
-            **kwargs: Additional arguments passed to parent LLMUserContextAggregator.
+            **kwargs: Additional arguments passed to parent LLMUserAggregator.
         """
-        super().__init__(context=OpenAILLMContext(), **kwargs)
+        super().__init__(context=LLMContext(), **kwargs)
 
     async def push_aggregation(self):
         """Push the aggregated user response as a TextFrame.

src/pipecat/processors/frame_processor.py

@@ -877,6 +877,8 @@ class FrameProcessor(BaseObject):
 
         """
         while True:
+            (frame, direction, callback) = await self.__input_queue.get()
+
             if self.__should_block_system_frames and self.__input_event:
                 logger.trace(f"{self}: system frame processing paused")
                 await self.__input_event.wait()
@@ -884,8 +886,6 @@ class FrameProcessor(BaseObject):
                 self.__should_block_system_frames = False
                 logger.trace(f"{self}: system frame processing resumed")
 
-            (frame, direction, callback) = await self.__input_queue.get()
-
             if isinstance(frame, SystemFrame):
                 await self.__process_frame(frame, direction, callback)
             elif self.__process_queue:
@@ -900,6 +900,8 @@ class FrameProcessor(BaseObject):
     async def __process_frame_task_handler(self):
         """Handle non-system frames from the process queue."""
         while True:
+            (frame, direction, callback) = await self.__process_queue.get()
+
             if self.__should_block_frames and self.__process_event:
                 logger.trace(f"{self}: frame processing paused")
                 await self.__process_event.wait()
@@ -907,8 +909,6 @@ class FrameProcessor(BaseObject):
                 self.__should_block_frames = False
                 logger.trace(f"{self}: frame processing resumed")
 
-            (frame, direction, callback) = await self.__process_queue.get()
-
             await self.__process_frame(frame, direction, callback)
 
             self.__process_queue.task_done()

src/pipecat/processors/frameworks/rtvi.py

@@ -13,6 +13,7 @@ and frame observation for the RTVI protocol.
 
 import asyncio
 import base64
+import time
 from dataclasses import dataclass
 from typing import (
     Any,
@@ -29,6 +30,7 @@ from typing import (
 from loguru import logger
 from pydantic import BaseModel, Field, PrivateAttr, ValidationError
 
+from pipecat.audio.utils import calculate_audio_volume
 from pipecat.frames.frames import (
     BotStartedSpeakingFrame,
     BotStoppedSpeakingFrame,
@@ -40,6 +42,7 @@ from pipecat.frames.frames import (
     Frame,
     FunctionCallResultFrame,
     InputAudioRawFrame,
+    InputTransportMessageFrame,
     InterimTranscriptionFrame,
     LLMConfigureOutputFrame,
     LLMContextFrame,
@@ -48,10 +51,11 @@ from pipecat.frames.frames import (
     LLMMessagesAppendFrame,
     LLMTextFrame,
     MetricsFrame,
+    OutputTransportMessageUrgentFrame,
     StartFrame,
     SystemFrame,
     TranscriptionFrame,
-    TransportMessageUrgentFrame,
+    TTSAudioRawFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
     TTSTextFrame,
@@ -613,9 +617,9 @@ class RTVIAppendToContextData(BaseModel):
 
     Contains the role, content, and whether to run the message immediately.
 
-        .. deprecated:: 0.0.85
-            The RTVI message, append-to-context, has been deprecated. Use send-text
-            or custom client and server messages instead.
+    .. deprecated:: 0.0.85
+        The RTVI message, append-to-context, has been deprecated. Use send-text
+        or custom client and server messages instead.
     """
 
     role: Literal["user", "assistant"] | str
@@ -839,6 +843,36 @@ class RTVIServerMessage(BaseModel):
     data: Any
 
 
+class RTVIAudioLevelMessageData(BaseModel):
+    """Data format for sending audio levels."""
+
+    value: float
+
+
+class RTVIUserAudioLevelMessage(BaseModel):
+    """Message indicating user audio level."""
+
+    label: RTVIMessageLiteral = RTVI_MESSAGE_LABEL
+    type: Literal["user-audio-level"] = "user-audio-level"
+    data: RTVIAudioLevelMessageData
+
+
+class RTVIBotAudioLevelMessage(BaseModel):
+    """Message indicating bot audio level."""
+
+    label: RTVIMessageLiteral = RTVI_MESSAGE_LABEL
+    type: Literal["bot-audio-level"] = "bot-audio-level"
+    data: RTVIAudioLevelMessageData
+
+
+class RTVISystemLogMessage(BaseModel):
+    """Message including a system log."""
+
+    label: RTVIMessageLiteral = RTVI_MESSAGE_LABEL
+    type: Literal["system-log"] = "system-log"
+    data: RTVITextMessageData
+
+
 @dataclass
 class RTVIServerMessageFrame(SystemFrame):
     """A frame for sending server messages to the client.
@@ -858,25 +892,36 @@ class RTVIServerMessageFrame(SystemFrame):
 class RTVIObserverParams:
     """Parameters for configuring RTVI Observer behavior.
 
+    .. deprecated:: 0.0.87
+        Parameter `errors_enabled` is deprecated. Error messages are always enabled.
+
     Parameters:
         bot_llm_enabled: Indicates if the bot's LLM messages should be sent.
         bot_tts_enabled: Indicates if the bot's TTS messages should be sent.
         bot_speaking_enabled: Indicates if the bot's started/stopped speaking messages should be sent.
+        bot_audio_level_enabled: Indicates if bot's audio level messages should be sent.
         user_llm_enabled: Indicates if the user's LLM input messages should be sent.
         user_speaking_enabled: Indicates if the user's started/stopped speaking messages should be sent.
         user_transcription_enabled: Indicates if user's transcription messages should be sent.
+        user_audio_level_enabled: Indicates if user's audio level messages should be sent.
         metrics_enabled: Indicates if metrics messages should be sent.
-        errors_enabled: Indicates if errors messages should be sent.
+        system_logs_enabled: Indicates if system logs should be sent.
+        errors_enabled: [Deprecated] Indicates if errors messages should be sent.
+        audio_level_period_secs: How often audio levels should be sent if enabled.
     """
 
     bot_llm_enabled: bool = True
     bot_tts_enabled: bool = True
     bot_speaking_enabled: bool = True
+    bot_audio_level_enabled: bool = False
     user_llm_enabled: bool = True
     user_speaking_enabled: bool = True
     user_transcription_enabled: bool = True
+    user_audio_level_enabled: bool = False
     metrics_enabled: bool = True
-    errors_enabled: bool = True
+    system_logs_enabled: bool = False
+    errors_enabled: Optional[bool] = None
+    audio_level_period_secs: float = 0.15
 
 
 class RTVIObserver(BaseObserver):
@@ -892,7 +937,11 @@ class RTVIObserver(BaseObserver):
     """
 
     def __init__(
-        self, rtvi: "RTVIProcessor", *, params: Optional[RTVIObserverParams] = None, **kwargs
+        self,
+        rtvi: Optional["RTVIProcessor"] = None,
+        *,
+        params: Optional[RTVIObserverParams] = None,
+        **kwargs,
     ):
         """Initialize the RTVI observer.
 
@@ -904,9 +953,50 @@ class RTVIObserver(BaseObserver):
         super().__init__(**kwargs)
         self._rtvi = rtvi
         self._params = params or RTVIObserverParams()
-        self._bot_transcription = ""
+
         self._frames_seen = set()
-        rtvi.set_errors_enabled(self._params.errors_enabled)
+
+        self._bot_transcription = ""
+        self._last_user_audio_level = 0
+        self._last_bot_audio_level = 0
+
+        if self._params.system_logs_enabled:
+            self._system_logger_id = logger.add(self._logger_sink)
+
+        if self._params.errors_enabled is not None:
+            import warnings
+
+            with warnings.catch_warnings():
+                warnings.simplefilter("always")
+                warnings.warn(
+                    "Parameter `errors_enabled` is deprecated. Error messages are always enabled.",
+                    DeprecationWarning,
+                )
+
+    async def _logger_sink(self, message):
+        """Logger sink so we cna send system logs to RTVI clients."""
+        message = RTVISystemLogMessage(data=RTVITextMessageData(text=message))
+        await self.send_rtvi_message(message)
+
+    async def cleanup(self):
+        """Cleanup RTVI observer resources."""
+        await super().cleanup()
+        if self._params.system_logs_enabled:
+            logger.remove(self._system_logger_id)
+
+    async def send_rtvi_message(self, model: BaseModel, exclude_none: bool = True):
+        """Send an RTVI message.
+
+        By default, we push a transport frame. But this function can be
+        overriden by subclass to send RTVI messages in different ways.
+
+        Args:
+            model: The message to send.
+            exclude_none: Whether to exclude None values from the model dump.
+
+        """
+        if self._rtvi:
+            await self._rtvi.push_transport_message(model, exclude_none)
 
     async def on_push_frame(self, data: FramePushed):
         """Process a frame being pushed through the pipeline.
@@ -948,52 +1038,58 @@ class RTVIObserver(BaseObserver):
         ):
             await self._handle_context(frame)
         elif isinstance(frame, LLMFullResponseStartFrame) and self._params.bot_llm_enabled:
-            await self.push_transport_message_urgent(RTVIBotLLMStartedMessage())
+            await self.send_rtvi_message(RTVIBotLLMStartedMessage())
         elif isinstance(frame, LLMFullResponseEndFrame) and self._params.bot_llm_enabled:
-            await self.push_transport_message_urgent(RTVIBotLLMStoppedMessage())
+            await self.send_rtvi_message(RTVIBotLLMStoppedMessage())
         elif isinstance(frame, LLMTextFrame) and self._params.bot_llm_enabled:
             await self._handle_llm_text_frame(frame)
         elif isinstance(frame, TTSStartedFrame) and self._params.bot_tts_enabled:
-            await self.push_transport_message_urgent(RTVIBotTTSStartedMessage())
+            await self.send_rtvi_message(RTVIBotTTSStartedMessage())
         elif isinstance(frame, TTSStoppedFrame) and self._params.bot_tts_enabled:
-            await self.push_transport_message_urgent(RTVIBotTTSStoppedMessage())
+            await self.send_rtvi_message(RTVIBotTTSStoppedMessage())
         elif isinstance(frame, TTSTextFrame) and self._params.bot_tts_enabled:
             if isinstance(src, BaseOutputTransport):
                 message = RTVIBotTTSTextMessage(data=RTVITextMessageData(text=frame.text))
-                await self.push_transport_message_urgent(message)
+                await self.send_rtvi_message(message)
             else:
                 mark_as_seen = False
         elif isinstance(frame, MetricsFrame) and self._params.metrics_enabled:
             await self._handle_metrics(frame)
         elif isinstance(frame, RTVIServerMessageFrame):
             message = RTVIServerMessage(data=frame.data)
-            await self.push_transport_message_urgent(message)
+            await self.send_rtvi_message(message)
         elif isinstance(frame, RTVIServerResponseFrame):
             if frame.error is not None:
                 await self._send_error_response(frame)
             else:
                 await self._send_server_response(frame)
+        elif isinstance(frame, InputAudioRawFrame) and self._params.user_audio_level_enabled:
+            curr_time = time.time()
+            diff_time = curr_time - self._last_user_audio_level
+            if diff_time > self._params.audio_level_period_secs:
+                level = calculate_audio_volume(frame.audio, frame.sample_rate)
+                message = RTVIUserAudioLevelMessage(data=RTVIAudioLevelMessageData(value=level))
+                await self.send_rtvi_message(message)
+                self._last_user_audio_level = curr_time
+        elif isinstance(frame, TTSAudioRawFrame) and self._params.bot_audio_level_enabled:
+            curr_time = time.time()
+            diff_time = curr_time - self._last_bot_audio_level
+            if diff_time > self._params.audio_level_period_secs:
+                level = calculate_audio_volume(frame.audio, frame.sample_rate)
+                message = RTVIBotAudioLevelMessage(data=RTVIAudioLevelMessageData(value=level))
+                await self.send_rtvi_message(message)
+                self._last_bot_audio_level = curr_time
 
         if mark_as_seen:
             self._frames_seen.add(frame.id)
 
-    async def push_transport_message_urgent(self, model: BaseModel, exclude_none: bool = True):
-        """Push an urgent transport message to the RTVI processor.
-
-        Args:
-            model: The message model to send.
-            exclude_none: Whether to exclude None values from the model dump.
-        """
-        frame = TransportMessageUrgentFrame(message=model.model_dump(exclude_none=exclude_none))
-        await self._rtvi.push_frame(frame)
-
     async def _push_bot_transcription(self):
         """Push accumulated bot transcription as a message."""
         if len(self._bot_transcription) > 0:
             message = RTVIBotTranscriptionMessage(
                 data=RTVITextMessageData(text=self._bot_transcription)
             )
-            await self.push_transport_message_urgent(message)
+            await self.send_rtvi_message(message)
             self._bot_transcription = ""
 
     async def _handle_interruptions(self, frame: Frame):
@@ -1005,7 +1101,7 @@ class RTVIObserver(BaseObserver):
             message = RTVIUserStoppedSpeakingMessage()
 
         if message:
-            await self.push_transport_message_urgent(message)
+            await self.send_rtvi_message(message)
 
     async def _handle_bot_speaking(self, frame: Frame):
         """Handle bot speaking event frames."""
@@ -1016,12 +1112,12 @@ class RTVIObserver(BaseObserver):
             message = RTVIBotStoppedSpeakingMessage()
 
         if message:
-            await self.push_transport_message_urgent(message)
+            await self.send_rtvi_message(message)
 
     async def _handle_llm_text_frame(self, frame: LLMTextFrame):
         """Handle LLM text output frames."""
         message = RTVIBotLLMTextMessage(data=RTVITextMessageData(text=frame.text))
-        await self.push_transport_message_urgent(message)
+        await self.send_rtvi_message(message)
 
         self._bot_transcription += frame.text
         if match_endofsentence(self._bot_transcription):
@@ -1044,7 +1140,7 @@ class RTVIObserver(BaseObserver):
             )
 
         if message:
-            await self.push_transport_message_urgent(message)
+            await self.send_rtvi_message(message)
 
     async def _handle_context(self, frame: OpenAILLMContextFrame | LLMContextFrame):
         """Process LLM context frames to extract user messages for the RTVI client."""
@@ -1064,7 +1160,7 @@ class RTVIObserver(BaseObserver):
                 text = "".join(part.text for part in message.parts if hasattr(part, "text"))
                 if text:
                     rtvi_message = RTVIUserLLMTextMessage(data=RTVITextMessageData(text=text))
-                    await self.push_transport_message_urgent(rtvi_message)
+                    await self.send_rtvi_message(rtvi_message)
 
             # Handle OpenAI format (original implementation)
             elif isinstance(message, dict):
@@ -1075,7 +1171,7 @@ class RTVIObserver(BaseObserver):
                     else:
                         text = content
                     rtvi_message = RTVIUserLLMTextMessage(data=RTVITextMessageData(text=text))
-                    await self.push_transport_message_urgent(rtvi_message)
+                    await self.send_rtvi_message(rtvi_message)
 
         except Exception as e:
             logger.warning(f"Caught an error while trying to handle context: {e}")
@@ -1102,7 +1198,7 @@ class RTVIObserver(BaseObserver):
                 metrics["characters"].append(d.model_dump(exclude_none=True))
 
         message = RTVIMetricsMessage(data=metrics)
-        await self.push_transport_message_urgent(message)
+        await self.send_rtvi_message(message)
 
     async def _send_server_response(self, frame: RTVIServerResponseFrame):
         """Send a response to the client for a specific request."""
@@ -1110,15 +1206,14 @@ class RTVIObserver(BaseObserver):
             id=str(frame.client_msg.msg_id),
             data=RTVIRawServerResponseData(t=frame.client_msg.type, d=frame.data),
         )
-        await self.push_transport_message_urgent(message)
+        await self.send_rtvi_message(message)
 
     async def _send_error_response(self, frame: RTVIServerResponseFrame):
         """Send a response to the client for a specific request."""
-        if self._params.errors_enabled:
-            message = RTVIErrorResponse(
-                id=str(frame.client_msg.msg_id), data=RTVIErrorResponseData(error=frame.error)
-            )
-            await self.push_transport_message_urgent(message)
+        message = RTVIErrorResponse(
+            id=str(frame.client_msg.msg_id), data=RTVIErrorResponseData(error=frame.error)
+        )
+        await self.send_rtvi_message(message)
 
 
 class RTVIProcessor(FrameProcessor):
@@ -1152,7 +1247,6 @@ class RTVIProcessor(FrameProcessor):
         # Default to 0.3.0 which is the last version before actually having a
         # "client-version".
         self._client_version = [0, 3, 0]
-        self._errors_enabled = True
         self._skip_tts: bool = False  # Keep in sync with llm_service.py
 
         self._registered_actions: Dict[str, RTVIAction] = {}
@@ -1222,14 +1316,6 @@ class RTVIProcessor(FrameProcessor):
         await self._update_config(self._config, False)
         await self._send_bot_ready()
 
-    def set_errors_enabled(self, enabled: bool):
-        """Enable or disable error message sending.
-
-        Args:
-            enabled: Whether to send error messages.
-        """
-        self._errors_enabled = enabled
-
     async def interrupt_bot(self):
         """Send a bot interruption frame upstream."""
         await self.push_interruption_task_frame_and_wait()
@@ -1258,6 +1344,13 @@ class RTVIProcessor(FrameProcessor):
         """
         await self._send_error_frame(ErrorFrame(error=error))
 
+    async def push_transport_message(self, model: BaseModel, exclude_none: bool = True):
+        """Push a transport message frame."""
+        frame = OutputTransportMessageUrgentFrame(
+            message=model.model_dump(exclude_none=exclude_none)
+        )
+        await self.push_frame(frame)
+
     async def handle_message(self, message: RTVIMessage):
         """Handle an incoming RTVI message.
 
@@ -1278,7 +1371,7 @@ class RTVIProcessor(FrameProcessor):
             args=params.arguments,
         )
         message = RTVILLMFunctionCallMessage(data=fn)
-        await self._push_transport_message(message, exclude_none=False)
+        await self.push_transport_message(message, exclude_none=False)
 
     async def handle_function_call_start(
         self, function_name: str, llm: FrameProcessor, context: OpenAILLMContext
@@ -1305,7 +1398,7 @@ class RTVIProcessor(FrameProcessor):
 
         fn = RTVILLMFunctionCallStartMessageData(function_name=function_name)
         message = RTVILLMFunctionCallStartMessage(data=fn)
-        await self._push_transport_message(message, exclude_none=False)
+        await self.push_transport_message(message, exclude_none=False)
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         """Process incoming frames through the RTVI processor.
@@ -1328,7 +1421,7 @@ class RTVIProcessor(FrameProcessor):
         elif isinstance(frame, ErrorFrame):
             await self._send_error_frame(frame)
             await self.push_frame(frame, direction)
-        elif isinstance(frame, TransportMessageUrgentFrame):
+        elif isinstance(frame, InputTransportMessageFrame):
             await self._handle_transport_message(frame)
         # All other system frames
         elif isinstance(frame, SystemFrame):
@@ -1377,11 +1470,6 @@ class RTVIProcessor(FrameProcessor):
             await self.cancel_task(self._message_task)
             self._message_task = None
 
-    async def _push_transport_message(self, model: BaseModel, exclude_none: bool = True):
-        """Push a transport message frame."""
-        frame = TransportMessageUrgentFrame(message=model.model_dump(exclude_none=exclude_none))
-        await self.push_frame(frame)
-
     async def _action_task_handler(self):
         """Handle incoming action frames."""
         while True:
@@ -1396,7 +1484,7 @@ class RTVIProcessor(FrameProcessor):
             await self._handle_message(message)
             self._message_queue.task_done()
 
-    async def _handle_transport_message(self, frame: TransportMessageUrgentFrame):
+    async def _handle_transport_message(self, frame: InputTransportMessageFrame):
         """Handle an incoming transport message frame."""
         try:
             transport_message = frame.message
@@ -1518,7 +1606,7 @@ class RTVIProcessor(FrameProcessor):
 
         services = list(self._registered_services.values())
         message = RTVIDescribeConfig(id=request_id, data=RTVIDescribeConfigData(config=services))
-        await self._push_transport_message(message)
+        await self.push_transport_message(message)
 
     async def _handle_describe_actions(self, request_id: str):
         """Handle a describe-actions request."""
@@ -1533,7 +1621,7 @@ class RTVIProcessor(FrameProcessor):
 
         actions = list(self._registered_actions.values())
         message = RTVIDescribeActions(id=request_id, data=RTVIDescribeActionsData(actions=actions))
-        await self._push_transport_message(message)
+        await self.push_transport_message(message)
 
     async def _handle_get_config(self, request_id: str):
         """Handle a get-config request."""
@@ -1547,7 +1635,7 @@ class RTVIProcessor(FrameProcessor):
             )
 
         message = RTVIConfigResponse(id=request_id, data=self._config)
-        await self._push_transport_message(message)
+        await self.push_transport_message(message)
 
     def _update_config_option(self, service: str, config: RTVIServiceOptionConfig):
         """Update a specific configuration option."""
@@ -1672,7 +1760,7 @@ class RTVIProcessor(FrameProcessor):
         # action responses (such as webhooks) don't set a request_id
         if request_id:
             message = RTVIActionResponse(id=request_id, data=RTVIActionResponseData(result=result))
-            await self._push_transport_message(message)
+            await self.push_transport_message(message)
 
     async def _send_bot_ready(self):
         """Send the bot-ready message to the client."""
@@ -1683,23 +1771,21 @@ class RTVIProcessor(FrameProcessor):
             id=self._client_ready_id,
             data=RTVIBotReadyData(version=RTVI_PROTOCOL_VERSION, config=config),
         )
-        await self._push_transport_message(message)
+        await self.push_transport_message(message)
 
     async def _send_server_message(self, message: RTVIServerMessage | RTVIServerResponse):
         """Send a message or response to the client."""
-        await self._push_transport_message(message)
+        await self.push_transport_message(message)
 
     async def _send_error_frame(self, frame: ErrorFrame):
         """Send an error frame as an RTVI error message."""
-        if self._errors_enabled:
-            message = RTVIError(data=RTVIErrorData(error=frame.error, fatal=frame.fatal))
-            await self._push_transport_message(message)
+        message = RTVIError(data=RTVIErrorData(error=frame.error, fatal=frame.fatal))
+        await self.push_transport_message(message)
 
     async def _send_error_response(self, id: str, error: str):
         """Send an error response message."""
-        if self._errors_enabled:
-            message = RTVIErrorResponse(id=id, data=RTVIErrorResponseData(error=error))
-            await self._push_transport_message(message)
+        message = RTVIErrorResponse(id=id, data=RTVIErrorResponseData(error=error))
+        await self.push_transport_message(message)
 
     def _action_id(self, service: str, action: str) -> str:
         """Generate an action ID from service and action names."""

src/pipecat/processors/logger.py

@@ -15,7 +15,7 @@ from pipecat.frames.frames import (
     Frame,
     InputAudioRawFrame,
     OutputAudioRawFrame,
-    TransportMessageFrame,
+    UserSpeakingFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 
@@ -36,9 +36,9 @@ class FrameLogger(FrameProcessor):
         color: Optional[str] = None,
         ignored_frame_types: Tuple[Type[Frame], ...] = (
             BotSpeakingFrame,
+            UserSpeakingFrame,
             InputAudioRawFrame,
             OutputAudioRawFrame,
-            TransportMessageFrame,
         ),
     ):
         """Initialize the frame logger.

src/pipecat/runner/daily.py

@@ -82,6 +82,7 @@ async def configure(
     sip_enable_video: Optional[bool] = False,
     sip_num_endpoints: Optional[int] = 1,
     sip_codecs: Optional[Dict[str, List[str]]] = None,
+    room_properties: Optional[DailyRoomProperties] = None,
 ) -> DailyRoomConfig:
     """Configure Daily room URL and token with optional SIP capabilities.
 
@@ -99,6 +100,10 @@ async def configure(
         sip_num_endpoints: Number of allowed SIP endpoints.
         sip_codecs: Codecs to support for audio and video. If None, uses Daily defaults.
             Example: {"audio": ["OPUS"], "video": ["H264"]}
+        room_properties: Optional DailyRoomProperties to use instead of building from
+            individual parameters. When provided, this overrides room_exp_duration and
+            SIP-related parameters. If not provided, properties are built from the
+            individual parameters as before.
 
     Returns:
         DailyRoomConfig: Object with room_url, token, and optional sip_endpoint.
@@ -115,6 +120,13 @@ async def configure(
         # SIP-enabled room
         sip_config = await configure(session, sip_caller_phone="+15551234567")
         print(f"SIP endpoint: {sip_config.sip_endpoint}")
+
+        # Custom room properties with recording enabled
+        custom_props = DailyRoomProperties(
+            enable_recording="cloud",
+            max_participants=2,
+        )
+        config = await configure(session, room_properties=custom_props)
     """
     # Check for required API key
     api_key = os.getenv("DAILY_API_KEY")
@@ -124,9 +136,32 @@ async def configure(
             "Get your API key from https://dashboard.daily.co/developers"
         )
 
+    # Warn if both room_properties and individual parameters are provided
+    if room_properties is not None:
+        individual_params_provided = any(
+            [
+                room_exp_duration != 2.0,
+                token_exp_duration != 2.0,
+                sip_caller_phone is not None,
+                sip_enable_video is not False,
+                sip_num_endpoints != 1,
+                sip_codecs is not None,
+            ]
+        )
+        if individual_params_provided:
+            logger.warning(
+                "Both room_properties and individual parameters (room_exp_duration, token_exp_duration, "
+                "sip_*) were provided. The room_properties will be used and individual parameters "
+                "will be ignored."
+            )
+
     # Determine if SIP mode is enabled
     sip_enabled = sip_caller_phone is not None
 
+    # If room_properties is provided, check if it has SIP configuration
+    if room_properties and room_properties.sip:
+        sip_enabled = True
+
     daily_rest_helper = DailyRESTHelper(
         daily_api_key=api_key,
         daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
@@ -150,27 +185,29 @@ async def configure(
     room_name = f"{room_prefix}-{uuid.uuid4().hex[:8]}"
     logger.info(f"Creating new Daily room: {room_name}")
 
-    # Calculate expiration time
-    expiration_time = time.time() + (room_exp_duration * 60 * 60)
+    # Use provided room_properties or build from parameters
+    if room_properties is None:
+        # Calculate expiration time
+        expiration_time = time.time() + (room_exp_duration * 60 * 60)
 
-    # Create room properties
-    room_properties = DailyRoomProperties(
-        exp=expiration_time,
-        eject_at_room_exp=True,
-    )
-
-    # Add SIP configuration if enabled
-    if sip_enabled:
-        sip_params = DailyRoomSipParams(
-            display_name=sip_caller_phone,
-            video=sip_enable_video,
-            sip_mode="dial-in",
-            num_endpoints=sip_num_endpoints,
-            codecs=sip_codecs,
+        # Create room properties
+        room_properties = DailyRoomProperties(
+            exp=expiration_time,
+            eject_at_room_exp=True,
         )
-        room_properties.sip = sip_params
-        room_properties.enable_dialout = True  # Enable outbound calls if needed
-        room_properties.start_video_off = not sip_enable_video  # Voice-only by default
+
+        # Add SIP configuration if enabled
+        if sip_enabled:
+            sip_params = DailyRoomSipParams(
+                display_name=sip_caller_phone,
+                video=sip_enable_video,
+                sip_mode="dial-in",
+                num_endpoints=sip_num_endpoints,
+                codecs=sip_codecs,
+            )
+            room_properties.sip = sip_params
+            room_properties.enable_dialout = True  # Enable outbound calls if needed
+            room_properties.start_video_off = not sip_enable_video  # Voice-only by default
 
     # Create room parameters
     room_params = DailyRoomParams(name=room_name, properties=room_properties)

src/pipecat/runner/run.py

@@ -67,10 +67,17 @@ To run locally:
 
 import argparse
 import asyncio
+import mimetypes
 import os
 import sys
+import uuid
 from contextlib import asynccontextmanager
+from http import HTTPMethod
+from pathlib import Path
+from typing import Any, Dict, List, Optional, TypedDict
 
+import aiohttp
+from fastapi.responses import FileResponse, Response
 from loguru import logger
 
 from pipecat.runner.types import (
@@ -82,7 +89,7 @@ from pipecat.runner.types import (
 try:
     import uvicorn
     from dotenv import load_dotenv
-    from fastapi import BackgroundTasks, FastAPI, Request, WebSocket
+    from fastapi import BackgroundTasks, FastAPI, Header, HTTPException, Request, WebSocket
     from fastapi.middleware.cors import CORSMiddleware
     from fastapi.responses import HTMLResponse, RedirectResponse
 except ImportError as e:
@@ -96,6 +103,12 @@ except ImportError as e:
 load_dotenv(override=True)
 os.environ["ENV"] = "local"
 
+TELEPHONY_TRANSPORTS = ["twilio", "telnyx", "plivo", "exotel"]
+
+RUNNER_DOWNLOADS_FOLDER: Optional[str] = None
+RUNNER_HOST: str = "localhost"
+RUNNER_PORT: int = 7860
+
 
 def _get_bot_module():
     """Get the bot module from the calling script."""
@@ -150,7 +163,13 @@ async def _run_telephony_bot(websocket: WebSocket):
 
 
 def _create_server_app(
-    transport_type: str, host: str = "localhost", proxy: str = None, esp32_mode: bool = False
+    *,
+    transport_type: str,
+    host: str = "localhost",
+    proxy: str,
+    esp32_mode: bool = False,
+    whatsapp_enabled: bool = False,
+    folder: Optional[str] = None,
 ):
     """Create FastAPI app with transport-specific routes."""
     app = FastAPI()
@@ -165,24 +184,30 @@ def _create_server_app(
 
     # Set up transport-specific routes
     if transport_type == "webrtc":
-        _setup_webrtc_routes(app, esp32_mode=esp32_mode, host=host)
+        _setup_webrtc_routes(app, esp32_mode=esp32_mode, host=host, folder=folder)
+        if whatsapp_enabled:
+            _setup_whatsapp_routes(app)
     elif transport_type == "daily":
         _setup_daily_routes(app)
-    elif transport_type in ["twilio", "telnyx", "plivo", "exotel"]:
-        _setup_telephony_routes(app, transport_type, proxy)
+    elif transport_type in TELEPHONY_TRANSPORTS:
+        _setup_telephony_routes(app, transport_type=transport_type, proxy=proxy)
     else:
         logger.warning(f"Unknown transport type: {transport_type}")
 
     return app
 
 
-def _setup_webrtc_routes(app: FastAPI, esp32_mode: bool = False, host: str = "localhost"):
+def _setup_webrtc_routes(
+    app: FastAPI, *, esp32_mode: bool = False, host: str = "localhost", folder: Optional[str] = None
+):
     """Set up WebRTC-specific routes."""
     try:
         from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
 
-        from pipecat.transports.smallwebrtc.connection import SmallWebRTCConnection
+        from pipecat.transports.smallwebrtc.connection import IceServer, SmallWebRTCConnection
         from pipecat.transports.smallwebrtc.request_handler import (
+            IceCandidate,
+            SmallWebRTCPatchRequest,
             SmallWebRTCRequest,
             SmallWebRTCRequestHandler,
         )
@@ -190,6 +215,16 @@ def _setup_webrtc_routes(app: FastAPI, esp32_mode: bool = False, host: str = "lo
         logger.error(f"WebRTC transport dependencies not installed: {e}")
         return
 
+    class IceConfig(TypedDict):
+        iceServers: List[IceServer]
+
+    class StartBotResult(TypedDict, total=False):
+        sessionId: str
+        iceConfig: Optional[IceConfig]
+
+    # In-memory store of active sessions: session_id -> session info
+    active_sessions: Dict[str, Dict[str, Any]] = {}
+
     # Mount the frontend
     app.mount("/client", SmallWebRTCPrebuiltUI)
 
@@ -198,6 +233,21 @@ def _setup_webrtc_routes(app: FastAPI, esp32_mode: bool = False, host: str = "lo
         """Redirect root requests to client interface."""
         return RedirectResponse(url="/client/")
 
+    @app.get("/files/{filename:path}")
+    async def download_file(filename: str):
+        """Handle file downloads."""
+        if not folder:
+            logger.warning(f"Attempting to dowload {filename}, but downloads folder not setup.")
+            return
+
+        file_path = Path(folder) / filename
+        if not os.path.exists(file_path):
+            raise HTTPException(404)
+
+        media_type, _ = mimetypes.guess_type(file_path)
+
+        return FileResponse(path=file_path, media_type=media_type, filename=filename)
+
     # Initialize the SmallWebRTC request handler
     small_webrtc_handler: SmallWebRTCRequestHandler = SmallWebRTCRequestHandler(
         esp32_mode=esp32_mode, host=host
@@ -220,13 +270,259 @@ def _setup_webrtc_routes(app: FastAPI, esp32_mode: bool = False, host: str = "lo
         )
         return answer
 
+    @app.patch("/api/offer")
+    async def ice_candidate(request: SmallWebRTCPatchRequest):
+        """Handle WebRTC new ice candidate requests."""
+        logger.debug(f"Received patch request: {request}")
+        await small_webrtc_handler.handle_patch_request(request)
+        return {"status": "success"}
+
+    @app.post("/start")
+    async def rtvi_start(request: Request):
+        """Mimic Pipecat Cloud's /start endpoint."""
+        # Parse the request body
+        try:
+            request_data = await request.json()
+            logger.debug(f"Received request: {request_data}")
+        except Exception as e:
+            logger.error(f"Failed to parse request body: {e}")
+            request_data = {}
+
+        # Store session info immediately in memory, replicate the behavior expected on Pipecat Cloud
+        session_id = str(uuid.uuid4())
+        active_sessions[session_id] = request_data
+
+        result: StartBotResult = {"sessionId": session_id}
+        if request_data.get("enableDefaultIceServers"):
+            result["iceConfig"] = IceConfig(
+                iceServers=[IceServer(urls="stun:stun.l.google.com:19302")]
+            )
+
+        return result
+
+    @app.api_route(
+        "/sessions/{session_id}/{path:path}",
+        methods=["GET", "POST", "PUT", "PATCH", "DELETE"],
+    )
+    async def proxy_request(
+        session_id: str, path: str, request: Request, background_tasks: BackgroundTasks
+    ):
+        """Mimic Pipecat Cloud's proxy."""
+        active_session = active_sessions.get(session_id)
+        if not active_session:
+            return Response(content="Invalid or not-yet-ready session_id", status_code=404)
+
+        if path.endswith("api/offer"):
+            # Parse the request body and convert to SmallWebRTCRequest
+            try:
+                request_data = await request.json()
+                if request.method == HTTPMethod.POST.value:
+                    webrtc_request = SmallWebRTCRequest(
+                        sdp=request_data["sdp"],
+                        type=request_data["type"],
+                        pc_id=request_data.get("pc_id"),
+                        restart_pc=request_data.get("restart_pc"),
+                        request_data=request_data,
+                    )
+                    return await offer(webrtc_request, background_tasks)
+                elif request.method == HTTPMethod.PATCH.value:
+                    patch_request = SmallWebRTCPatchRequest(
+                        pc_id=request_data["pc_id"],
+                        candidates=[IceCandidate(**c) for c in request_data.get("candidates", [])],
+                    )
+                    return await ice_candidate(patch_request)
+            except Exception as e:
+                logger.error(f"Failed to parse WebRTC request: {e}")
+                return Response(content="Invalid WebRTC request", status_code=400)
+
+        logger.info(f"Received request for path: {path}")
+        return Response(status_code=200)
+
     @asynccontextmanager
-    async def lifespan(app: FastAPI):
+    async def smallwebrtc_lifespan(app: FastAPI):
         """Manage FastAPI application lifecycle and cleanup connections."""
         yield
         await small_webrtc_handler.close()
 
-    app.router.lifespan_context = lifespan
+    # Add the SmallWebRTC lifespan to the app
+    _add_lifespan_to_app(app, smallwebrtc_lifespan)
+
+
+def _add_lifespan_to_app(app: FastAPI, new_lifespan):
+    """Add a new lifespan context manager to the app, combining with existing if present.
+
+    Args:
+        app: The FastAPI application instance
+        new_lifespan: The new lifespan context manager to add
+    """
+    if hasattr(app.router, "lifespan_context") and app.router.lifespan_context is not None:
+        # If there's already a lifespan context, combine them
+        existing_lifespan = app.router.lifespan_context
+
+        @asynccontextmanager
+        async def combined_lifespan(app: FastAPI):
+            async with existing_lifespan(app):
+                async with new_lifespan(app):
+                    yield
+
+        app.router.lifespan_context = combined_lifespan
+    else:
+        # No existing lifespan, use the new one
+        app.router.lifespan_context = new_lifespan
+
+
+def _setup_whatsapp_routes(app: FastAPI):
+    """Set up WebRTC-specific routes."""
+    WHATSAPP_APP_SECRET = os.getenv("WHATSAPP_APP_SECRET")
+    WHATSAPP_PHONE_NUMBER_ID = os.getenv("WHATSAPP_PHONE_NUMBER_ID")
+    WHATSAPP_TOKEN = os.getenv("WHATSAPP_TOKEN")
+    WHATSAPP_WEBHOOK_VERIFICATION_TOKEN = os.getenv("WHATSAPP_WEBHOOK_VERIFICATION_TOKEN")
+
+    if not all(
+        [
+            WHATSAPP_APP_SECRET,
+            WHATSAPP_PHONE_NUMBER_ID,
+            WHATSAPP_TOKEN,
+            WHATSAPP_WEBHOOK_VERIFICATION_TOKEN,
+        ]
+    ):
+        logger.error(
+            """Missing required environment variables for WhatsApp transport:
+    WHATSAPP_APP_SECRET
+    WHATSAPP_PHONE_NUMBER_ID
+    WHATSAPP_TOKEN
+    WHATSAPP_WEBHOOK_VERIFICATION_TOKEN
+            """
+        )
+        return
+
+    try:
+        from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
+
+        from pipecat.transports.smallwebrtc.connection import SmallWebRTCConnection
+        from pipecat.transports.smallwebrtc.request_handler import (
+            SmallWebRTCRequest,
+            SmallWebRTCRequestHandler,
+        )
+        from pipecat.transports.whatsapp.api import WhatsAppWebhookRequest
+        from pipecat.transports.whatsapp.client import WhatsAppClient
+    except ImportError as e:
+        logger.error(f"WhatsApp transport dependencies not installed: {e}")
+        return
+
+    # Global WhatsApp client instance
+    whatsapp_client: Optional[WhatsAppClient] = None
+
+    @app.get(
+        "/whatsapp",
+        summary="Verify WhatsApp webhook",
+        description="Handles WhatsApp webhook verification requests from Meta",
+    )
+    async def verify_webhook(request: Request):
+        """Verify WhatsApp webhook endpoint.
+
+        This endpoint is called by Meta's WhatsApp Business API to verify
+        the webhook URL during setup. It validates the verification token
+        and returns the challenge parameter if successful.
+        """
+        if whatsapp_client is None:
+            logger.error("WhatsApp client is not initialized")
+            raise HTTPException(status_code=503, detail="Service unavailable")
+
+        params = dict(request.query_params)
+        logger.debug(f"Webhook verification request received with params: {list(params.keys())}")
+
+        try:
+            result = await whatsapp_client.handle_verify_webhook_request(
+                params=params, expected_verification_token=WHATSAPP_WEBHOOK_VERIFICATION_TOKEN
+            )
+            logger.info("Webhook verification successful")
+            return result
+        except ValueError as e:
+            logger.warning(f"Webhook verification failed: {e}")
+            raise HTTPException(status_code=403, detail="Verification failed")
+
+    @app.post(
+        "/whatsapp",
+        summary="Handle WhatsApp webhook events",
+        description="Processes incoming WhatsApp messages and call events",
+    )
+    async def whatsapp_webhook(
+        body: WhatsAppWebhookRequest,
+        background_tasks: BackgroundTasks,
+        request: Request,
+        x_hub_signature_256: str = Header(None),
+    ):
+        """Handle incoming WhatsApp webhook events.
+
+        For call events, establishes WebRTC connections and spawns bot instances
+        in the background to handle real-time communication.
+        """
+        if whatsapp_client is None:
+            logger.error("WhatsApp client is not initialized")
+            raise HTTPException(status_code=503, detail="Service unavailable")
+
+        # Validate webhook object type
+        if body.object != "whatsapp_business_account":
+            logger.warning(f"Invalid webhook object type: {body.object}")
+            raise HTTPException(status_code=400, detail="Invalid object type")
+
+        logger.debug(f"Processing WhatsApp webhook: {body.model_dump()}")
+
+        async def connection_callback(connection: SmallWebRTCConnection):
+            """Handle new WebRTC connections from WhatsApp calls.
+
+            Called when a WebRTC connection is established for a WhatsApp call.
+            Spawns a bot instance to handle the conversation.
+
+            Args:
+                connection: The established WebRTC connection
+            """
+            bot_module = _get_bot_module()
+            runner_args = SmallWebRTCRunnerArguments(webrtc_connection=connection)
+            background_tasks.add_task(bot_module.bot, runner_args)
+
+        try:
+            # Process the webhook request
+            raw_body = await request.body()
+            result = await whatsapp_client.handle_webhook_request(
+                body, connection_callback, sha256_signature=x_hub_signature_256, raw_body=raw_body
+            )
+            logger.debug(f"Webhook processed successfully: {result}")
+            return {"status": "success", "message": "Webhook processed successfully"}
+        except ValueError as ve:
+            logger.warning(f"Invalid webhook request format: {ve}")
+            raise HTTPException(status_code=400, detail=f"Invalid request: {str(ve)}")
+        except Exception as e:
+            logger.error(f"Internal error processing webhook: {e}")
+            raise HTTPException(status_code=500, detail="Internal server error processing webhook")
+
+    @asynccontextmanager
+    async def whatsapp_lifespan(app: FastAPI):
+        """Manage WhatsApp client lifecycle and cleanup connections."""
+        nonlocal whatsapp_client
+
+        # Initialize WhatsApp client with persistent HTTP session
+        async with aiohttp.ClientSession() as session:
+            whatsapp_client = WhatsAppClient(
+                whatsapp_token=WHATSAPP_TOKEN,
+                whatsapp_secret=WHATSAPP_APP_SECRET,
+                phone_number_id=WHATSAPP_PHONE_NUMBER_ID,
+                session=session,
+            )
+            logger.info("WhatsApp client initialized successfully")
+
+            try:
+                yield  # Run the application
+            finally:
+                # Cleanup all active calls on shutdown
+                logger.info("Cleaning up WhatsApp client resources...")
+                if whatsapp_client:
+                    await whatsapp_client.terminate_all_calls()
+                logger.info("WhatsApp cleanup completed")
+
+    # Add the WhatsApp lifespan to the app
+    _add_lifespan_to_app(app, whatsapp_lifespan)
 
 
 def _setup_daily_routes(app: FastAPI):
@@ -281,8 +577,6 @@ def _setup_daily_routes(app: FastAPI):
         else:
             logger.debug("No body data provided in request")
 
-        import aiohttp
-
         from pipecat.runner.daily import configure
 
         async with aiohttp.ClientSession() as session:
@@ -314,7 +608,7 @@ def _setup_daily_routes(app: FastAPI):
         return await _handle_rtvi_request(request)
 
 
-def _setup_telephony_routes(app: FastAPI, transport_type: str, proxy: str):
+def _setup_telephony_routes(app: FastAPI, *, transport_type: str, proxy: str):
     """Set up telephony-specific routes."""
     # XML response templates (Exotel doesn't use XML webhooks)
     XML_TEMPLATES = {
@@ -370,8 +664,6 @@ def _setup_telephony_routes(app: FastAPI, transport_type: str, proxy: str):
 async def _run_daily_direct():
     """Run Daily bot with direct connection (no FastAPI server)."""
     try:
-        import aiohttp
-
         from pipecat.runner.daily import configure
     except ImportError as e:
         logger.error("Daily transport dependencies not installed.")
@@ -417,6 +709,21 @@ def _validate_and_clean_proxy(proxy: str) -> str:
     return proxy
 
 
+def runner_downloads_folder() -> Optional[str]:
+    """Returns the folder where files are stored for later download."""
+    return RUNNER_DOWNLOADS_FOLDER
+
+
+def runner_host() -> str:
+    """Returns the host name of this runner."""
+    return RUNNER_HOST
+
+
+def runner_port() -> int:
+    """Returns the port of this runner."""
+    return RUNNER_PORT
+
+
 def main():
     """Start the Pipecat development runner.
 
@@ -437,14 +744,16 @@ def main():
 
     The bot file must contain a `bot(runner_args)` function as the entry point.
     """
+    global RUNNER_DOWNLOADS_FOLDER, RUNNER_HOST, RUNNER_PORT
+
     parser = argparse.ArgumentParser(description="Pipecat Development Runner")
-    parser.add_argument("--host", type=str, default="localhost", help="Host address")
-    parser.add_argument("--port", type=int, default=7860, help="Port number")
+    parser.add_argument("--host", type=str, default=RUNNER_HOST, help="Host address")
+    parser.add_argument("--port", type=int, default=RUNNER_PORT, help="Port number")
     parser.add_argument(
         "-t",
         "--transport",
         type=str,
-        choices=["daily", "webrtc", "twilio", "telnyx", "plivo", "exotel"],
+        choices=["daily", "webrtc", *TELEPHONY_TRANSPORTS],
         default="webrtc",
         help="Transport type",
     )
@@ -462,9 +771,16 @@ def main():
         default=False,
         help="Connect directly to Daily room (automatically sets transport to daily)",
     )
+    parser.add_argument("-f", "--folder", type=str, help="Path to downloads folder")
     parser.add_argument(
         "--verbose", "-v", action="count", default=0, help="Increase logging verbosity"
     )
+    parser.add_argument(
+        "--whatsapp",
+        action="store_true",
+        default=False,
+        help="Ensure requried WhatsApp environment variables are present",
+    )
 
     args = parser.parse_args()
 
@@ -484,6 +800,10 @@ def main():
         logger.error("For ESP32, you need to specify `--host IP` so we can do SDP munging.")
         return
 
+    if args.transport in TELEPHONY_TRANSPORTS and not args.proxy:
+        logger.error(f"For telephony transports, you need to specify `--proxy PROXY`.")
+        return
+
     # Log level
     logger.remove()
     logger.add(sys.stderr, level="TRACE" if args.verbose else "DEBUG")
@@ -503,10 +823,11 @@ def main():
         print()
         if args.esp32:
             print(f"🚀 Bot ready! (ESP32 mode)")
-            print(f"   → Open http://{args.host}:{args.port}/client in your browser")
+        elif args.whatsapp:
+            print(f"🚀 Bot ready! (WhatsApp)")
         else:
             print(f"🚀 Bot ready!")
-            print(f"   → Open http://{args.host}:{args.port}/client in your browser")
+        print(f"   → Open http://{args.host}:{args.port}/client in your browser")
         print()
     elif args.transport == "daily":
         print()
@@ -514,8 +835,19 @@ def main():
         print(f"   → Open http://{args.host}:{args.port} in your browser to start a session")
         print()
 
+    RUNNER_DOWNLOADS_FOLDER = args.folder
+    RUNNER_HOST = args.host
+    RUNNER_PORT = args.port
+
     # Create the app with transport-specific setup
-    app = _create_server_app(args.transport, args.host, args.proxy, args.esp32)
+    app = _create_server_app(
+        transport_type=args.transport,
+        host=args.host,
+        proxy=args.proxy,
+        esp32_mode=args.esp32,
+        whatsapp_enabled=args.whatsapp,
+        folder=args.folder,
+    )
 
     # Run the server
     uvicorn.run(app, host=args.host, port=args.port)

src/pipecat/runner/utils.py

@@ -99,29 +99,41 @@ async def parse_telephony_websocket(websocket: WebSocket):
         tuple: (transport_type: str, call_data: dict)
 
         call_data contains provider-specific fields:
-        - Twilio: {
-            "stream_id": str,
-            "call_id": str,
-            "body": dict
-        }
-        - Telnyx: {
-            "stream_id": str,
-            "call_control_id": str,
-            "outbound_encoding": str,
-            "from": str,
-            "to": str,
-        }
-        - Plivo: {
-            "stream_id": str,
-            "call_id": str,
-        }
-        - Exotel: {
-            "stream_id": str,
-            "call_id": str,
-            "account_sid": str,
-            "from": str,
-            "to": str,
-        }
+
+        - Twilio::
+
+            {
+                "stream_id": str,
+                "call_id": str,
+                "body": dict
+            }
+
+        - Telnyx::
+
+            {
+                "stream_id": str,
+                "call_control_id": str,
+                "outbound_encoding": str,
+                "from": str,
+                "to": str,
+            }
+
+        - Plivo::
+
+            {
+                "stream_id": str,
+                "call_id": str,
+            }
+
+        - Exotel::
+
+            {
+                "stream_id": str,
+                "call_id": str,
+                "account_sid": str,
+                "from": str,
+                "to": str,
+            }
 
     Example usage::
 
@@ -301,6 +313,7 @@ def _smallwebrtc_sdp_cleanup_ice_candidates(text: str, pattern: str) -> str:
     Returns:
         Cleaned SDP text with filtered ICE candidates.
     """
+    logger.debug("Removing unsupported ICE candidates from SDP")
     result = []
     lines = text.splitlines()
     for line in lines:
@@ -309,7 +322,7 @@ def _smallwebrtc_sdp_cleanup_ice_candidates(text: str, pattern: str) -> str:
                 result.append(line)
         else:
             result.append(line)
-    return "\r\n".join(result)
+    return "\r\n".join(result) + "\r\n"
 
 
 def _smallwebrtc_sdp_cleanup_fingerprints(text: str) -> str:
@@ -321,15 +334,16 @@ def _smallwebrtc_sdp_cleanup_fingerprints(text: str) -> str:
     Returns:
         SDP text with sha-384 and sha-512 fingerprints removed.
     """
+    logger.debug("Removing unsupported fingerprints from SDP")
     result = []
     lines = text.splitlines()
     for line in lines:
         if not re.search("sha-384", line) and not re.search("sha-512", line):
             result.append(line)
-    return "\r\n".join(result)
+    return "\r\n".join(result) + "\r\n"
 
 
-def smallwebrtc_sdp_munging(sdp: str, host: str) -> str:
+def smallwebrtc_sdp_munging(sdp: str, host: Optional[str]) -> str:
     """Apply SDP modifications for SmallWebRTC compatibility.
 
     Args:
@@ -340,7 +354,8 @@ def smallwebrtc_sdp_munging(sdp: str, host: str) -> str:
         Modified SDP string with fingerprint and ICE candidate cleanup.
     """
     sdp = _smallwebrtc_sdp_cleanup_fingerprints(sdp)
-    sdp = _smallwebrtc_sdp_cleanup_ice_candidates(sdp, host)
+    if host:
+        sdp = _smallwebrtc_sdp_cleanup_ice_candidates(sdp, host)
     return sdp
 
 

src/pipecat/serializers/exotel.py

@@ -21,9 +21,9 @@ from pipecat.frames.frames import (
     InputAudioRawFrame,
     InputDTMFFrame,
     InterruptionFrame,
+    OutputTransportMessageFrame,
+    OutputTransportMessageUrgentFrame,
     StartFrame,
-    TransportMessageFrame,
-    TransportMessageUrgentFrame,
 )
 from pipecat.serializers.base_serializer import FrameSerializer, FrameSerializerType
 
@@ -121,7 +121,7 @@ class ExotelFrameSerializer(FrameSerializer):
             }
 
             return json.dumps(answer)
-        elif isinstance(frame, (TransportMessageFrame, TransportMessageUrgentFrame)):
+        elif isinstance(frame, (OutputTransportMessageFrame, OutputTransportMessageUrgentFrame)):
             return json.dumps(frame.message)
 
         return None

src/pipecat/serializers/livekit.py

@@ -25,11 +25,31 @@ except ModuleNotFoundError as e:
 class LivekitFrameSerializer(FrameSerializer):
     """Serializer for converting between Pipecat frames and LiveKit audio frames.
 
+    .. deprecated:: 0.0.90
+
+        This class is deprecated and will be removed in a future version.
+        Please use LiveKitTransport instead, which handles audio streaming
+        and frame conversion natively.
+
     This serializer handles the conversion of Pipecat's OutputAudioRawFrame objects
     to LiveKit AudioFrame objects for transmission, and the reverse conversion
     for received audio data.
     """
 
+    def __init__(self):
+        """Initialize the LiveKit frame serializer."""
+        super().__init__()
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "LivekitFrameSerializer is deprecated and will be removed in a future version. "
+                "Please use LiveKitTransport instead, which handles audio streaming natively.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
     @property
     def type(self) -> FrameSerializerType:
         """Get the serializer type.

src/pipecat/serializers/plivo.py

@@ -23,9 +23,9 @@ from pipecat.frames.frames import (
     InputAudioRawFrame,
     InputDTMFFrame,
     InterruptionFrame,
+    OutputTransportMessageFrame,
+    OutputTransportMessageUrgentFrame,
     StartFrame,
-    TransportMessageFrame,
-    TransportMessageUrgentFrame,
 )
 from pipecat.serializers.base_serializer import FrameSerializer, FrameSerializerType
 
@@ -148,7 +148,7 @@ class PlivoFrameSerializer(FrameSerializer):
             }
 
             return json.dumps(answer)
-        elif isinstance(frame, (TransportMessageFrame, TransportMessageUrgentFrame)):
+        elif isinstance(frame, (OutputTransportMessageFrame, OutputTransportMessageUrgentFrame)):
             return json.dumps(frame.message)
 
         # Return None for unhandled frames

src/pipecat/serializers/protobuf.py

@@ -15,11 +15,12 @@ import pipecat.frames.protobufs.frames_pb2 as frame_protos
 from pipecat.frames.frames import (
     Frame,
     InputAudioRawFrame,
+    InputTransportMessageFrame,
     OutputAudioRawFrame,
+    OutputTransportMessageFrame,
+    OutputTransportMessageUrgentFrame,
     TextFrame,
     TranscriptionFrame,
-    TransportMessageFrame,
-    TransportMessageUrgentFrame,
 )
 from pipecat.serializers.base_serializer import FrameSerializer, FrameSerializerType
 
@@ -82,7 +83,7 @@ class ProtobufFrameSerializer(FrameSerializer):
             Serialized frame as bytes, or None if frame type is not serializable.
         """
         # Wrapping this messages as a JSONFrame to send
-        if isinstance(frame, (TransportMessageFrame, TransportMessageUrgentFrame)):
+        if isinstance(frame, (OutputTransportMessageFrame, OutputTransportMessageUrgentFrame)):
             frame = MessageFrame(
                 data=json.dumps(frame.message),
             )
@@ -134,11 +135,11 @@ class ProtobufFrameSerializer(FrameSerializer):
         if "pts" in args_dict:
             del args_dict["pts"]
 
-        # Special handling for MessageFrame -> TransportMessageUrgentFrame
+        # Special handling for MessageFrame -> OutputTransportMessageUrgentFrame
         if class_name == MessageFrame:
             try:
                 msg = json.loads(args_dict["data"])
-                instance = TransportMessageUrgentFrame(message=msg)
+                instance = InputTransportMessageFrame(message=msg)
                 logger.debug(f"ProtobufFrameSerializer: Transport message {instance}")
             except Exception as e:
                 logger.error(f"Error parsing MessageFrame data: {e}")

src/pipecat/serializers/twilio.py

@@ -23,9 +23,9 @@ from pipecat.frames.frames import (
     InputAudioRawFrame,
     InputDTMFFrame,
     InterruptionFrame,
+    OutputTransportMessageFrame,
+    OutputTransportMessageUrgentFrame,
     StartFrame,
-    TransportMessageFrame,
-    TransportMessageUrgentFrame,
 )
 from pipecat.serializers.base_serializer import FrameSerializer, FrameSerializerType
 
@@ -175,7 +175,7 @@ class TwilioFrameSerializer(FrameSerializer):
             }
 
             return json.dumps(answer)
-        elif isinstance(frame, (TransportMessageFrame, TransportMessageUrgentFrame)):
+        elif isinstance(frame, (OutputTransportMessageFrame, OutputTransportMessageUrgentFrame)):
             return json.dumps(frame.message)
 
         # Return None for unhandled frames

src/pipecat/services/ai_service.py

@@ -97,9 +97,7 @@ class AIService(FrameProcessor):
         pass
 
     async def _update_settings(self, settings: Mapping[str, Any]):
-        from pipecat.services.openai_realtime_beta.events import (
-            SessionProperties,
-        )
+        from pipecat.services.openai.realtime.events import SessionProperties
 
         for key, value in settings.items():
             logger.debug("Update request for:", key, value)
@@ -111,9 +109,7 @@ class AIService(FrameProcessor):
                 logger.debug("Attempting to update", key, value)
 
                 try:
-                    from pipecat.services.openai_realtime_beta.events import (
-                        TurnDetection,
-                    )
+                    from pipecat.services.openai.realtime.events import TurnDetection
 
                     if isinstance(self._session_properties, SessionProperties):
                         current_properties = self._session_properties

src/pipecat/services/anthropic/llm.py

@@ -151,7 +151,7 @@ class AnthropicLLMService(LLMService):
         self,
         *,
         api_key: str,
-        model: str = "claude-sonnet-4-20250514",
+        model: str = "claude-sonnet-4-5-20250929",
         params: Optional[InputParams] = None,
         client=None,
         retry_timeout_secs: Optional[float] = 5.0,
@@ -162,7 +162,7 @@ class AnthropicLLMService(LLMService):
 
         Args:
             api_key: Anthropic API key for authentication.
-            model: Model name to use. Defaults to "claude-sonnet-4-20250514".
+            model: Model name to use. Defaults to "claude-sonnet-4-5-20250929".
             params: Optional model parameters for inference.
             client: Optional custom Anthropic client instance.
             retry_timeout_secs: Request timeout in seconds for retry logic.

src/pipecat/services/assemblyai/models.py

@@ -108,6 +108,8 @@ class AssemblyAIConnectionParams(BaseModel):
         end_of_turn_confidence_threshold: Confidence threshold for end-of-turn detection.
         min_end_of_turn_silence_when_confident: Minimum silence duration when confident about end-of-turn.
         max_turn_silence: Maximum silence duration before forcing end-of-turn.
+        keyterms_prompt: List of key terms to guide transcription. Will be JSON serialized before sending.
+        speech_model: Select between English and multilingual models. Defaults to "universal-streaming-english".
     """
 
     sample_rate: int = 16000
@@ -117,3 +119,7 @@ class AssemblyAIConnectionParams(BaseModel):
     end_of_turn_confidence_threshold: Optional[float] = None
     min_end_of_turn_silence_when_confident: Optional[int] = None
     max_turn_silence: Optional[int] = None
+    keyterms_prompt: Optional[List[str]] = None
+    speech_model: Literal["universal-streaming-english", "universal-streaming-multilingual"] = (
+        "universal-streaming-english"
+    )

src/pipecat/services/assemblyai/stt.py

@@ -174,11 +174,16 @@ class AssemblyAISTTService(STTService):
 
     def _build_ws_url(self) -> str:
         """Build WebSocket URL with query parameters using urllib.parse.urlencode."""
-        params = {
-            k: str(v).lower() if isinstance(v, bool) else v
-            for k, v in self._connection_params.model_dump().items()
-            if v is not None
-        }
+        params = {}
+        for k, v in self._connection_params.model_dump().items():
+            if v is not None:
+                if k == "keyterms_prompt":
+                    params[k] = json.dumps(v)
+                elif isinstance(v, bool):
+                    params[k] = str(v).lower()
+                else:
+                    params[k] = v
+
         if params:
             query_string = urlencode(params)
             return f"{self._api_endpoint_base_url}?{query_string}"
@@ -197,6 +202,8 @@ class AssemblyAISTTService(STTService):
             )
             self._connected = True
             self._receive_task = self.create_task(self._receive_task_handler())
+
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"Failed to connect to AssemblyAI: {e}")
             self._connected = False
@@ -238,6 +245,7 @@ class AssemblyAISTTService(STTService):
             self._websocket = None
             self._connected = False
             self._receive_task = None
+            await self._call_event_handler("on_disconnected")
 
     async def _receive_task_handler(self):
         """Handle incoming WebSocket messages."""

src/pipecat/services/asyncai/tts.py

@@ -235,6 +235,8 @@ class AsyncAITTSService(InterruptibleTTSService):
             }
 
             await self._get_websocket().send(json.dumps(init_msg))
+
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -252,6 +254,7 @@ class AsyncAITTSService(InterruptibleTTSService):
         finally:
             self._websocket = None
             self._started = False
+            await self._call_event_handler("on_disconnected")
 
     def _get_websocket(self):
         if self._websocket:

src/pipecat/services/aws/__init__.py

@@ -9,6 +9,7 @@ import sys
 from pipecat.services import DeprecatedModuleProxy
 
 from .llm import *
+from .nova_sonic import *
 from .stt import *
 from .tts import *
 

src/pipecat/services/aws/llm.py

@@ -61,7 +61,6 @@ from pipecat.utils.tracing.service_decorators import traced_llm
 
 try:
     import aioboto3
-    import httpx
     from botocore.config import Config
     from botocore.exceptions import ReadTimeoutError
 except ModuleNotFoundError as e:
@@ -1117,7 +1116,7 @@ class AWSBedrockLLMService(LLMService):
             # also get cancelled.
             use_completion_tokens_estimate = True
             raise
-        except httpx.TimeoutException:
+        except (ReadTimeoutError, asyncio.TimeoutError):
             await self._call_event_handler("on_completion_timeout")
         except Exception as e:
             logger.exception(f"{self} exception: {e}")

src/pipecat/services/aws/nova_sonic/context.py

@@ -0,0 +1,367 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Context management for AWS Nova Sonic LLM service.
+
+This module provides specialized context aggregators and message handling for AWS Nova Sonic,
+including conversation history management and role-specific message processing.
+"""
+
+import copy
+from dataclasses import dataclass, field
+from enum import Enum
+
+from loguru import logger
+
+from pipecat.frames.frames import (
+    BotStoppedSpeakingFrame,
+    DataFrame,
+    Frame,
+    FunctionCallResultFrame,
+    InterruptionFrame,
+    LLMFullResponseEndFrame,
+    LLMFullResponseStartFrame,
+    LLMMessagesAppendFrame,
+    LLMMessagesUpdateFrame,
+    LLMSetToolChoiceFrame,
+    LLMSetToolsFrame,
+    TextFrame,
+    UserImageRawFrame,
+)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.frame_processor import FrameDirection
+from pipecat.services.aws.nova_sonic.frames import AWSNovaSonicFunctionCallResultFrame
+from pipecat.services.openai.llm import (
+    OpenAIAssistantContextAggregator,
+    OpenAIUserContextAggregator,
+)
+
+
+class Role(Enum):
+    """Roles supported in AWS Nova Sonic conversations.
+
+    Parameters:
+        SYSTEM: System-level messages (not used in conversation history).
+        USER: Messages sent by the user.
+        ASSISTANT: Messages sent by the assistant.
+        TOOL: Messages sent by tools (not used in conversation history).
+    """
+
+    SYSTEM = "SYSTEM"
+    USER = "USER"
+    ASSISTANT = "ASSISTANT"
+    TOOL = "TOOL"
+
+
+@dataclass
+class AWSNovaSonicConversationHistoryMessage:
+    """A single message in AWS Nova Sonic conversation history.
+
+    Parameters:
+        role: The role of the message sender (USER or ASSISTANT only).
+        text: The text content of the message.
+    """
+
+    role: Role  # only USER and ASSISTANT
+    text: str
+
+
+@dataclass
+class AWSNovaSonicConversationHistory:
+    """Complete conversation history for AWS Nova Sonic initialization.
+
+    Parameters:
+        system_instruction: System-level instruction for the conversation.
+        messages: List of conversation messages between user and assistant.
+    """
+
+    system_instruction: str = None
+    messages: list[AWSNovaSonicConversationHistoryMessage] = field(default_factory=list)
+
+
+class AWSNovaSonicLLMContext(OpenAILLMContext):
+    """Specialized LLM context for AWS Nova Sonic service.
+
+    Extends OpenAI context with Nova Sonic-specific message handling,
+    conversation history management, and text buffering capabilities.
+    """
+
+    def __init__(self, messages=None, tools=None, **kwargs):
+        """Initialize AWS Nova Sonic LLM context.
+
+        Args:
+            messages: Initial messages for the context.
+            tools: Available tools for the context.
+            **kwargs: Additional arguments passed to parent class.
+        """
+        super().__init__(messages=messages, tools=tools, **kwargs)
+        self.__setup_local()
+
+    def __setup_local(self, system_instruction: str = ""):
+        self._assistant_text = ""
+        self._user_text = ""
+        self._system_instruction = system_instruction
+
+    @staticmethod
+    def upgrade_to_nova_sonic(
+        obj: OpenAILLMContext, system_instruction: str
+    ) -> "AWSNovaSonicLLMContext":
+        """Upgrade an OpenAI context to AWS Nova Sonic context.
+
+        Args:
+            obj: The OpenAI context to upgrade.
+            system_instruction: System instruction for the context.
+
+        Returns:
+            The upgraded AWS Nova Sonic context.
+        """
+        if isinstance(obj, OpenAILLMContext) and not isinstance(obj, AWSNovaSonicLLMContext):
+            obj.__class__ = AWSNovaSonicLLMContext
+            obj.__setup_local(system_instruction)
+        return obj
+
+    # NOTE: this method has the side-effect of updating _system_instruction from messages
+    def get_messages_for_initializing_history(self) -> AWSNovaSonicConversationHistory:
+        """Get conversation history for initializing AWS Nova Sonic session.
+
+        Processes stored messages and extracts system instruction and conversation
+        history in the format expected by AWS Nova Sonic.
+
+        Returns:
+            Formatted conversation history with system instruction and messages.
+        """
+        history = AWSNovaSonicConversationHistory(system_instruction=self._system_instruction)
+
+        # Bail if there are no messages
+        if not self.messages:
+            return history
+
+        messages = copy.deepcopy(self.messages)
+
+        # If we have a "system" message as our first message, let's pull that out into "instruction"
+        if messages[0].get("role") == "system":
+            system = messages.pop(0)
+            content = system.get("content")
+            if isinstance(content, str):
+                history.system_instruction = content
+            elif isinstance(content, list):
+                history.system_instruction = content[0].get("text")
+            if history.system_instruction:
+                self._system_instruction = history.system_instruction
+
+        # Process remaining messages to fill out conversation history.
+        # Nova Sonic supports "user" and "assistant" messages in history.
+        for message in messages:
+            history_message = self.from_standard_message(message)
+            if history_message:
+                history.messages.append(history_message)
+
+        return history
+
+    def get_messages_for_persistent_storage(self):
+        """Get messages formatted for persistent storage.
+
+        Returns:
+            List of messages including system instruction if present.
+        """
+        messages = super().get_messages_for_persistent_storage()
+        # If we have a system instruction and messages doesn't already contain it, add it
+        if self._system_instruction and not (messages and messages[0].get("role") == "system"):
+            messages.insert(0, {"role": "system", "content": self._system_instruction})
+        return messages
+
+    def from_standard_message(self, message) -> AWSNovaSonicConversationHistoryMessage:
+        """Convert standard message format to Nova Sonic format.
+
+        Args:
+            message: Standard message dictionary to convert.
+
+        Returns:
+            Nova Sonic conversation history message, or None if not convertible.
+        """
+        role = message.get("role")
+        if message.get("role") == "user" or message.get("role") == "assistant":
+            content = message.get("content")
+            if isinstance(message.get("content"), list):
+                content = ""
+                for c in message.get("content"):
+                    if c.get("type") == "text":
+                        content += " " + c.get("text")
+                    else:
+                        logger.error(
+                            f"Unhandled content type in context message: {c.get('type')} - {message}"
+                        )
+            # There won't be content if this is an assistant tool call entry.
+            # We're ignoring those since they can't be loaded into AWS Nova Sonic conversation
+            # history
+            if content:
+                return AWSNovaSonicConversationHistoryMessage(role=Role[role.upper()], text=content)
+        # NOTE: we're ignoring messages with role "tool" since they can't be loaded into AWS Nova
+        # Sonic conversation history
+
+    def buffer_user_text(self, text):
+        """Buffer user text for later flushing to context.
+
+        Args:
+            text: User text to buffer.
+        """
+        self._user_text += f" {text}" if self._user_text else text
+        # logger.debug(f"User text buffered: {self._user_text}")
+
+    def flush_aggregated_user_text(self) -> str:
+        """Flush buffered user text to context as a complete message.
+
+        Returns:
+            The flushed user text, or empty string if no text was buffered.
+        """
+        if not self._user_text:
+            return ""
+        user_text = self._user_text
+        message = {
+            "role": "user",
+            "content": [{"type": "text", "text": user_text}],
+        }
+        self._user_text = ""
+        self.add_message(message)
+        # logger.debug(f"Context updated (user): {self.get_messages_for_logging()}")
+        return user_text
+
+    def buffer_assistant_text(self, text):
+        """Buffer assistant text for later flushing to context.
+
+        Args:
+            text: Assistant text to buffer.
+        """
+        self._assistant_text += text
+        # logger.debug(f"Assistant text buffered: {self._assistant_text}")
+
+    def flush_aggregated_assistant_text(self):
+        """Flush buffered assistant text to context as a complete message."""
+        if not self._assistant_text:
+            return
+        message = {
+            "role": "assistant",
+            "content": [{"type": "text", "text": self._assistant_text}],
+        }
+        self._assistant_text = ""
+        self.add_message(message)
+        # logger.debug(f"Context updated (assistant): {self.get_messages_for_logging()}")
+
+
+@dataclass
+class AWSNovaSonicMessagesUpdateFrame(DataFrame):
+    """Frame containing updated AWS Nova Sonic context.
+
+    Parameters:
+        context: The updated AWS Nova Sonic LLM context.
+    """
+
+    context: AWSNovaSonicLLMContext
+
+
+class AWSNovaSonicUserContextAggregator(OpenAIUserContextAggregator):
+    """Context aggregator for user messages in AWS Nova Sonic conversations.
+
+    Extends the OpenAI user context aggregator to emit Nova Sonic-specific
+    context update frames.
+    """
+
+    async def process_frame(
+        self, frame: Frame, direction: FrameDirection = FrameDirection.DOWNSTREAM
+    ):
+        """Process frames and emit Nova Sonic-specific context updates.
+
+        Args:
+            frame: The frame to process.
+            direction: The direction the frame is traveling.
+        """
+        await super().process_frame(frame, direction)
+
+        # Parent does not push LLMMessagesUpdateFrame
+        if isinstance(frame, LLMMessagesUpdateFrame):
+            await self.push_frame(AWSNovaSonicMessagesUpdateFrame(context=self._context))
+
+
+class AWSNovaSonicAssistantContextAggregator(OpenAIAssistantContextAggregator):
+    """Context aggregator for assistant messages in AWS Nova Sonic conversations.
+
+    Provides specialized handling for assistant responses and function calls
+    in AWS Nova Sonic context, with custom frame processing logic.
+    """
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        """Process frames with Nova Sonic-specific logic.
+
+        Args:
+            frame: The frame to process.
+            direction: The direction the frame is traveling.
+        """
+        # HACK: For now, disable the context aggregator by making it just pass through all frames
+        # that the parent handles (except the function call stuff, which we still need).
+        # For an explanation of this hack, see
+        # AWSNovaSonicLLMService._report_assistant_response_text_added.
+        if isinstance(
+            frame,
+            (
+                InterruptionFrame,
+                LLMFullResponseStartFrame,
+                LLMFullResponseEndFrame,
+                TextFrame,
+                LLMMessagesAppendFrame,
+                LLMMessagesUpdateFrame,
+                LLMSetToolsFrame,
+                LLMSetToolChoiceFrame,
+                UserImageRawFrame,
+                BotStoppedSpeakingFrame,
+            ),
+        ):
+            await self.push_frame(frame, direction)
+        else:
+            await super().process_frame(frame, direction)
+
+    async def handle_function_call_result(self, frame: FunctionCallResultFrame):
+        """Handle function call results for AWS Nova Sonic.
+
+        Args:
+            frame: The function call result frame to handle.
+        """
+        await super().handle_function_call_result(frame)
+
+        # The standard function callback code path pushes the FunctionCallResultFrame from the LLM
+        # itself, so we didn't have a chance to add the result to the AWS Nova Sonic server-side
+        # context. Let's push a special frame to do that.
+        await self.push_frame(
+            AWSNovaSonicFunctionCallResultFrame(result_frame=frame), FrameDirection.UPSTREAM
+        )
+
+
+@dataclass
+class AWSNovaSonicContextAggregatorPair:
+    """Pair of user and assistant context aggregators for AWS Nova Sonic.
+
+    Parameters:
+        _user: The user context aggregator.
+        _assistant: The assistant context aggregator.
+    """
+
+    _user: AWSNovaSonicUserContextAggregator
+    _assistant: AWSNovaSonicAssistantContextAggregator
+
+    def user(self) -> AWSNovaSonicUserContextAggregator:
+        """Get the user context aggregator.
+
+        Returns:
+            The user context aggregator instance.
+        """
+        return self._user
+
+    def assistant(self) -> AWSNovaSonicAssistantContextAggregator:
+        """Get the assistant context aggregator.
+
+        Returns:
+            The assistant context aggregator instance.
+        """
+        return self._assistant

src/pipecat/services/aws/nova_sonic/frames.py

@@ -0,0 +1,25 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Custom frames for AWS Nova Sonic LLM service."""
+
+from dataclasses import dataclass
+
+from pipecat.frames.frames import DataFrame, FunctionCallResultFrame
+
+
+@dataclass
+class AWSNovaSonicFunctionCallResultFrame(DataFrame):
+    """Frame containing function call result for AWS Nova Sonic processing.
+
+    This frame wraps a standard function call result frame to enable
+    AWS Nova Sonic-specific handling and context updates.
+
+    Parameters:
+        result_frame: The underlying function call result frame.
+    """
+
+    result_frame: FunctionCallResultFrame

src/pipecat/services/aws/stt.py

@@ -286,6 +286,7 @@ class AWSTranscribeSTTService(STTService):
 
                 logger.info(f"{self} Successfully connected to AWS Transcribe")
 
+                await self._call_event_handler("on_connected")
             except Exception as e:
                 logger.error(f"{self} Failed to connect to AWS Transcribe: {e}")
                 await self._disconnect()
@@ -310,6 +311,7 @@ class AWSTranscribeSTTService(STTService):
             logger.warning(f"{self} Error closing WebSocket connection: {e}")
         finally:
             self._ws_client = None
+            await self._call_event_handler("on_disconnected")
 
     def language_to_service_language(self, language: Language) -> str | None:
         """Convert internal language enum to AWS Transcribe language code.

src/pipecat/services/aws_nova_sonic/__init__.py

@@ -1 +1,19 @@
-from .aws import AWSNovaSonicLLMService, Params
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import warnings
+
+from pipecat.services.aws.nova_sonic.llm import AWSNovaSonicLLMService, Params
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.aws_nova_sonic are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.aws.nova_sonic.llm instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

src/pipecat/services/aws_nova_sonic/context.py

@@ -10,358 +10,16 @@ This module provides specialized context aggregators and message handling for AW
 including conversation history management and role-specific message processing.
 """
 
-import copy
-from dataclasses import dataclass, field
-from enum import Enum
-
-from loguru import logger
-
-from pipecat.frames.frames import (
-    BotStoppedSpeakingFrame,
-    DataFrame,
-    Frame,
-    FunctionCallResultFrame,
-    InterruptionFrame,
-    LLMFullResponseEndFrame,
-    LLMFullResponseStartFrame,
-    LLMMessagesAppendFrame,
-    LLMMessagesUpdateFrame,
-    LLMSetToolChoiceFrame,
-    LLMSetToolsFrame,
-    TextFrame,
-    UserImageRawFrame,
-)
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.processors.frame_processor import FrameDirection
-from pipecat.services.aws_nova_sonic.frames import AWSNovaSonicFunctionCallResultFrame
-from pipecat.services.openai.llm import (
-    OpenAIAssistantContextAggregator,
-    OpenAIUserContextAggregator,
-)
-
-
-class Role(Enum):
-    """Roles supported in AWS Nova Sonic conversations.
-
-    Parameters:
-        SYSTEM: System-level messages (not used in conversation history).
-        USER: Messages sent by the user.
-        ASSISTANT: Messages sent by the assistant.
-        TOOL: Messages sent by tools (not used in conversation history).
-    """
-
-    SYSTEM = "SYSTEM"
-    USER = "USER"
-    ASSISTANT = "ASSISTANT"
-    TOOL = "TOOL"
-
-
-@dataclass
-class AWSNovaSonicConversationHistoryMessage:
-    """A single message in AWS Nova Sonic conversation history.
-
-    Parameters:
-        role: The role of the message sender (USER or ASSISTANT only).
-        text: The text content of the message.
-    """
-
-    role: Role  # only USER and ASSISTANT
-    text: str
-
-
-@dataclass
-class AWSNovaSonicConversationHistory:
-    """Complete conversation history for AWS Nova Sonic initialization.
-
-    Parameters:
-        system_instruction: System-level instruction for the conversation.
-        messages: List of conversation messages between user and assistant.
-    """
-
-    system_instruction: str = None
-    messages: list[AWSNovaSonicConversationHistoryMessage] = field(default_factory=list)
-
-
-class AWSNovaSonicLLMContext(OpenAILLMContext):
-    """Specialized LLM context for AWS Nova Sonic service.
-
-    Extends OpenAI context with Nova Sonic-specific message handling,
-    conversation history management, and text buffering capabilities.
-    """
-
-    def __init__(self, messages=None, tools=None, **kwargs):
-        """Initialize AWS Nova Sonic LLM context.
-
-        Args:
-            messages: Initial messages for the context.
-            tools: Available tools for the context.
-            **kwargs: Additional arguments passed to parent class.
-        """
-        super().__init__(messages=messages, tools=tools, **kwargs)
-        self.__setup_local()
-
-    def __setup_local(self, system_instruction: str = ""):
-        self._assistant_text = ""
-        self._user_text = ""
-        self._system_instruction = system_instruction
-
-    @staticmethod
-    def upgrade_to_nova_sonic(
-        obj: OpenAILLMContext, system_instruction: str
-    ) -> "AWSNovaSonicLLMContext":
-        """Upgrade an OpenAI context to AWS Nova Sonic context.
-
-        Args:
-            obj: The OpenAI context to upgrade.
-            system_instruction: System instruction for the context.
-
-        Returns:
-            The upgraded AWS Nova Sonic context.
-        """
-        if isinstance(obj, OpenAILLMContext) and not isinstance(obj, AWSNovaSonicLLMContext):
-            obj.__class__ = AWSNovaSonicLLMContext
-            obj.__setup_local(system_instruction)
-        return obj
-
-    # NOTE: this method has the side-effect of updating _system_instruction from messages
-    def get_messages_for_initializing_history(self) -> AWSNovaSonicConversationHistory:
-        """Get conversation history for initializing AWS Nova Sonic session.
-
-        Processes stored messages and extracts system instruction and conversation
-        history in the format expected by AWS Nova Sonic.
-
-        Returns:
-            Formatted conversation history with system instruction and messages.
-        """
-        history = AWSNovaSonicConversationHistory(system_instruction=self._system_instruction)
-
-        # Bail if there are no messages
-        if not self.messages:
-            return history
-
-        messages = copy.deepcopy(self.messages)
-
-        # If we have a "system" message as our first message, let's pull that out into "instruction"
-        if messages[0].get("role") == "system":
-            system = messages.pop(0)
-            content = system.get("content")
-            if isinstance(content, str):
-                history.system_instruction = content
-            elif isinstance(content, list):
-                history.system_instruction = content[0].get("text")
-            if history.system_instruction:
-                self._system_instruction = history.system_instruction
-
-        # Process remaining messages to fill out conversation history.
-        # Nova Sonic supports "user" and "assistant" messages in history.
-        for message in messages:
-            history_message = self.from_standard_message(message)
-            if history_message:
-                history.messages.append(history_message)
-
-        return history
-
-    def get_messages_for_persistent_storage(self):
-        """Get messages formatted for persistent storage.
-
-        Returns:
-            List of messages including system instruction if present.
-        """
-        messages = super().get_messages_for_persistent_storage()
-        # If we have a system instruction and messages doesn't already contain it, add it
-        if self._system_instruction and not (messages and messages[0].get("role") == "system"):
-            messages.insert(0, {"role": "system", "content": self._system_instruction})
-        return messages
-
-    def from_standard_message(self, message) -> AWSNovaSonicConversationHistoryMessage:
-        """Convert standard message format to Nova Sonic format.
-
-        Args:
-            message: Standard message dictionary to convert.
-
-        Returns:
-            Nova Sonic conversation history message, or None if not convertible.
-        """
-        role = message.get("role")
-        if message.get("role") == "user" or message.get("role") == "assistant":
-            content = message.get("content")
-            if isinstance(message.get("content"), list):
-                content = ""
-                for c in message.get("content"):
-                    if c.get("type") == "text":
-                        content += " " + c.get("text")
-                    else:
-                        logger.error(
-                            f"Unhandled content type in context message: {c.get('type')} - {message}"
-                        )
-            # There won't be content if this is an assistant tool call entry.
-            # We're ignoring those since they can't be loaded into AWS Nova Sonic conversation
-            # history
-            if content:
-                return AWSNovaSonicConversationHistoryMessage(role=Role[role.upper()], text=content)
-        # NOTE: we're ignoring messages with role "tool" since they can't be loaded into AWS Nova
-        # Sonic conversation history
-
-    def buffer_user_text(self, text):
-        """Buffer user text for later flushing to context.
-
-        Args:
-            text: User text to buffer.
-        """
-        self._user_text += f" {text}" if self._user_text else text
-        # logger.debug(f"User text buffered: {self._user_text}")
-
-    def flush_aggregated_user_text(self) -> str:
-        """Flush buffered user text to context as a complete message.
-
-        Returns:
-            The flushed user text, or empty string if no text was buffered.
-        """
-        if not self._user_text:
-            return ""
-        user_text = self._user_text
-        message = {
-            "role": "user",
-            "content": [{"type": "text", "text": user_text}],
-        }
-        self._user_text = ""
-        self.add_message(message)
-        # logger.debug(f"Context updated (user): {self.get_messages_for_logging()}")
-        return user_text
-
-    def buffer_assistant_text(self, text):
-        """Buffer assistant text for later flushing to context.
-
-        Args:
-            text: Assistant text to buffer.
-        """
-        self._assistant_text += text
-        # logger.debug(f"Assistant text buffered: {self._assistant_text}")
-
-    def flush_aggregated_assistant_text(self):
-        """Flush buffered assistant text to context as a complete message."""
-        if not self._assistant_text:
-            return
-        message = {
-            "role": "assistant",
-            "content": [{"type": "text", "text": self._assistant_text}],
-        }
-        self._assistant_text = ""
-        self.add_message(message)
-        # logger.debug(f"Context updated (assistant): {self.get_messages_for_logging()}")
-
-
-@dataclass
-class AWSNovaSonicMessagesUpdateFrame(DataFrame):
-    """Frame containing updated AWS Nova Sonic context.
-
-    Parameters:
-        context: The updated AWS Nova Sonic LLM context.
-    """
-
-    context: AWSNovaSonicLLMContext
-
-
-class AWSNovaSonicUserContextAggregator(OpenAIUserContextAggregator):
-    """Context aggregator for user messages in AWS Nova Sonic conversations.
-
-    Extends the OpenAI user context aggregator to emit Nova Sonic-specific
-    context update frames.
-    """
-
-    async def process_frame(
-        self, frame: Frame, direction: FrameDirection = FrameDirection.DOWNSTREAM
-    ):
-        """Process frames and emit Nova Sonic-specific context updates.
-
-        Args:
-            frame: The frame to process.
-            direction: The direction the frame is traveling.
-        """
-        await super().process_frame(frame, direction)
-
-        # Parent does not push LLMMessagesUpdateFrame
-        if isinstance(frame, LLMMessagesUpdateFrame):
-            await self.push_frame(AWSNovaSonicMessagesUpdateFrame(context=self._context))
-
-
-class AWSNovaSonicAssistantContextAggregator(OpenAIAssistantContextAggregator):
-    """Context aggregator for assistant messages in AWS Nova Sonic conversations.
-
-    Provides specialized handling for assistant responses and function calls
-    in AWS Nova Sonic context, with custom frame processing logic.
-    """
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        """Process frames with Nova Sonic-specific logic.
-
-        Args:
-            frame: The frame to process.
-            direction: The direction the frame is traveling.
-        """
-        # HACK: For now, disable the context aggregator by making it just pass through all frames
-        # that the parent handles (except the function call stuff, which we still need).
-        # For an explanation of this hack, see
-        # AWSNovaSonicLLMService._report_assistant_response_text_added.
-        if isinstance(
-            frame,
-            (
-                InterruptionFrame,
-                LLMFullResponseStartFrame,
-                LLMFullResponseEndFrame,
-                TextFrame,
-                LLMMessagesAppendFrame,
-                LLMMessagesUpdateFrame,
-                LLMSetToolsFrame,
-                LLMSetToolChoiceFrame,
-                UserImageRawFrame,
-                BotStoppedSpeakingFrame,
-            ),
-        ):
-            await self.push_frame(frame, direction)
-        else:
-            await super().process_frame(frame, direction)
-
-    async def handle_function_call_result(self, frame: FunctionCallResultFrame):
-        """Handle function call results for AWS Nova Sonic.
-
-        Args:
-            frame: The function call result frame to handle.
-        """
-        await super().handle_function_call_result(frame)
-
-        # The standard function callback code path pushes the FunctionCallResultFrame from the LLM
-        # itself, so we didn't have a chance to add the result to the AWS Nova Sonic server-side
-        # context. Let's push a special frame to do that.
-        await self.push_frame(
-            AWSNovaSonicFunctionCallResultFrame(result_frame=frame), FrameDirection.UPSTREAM
-        )
-
-
-@dataclass
-class AWSNovaSonicContextAggregatorPair:
-    """Pair of user and assistant context aggregators for AWS Nova Sonic.
-
-    Parameters:
-        _user: The user context aggregator.
-        _assistant: The assistant context aggregator.
-    """
-
-    _user: AWSNovaSonicUserContextAggregator
-    _assistant: AWSNovaSonicAssistantContextAggregator
-
-    def user(self) -> AWSNovaSonicUserContextAggregator:
-        """Get the user context aggregator.
-
-        Returns:
-            The user context aggregator instance.
-        """
-        return self._user
-
-    def assistant(self) -> AWSNovaSonicAssistantContextAggregator:
-        """Get the assistant context aggregator.
-
-        Returns:
-            The assistant context aggregator instance.
-        """
-        return self._assistant
+import warnings
+
+from pipecat.services.aws.nova_sonic.context import *
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.aws_nova_sonic.context are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.aws.nova_sonic.context instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

src/pipecat/services/aws_nova_sonic/frames.py

@@ -6,20 +6,16 @@
 
 """Custom frames for AWS Nova Sonic LLM service."""
 
-from dataclasses import dataclass
+import warnings
 
-from pipecat.frames.frames import DataFrame, FunctionCallResultFrame
+from pipecat.services.aws.nova_sonic.frames import *
 
-
-@dataclass
-class AWSNovaSonicFunctionCallResultFrame(DataFrame):
-    """Frame containing function call result for AWS Nova Sonic processing.
-
-    This frame wraps a standard function call result frame to enable
-    AWS Nova Sonic-specific handling and context updates.
-
-    Parameters:
-        result_frame: The underlying function call result frame.
-    """
-
-    result_frame: FunctionCallResultFrame
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.aws_nova_sonic.frames are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.aws.nova_sonic.frames instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

src/pipecat/services/azure/realtime/llm.py

@@ -0,0 +1,65 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Azure OpenAI Realtime LLM service implementation."""
+
+from loguru import logger
+
+from pipecat.services.openai.realtime.llm import OpenAIRealtimeLLMService
+
+try:
+    from websockets.asyncio.client import connect as websocket_connect
+except ModuleNotFoundError as e:
+    logger.error(f"Exception: {e}")
+    logger.error("In order to use Azure Realtime, you need to `pip install pipecat-ai[openai]`.")
+    raise Exception(f"Missing module: {e}")
+
+
+class AzureRealtimeLLMService(OpenAIRealtimeLLMService):
+    """Azure OpenAI Realtime LLM service with Azure-specific authentication.
+
+    Extends the OpenAI Realtime service to work with Azure OpenAI endpoints,
+    using Azure's authentication headers and endpoint format. Provides the same
+    real-time audio and text communication capabilities as the base OpenAI service.
+    """
+
+    def __init__(
+        self,
+        *,
+        api_key: str,
+        base_url: str,
+        **kwargs,
+    ):
+        """Initialize Azure Realtime LLM service.
+
+        Args:
+            api_key: The API key for the Azure OpenAI service.
+            base_url: The full Azure WebSocket endpoint URL including api-version and deployment.
+                Example: "wss://my-project.openai.azure.com/openai/realtime?api-version=2024-10-01-preview&deployment=my-realtime-deployment"
+            **kwargs: Additional arguments passed to parent OpenAIRealtimeLLMService.
+        """
+        super().__init__(base_url=base_url, api_key=api_key, **kwargs)
+        self.api_key = api_key
+        self.base_url = base_url
+
+    async def _connect(self):
+        try:
+            if self._websocket:
+                # Here we assume that if we have a websocket, we are connected. We
+                # handle disconnections in the send/recv code paths.
+                return
+
+            logger.info(f"Connecting to {self.base_url}, api key: {self.api_key}")
+            self._websocket = await websocket_connect(
+                uri=self.base_url,
+                additional_headers={
+                    "api-key": self.api_key,
+                },
+            )
+            self._receive_task = self.create_task(self._receive_task_handler())
+        except Exception as e:
+            logger.error(f"{self} initialization error: {e}")
+            self._websocket = None

src/pipecat/services/cartesia/stt.py

@@ -28,13 +28,12 @@ from pipecat.frames.frames import (
     UserStoppedSpeakingFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
-from pipecat.services.stt_service import STTService
+from pipecat.services.stt_service import WebsocketSTTService
 from pipecat.transcriptions.language import Language
 from pipecat.utils.time import time_now_iso8601
 from pipecat.utils.tracing.service_decorators import traced_stt
 
 try:
-    import websockets
     from websockets.asyncio.client import connect as websocket_connect
     from websockets.protocol import State
 except ModuleNotFoundError as e:
@@ -124,7 +123,7 @@ class CartesiaLiveOptions:
         return cls(**json.loads(json_str))
 
 
-class CartesiaSTTService(STTService):
+class CartesiaSTTService(WebsocketSTTService):
     """Speech-to-text service using Cartesia Live API.
 
     Provides real-time speech transcription through WebSocket connection
@@ -176,8 +175,7 @@ class CartesiaSTTService(STTService):
         self.set_model_name(merged_options.model)
         self._api_key = api_key
         self._base_url = base_url or "api.cartesia.ai"
-        self._connection = None
-        self._receiver_task = None
+        self._receive_task = None
 
     def can_generate_metrics(self) -> bool:
         """Check if the service can generate processing metrics.
@@ -214,6 +212,27 @@ class CartesiaSTTService(STTService):
         await super().cancel(frame)
         await self._disconnect()
 
+    async def start_metrics(self):
+        """Start performance metrics collection for transcription processing."""
+        await self.start_ttfb_metrics()
+        await self.start_processing_metrics()
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        """Process incoming frames and handle speech events.
+
+        Args:
+            frame: The frame to process.
+            direction: Direction of frame flow in the pipeline.
+        """
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, UserStartedSpeakingFrame):
+            await self.start_metrics()
+        elif isinstance(frame, UserStoppedSpeakingFrame):
+            # Send finalize command to flush the transcription session
+            if self._websocket and self._websocket.state is State.OPEN:
+                await self._websocket.send("finalize")
+
     async def run_stt(self, audio: bytes) -> AsyncGenerator[Frame, None]:
         """Process audio data for speech-to-text transcription.
 
@@ -224,45 +243,71 @@ class CartesiaSTTService(STTService):
             None - transcription results are handled via WebSocket responses.
         """
         # If the connection is closed, due to timeout, we need to reconnect when the user starts speaking again
-        if not self._connection or self._connection.state is State.CLOSED:
+        if not self._websocket or self._websocket.state is State.CLOSED:
             await self._connect()
 
-        await self._connection.send(audio)
+        await self._websocket.send(audio)
         yield None
 
     async def _connect(self):
-        params = self._settings.to_dict()
-        ws_url = f"wss://{self._base_url}/stt/websocket?{urllib.parse.urlencode(params)}"
-        logger.debug(f"Connecting to Cartesia: {ws_url}")
-        headers = {"Cartesia-Version": "2025-04-16", "X-API-Key": self._api_key}
+        await self._connect_websocket()
 
+        if self._websocket and not self._receive_task:
+            self._receive_task = asyncio.create_task(self._receive_task_handler(self._report_error))
+
+    async def _disconnect(self):
+        if self._receive_task:
+            await self.cancel_task(self._receive_task)
+            self._receive_task = None
+
+        await self._disconnect_websocket()
+
+    async def _connect_websocket(self):
         try:
-            self._connection = await websocket_connect(ws_url, additional_headers=headers)
-            # Setup the receiver task to handle the incoming messages from the Cartesia server
-            if self._receiver_task is None or self._receiver_task.done():
-                self._receiver_task = asyncio.create_task(self._receive_messages())
-            logger.debug(f"Connected to Cartesia")
+            if self._websocket and self._websocket.state is State.OPEN:
+                return
+            logger.debug("Connecting to Cartesia STT")
+
+            params = self._settings.to_dict()
+            ws_url = f"wss://{self._base_url}/stt/websocket?{urllib.parse.urlencode(params)}"
+            headers = {"Cartesia-Version": "2025-04-16", "X-API-Key": self._api_key}
+
+            self._websocket = await websocket_connect(ws_url, additional_headers=headers)
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self}: unable to connect to Cartesia: {e}")
 
-    async def _receive_messages(self):
+    async def _disconnect_websocket(self):
         try:
-            while True:
-                if not self._connection or self._connection.state is State.CLOSED:
-                    break
-
-                message = await self._connection.recv()
-                try:
-                    data = json.loads(message)
-                    await self._process_response(data)
-                except json.JSONDecodeError:
-                    logger.warning(f"Received non-JSON message: {message}")
-        except asyncio.CancelledError:
-            pass
-        except websockets.exceptions.ConnectionClosed as e:
-            logger.debug(f"WebSocket connection closed: {e}")
+            if self._websocket and self._websocket.state is State.OPEN:
+                logger.debug("Disconnecting from Cartesia STT")
+                await self._websocket.close()
         except Exception as e:
-            logger.error(f"Error in message receiver: {e}")
+            logger.error(f"{self} error closing websocket: {e}")
+        finally:
+            self._websocket = None
+            await self._call_event_handler("on_disconnected")
+
+    def _get_websocket(self):
+        if self._websocket:
+            return self._websocket
+        raise Exception("Websocket not connected")
+
+    async def _process_messages(self):
+        async for message in self._get_websocket():
+            try:
+                data = json.loads(message)
+                await self._process_response(data)
+            except json.JSONDecodeError:
+                logger.warning(f"Received non-JSON message: {message}")
+
+    async def _receive_messages(self):
+        while True:
+            await self._process_messages()
+            # Cartesia times out after 5 minutes of innactivity (no keepalive
+            # mechanism is available). So, we try to reconnect.
+            logger.debug(f"{self} Cartesia connection was disconnected (timeout?), reconnecting")
+            await self._connect_websocket()
 
     async def _process_response(self, data):
         if "type" in data:
@@ -316,41 +361,3 @@ class CartesiaSTTService(STTService):
                         language,
                     )
                 )
-
-    async def _disconnect(self):
-        if self._receiver_task:
-            self._receiver_task.cancel()
-            try:
-                await self._receiver_task
-            except asyncio.CancelledError:
-                pass
-            except Exception as e:
-                logger.exception(f"Unexpected exception while cancelling task: {e}")
-            self._receiver_task = None
-
-        if self._connection and self._connection.state is State.OPEN:
-            logger.debug("Disconnecting from Cartesia")
-
-            await self._connection.close()
-            self._connection = None
-
-    async def start_metrics(self):
-        """Start performance metrics collection for transcription processing."""
-        await self.start_ttfb_metrics()
-        await self.start_processing_metrics()
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        """Process incoming frames and handle speech events.
-
-        Args:
-            frame: The frame to process.
-            direction: Direction of frame flow in the pipeline.
-        """
-        await super().process_frame(frame, direction)
-
-        if isinstance(frame, UserStartedSpeakingFrame):
-            await self.start_metrics()
-        elif isinstance(frame, UserStoppedSpeakingFrame):
-            # Send finalize command to flush the transcription session
-            if self._connection and self._connection.state is State.OPEN:
-                await self._connection.send("finalize")

src/pipecat/services/cartesia/tts.py

@@ -344,10 +344,11 @@ class CartesiaTTSService(AudioContextWordTTSService):
         try:
             if self._websocket and self._websocket.state is State.OPEN:
                 return
-            logger.debug("Connecting to Cartesia")
+            logger.debug("Connecting to Cartesia TTS")
             self._websocket = await websocket_connect(
                 f"{self._url}?api_key={self._api_key}&cartesia_version={self._cartesia_version}"
             )
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -365,6 +366,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
         finally:
             self._context_id = None
             self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     def _get_websocket(self):
         if self._websocket:

src/pipecat/services/deepgram/__init__.py

@@ -8,6 +8,7 @@ import sys
 
 from pipecat.services import DeprecatedModuleProxy
 
+from .flux import *
 from .stt import *
 from .tts import *
 

src/pipecat/services/deepgram/flux/stt.py

@@ -0,0 +1,640 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Deepgram Flux speech-to-text service implementation."""
+
+import json
+from enum import Enum
+from typing import Any, AsyncGenerator, Dict, Optional
+
+from loguru import logger
+from pydantic import BaseModel
+
+from pipecat.frames.frames import (
+    CancelFrame,
+    EndFrame,
+    ErrorFrame,
+    Frame,
+    InterimTranscriptionFrame,
+    StartFrame,
+    TranscriptionFrame,
+    UserStartedSpeakingFrame,
+    UserStoppedSpeakingFrame,
+)
+from pipecat.processors.frame_processor import FrameDirection
+from pipecat.services.stt_service import WebsocketSTTService
+from pipecat.transcriptions.language import Language
+from pipecat.utils.time import time_now_iso8601
+from pipecat.utils.tracing.service_decorators import traced_stt
+
+try:
+    from websockets.asyncio.client import connect as websocket_connect
+    from websockets.protocol import State
+except ModuleNotFoundError as e:
+    logger.error(f"Exception: {e}")
+    logger.error("In order to use Deepgram Flux, you need to `pip install pipecat-ai[deepgram]`.")
+    raise Exception(f"Missing module: {e}")
+
+
+class FluxMessageType(str, Enum):
+    """Deepgram Flux WebSocket message types.
+
+    These are the top-level message types that can be received from the
+    Deepgram Flux WebSocket connection.
+    """
+
+    RECEIVE_CONNECTED = "Connected"
+    RECEIVE_FATAL_ERROR = "Error"
+    TURN_INFO = "TurnInfo"
+
+
+class FluxEventType(str, Enum):
+    """Deepgram Flux TurnInfo event types.
+
+    These events are contained within TurnInfo messages and indicate
+    different stages of speech processing and turn detection.
+    """
+
+    START_OF_TURN = "StartOfTurn"
+    TURN_RESUMED = "TurnResumed"
+    END_OF_TURN = "EndOfTurn"
+    EAGER_END_OF_TURN = "EagerEndOfTurn"
+    UPDATE = "Update"
+
+
+class DeepgramFluxSTTService(WebsocketSTTService):
+    """Deepgram Flux speech-to-text service.
+
+    Provides real-time speech recognition using Deepgram's WebSocket API with Flux capabilities.
+    Supports configurable models, VAD events, and various audio processing options
+    including advanced turn detection and EagerEndOfTurn events for improved conversational AI performance.
+    """
+
+    class InputParams(BaseModel):
+        """Configuration parameters for Deepgram Flux API.
+
+        This class defines all available connection parameters for the Deepgram Flux API
+        based on the official documentation.
+
+        Parameters:
+            eager_eot_threshold: Optional. EagerEndOfTurn/TurnResumed are off by default.
+                You can turn them on by setting eager_eot_threshold to a valid value.
+                Lower values = more aggressive EagerEndOfTurning (faster response, more LLM calls).
+                Higher values = more conservative EagerEndOfTurning (slower response, fewer LLM calls).
+            eot_threshold: Optional. End-of-turn confidence required to finish a turn (default 0.7).
+                Lower values = turns end sooner (more interruptions, faster responses).
+                Higher values = turns end later (fewer interruptions, more complete utterances).
+            eot_timeout_ms: Optional. Time in milliseconds after speech to finish a turn
+                regardless of EOT confidence (default 5000).
+            keyterm: List of keyterms to boost recognition accuracy for specialized terminology.
+            mip_opt_out: Optional. Opts out requests from the Deepgram Model Improvement Program
+                (default False).
+            tag: List of tags to label requests for identification during usage reporting.
+        """
+
+        eager_eot_threshold: Optional[float] = None
+        eot_threshold: Optional[float] = None
+        eot_timeout_ms: Optional[int] = None
+        keyterm: list = []
+        mip_opt_out: Optional[bool] = None
+        tag: list = []
+
+    def __init__(
+        self,
+        *,
+        api_key: str,
+        url: str = "wss://api.deepgram.com/v2/listen",
+        sample_rate: Optional[int] = None,
+        model: str = "flux-general-en",
+        flux_encoding: str = "linear16",
+        params: Optional[InputParams] = None,
+        **kwargs,
+    ):
+        """Initialize the Deepgram Flux STT service.
+
+        Args:
+            api_key: Deepgram API key for authentication. Required for API access.
+            url: WebSocket URL for the Deepgram Flux API. Defaults to the preview endpoint.
+            sample_rate: Audio sample rate in Hz. If None, uses the rate from params or 16000.
+            model: Deepgram Flux model to use for transcription. Currently only supports "flux-general-en".
+            flux_encoding: Audio encoding format required by Flux API. Must be "linear16".
+                Raw signed little-endian 16-bit PCM encoding.
+            params: InputParams instance containing detailed API configuration options.
+                If None, default parameters will be used.
+            **kwargs: Additional arguments passed to the parent WebsocketSTTService class.
+
+        Examples:
+            Basic usage with default parameters::
+
+                stt = DeepgramFluxSTTService(api_key="your-api-key")
+
+            Advanced usage with custom parameters::
+
+                params = DeepgramFluxSTTService.InputParams(
+                    eager_eot_threshold=0.5,
+                    eot_threshold=0.8,
+                    keyterm=["AI", "machine learning", "neural network"],
+                    tag=["production", "voice-agent"]
+                )
+                stt = DeepgramFluxSTTService(
+                    api_key="your-api-key",
+                    model="flux-general-en",
+                    params=params
+                )
+        """
+        super().__init__(sample_rate=sample_rate, **kwargs)
+
+        self._api_key = api_key
+        self._url = url
+        self._model = model
+        self._params = params or DeepgramFluxSTTService.InputParams()
+        self._flux_encoding = flux_encoding
+        # This is the currently only supported language
+        self._language = Language.EN
+        self._websocket_url = None
+        self._receive_task = None
+
+    async def _connect(self):
+        """Connect to WebSocket and start background tasks.
+
+        Establishes the WebSocket connection to the Deepgram Flux API and starts
+        the background task for receiving transcription results.
+        """
+        await self._connect_websocket()
+
+        if self._websocket and not self._receive_task:
+            self._receive_task = self.create_task(self._receive_task_handler(self._report_error))
+
+    async def _disconnect(self):
+        """Disconnect from WebSocket and clean up tasks.
+
+        Gracefully disconnects from the Deepgram Flux API, cancels background tasks,
+        and cleans up resources to prevent memory leaks.
+        """
+        try:
+            # Cancel background tasks BEFORE closing websocket
+            if self._receive_task:
+                await self.cancel_task(self._receive_task, timeout=2.0)
+                self._receive_task = None
+
+            # Now close the websocket
+            await self._disconnect_websocket()
+
+        except Exception as e:
+            logger.error(f"Error during disconnect: {e}")
+        finally:
+            # Reset state only after everything is cleaned up
+            self._websocket = None
+
+    async def _connect_websocket(self):
+        """Establish WebSocket connection to API.
+
+        Creates a WebSocket connection to the Deepgram Flux API using the configured
+        URL and authentication headers. Handles connection errors and reports them
+        through the event handler system.
+        """
+        try:
+            if self._websocket and self._websocket.state is State.OPEN:
+                return
+
+            self._websocket = await websocket_connect(
+                self._websocket_url,
+                additional_headers={"Authorization": f"Token {self._api_key}"},
+            )
+            logger.debug("Connected to Deepgram Flux Websocket")
+            await self._call_event_handler("on_connected")
+        except Exception as e:
+            logger.error(f"{self} initialization error: {e}")
+            self._websocket = None
+            await self._call_event_handler("on_connection_error", f"{e}")
+
+    async def _disconnect_websocket(self):
+        """Close WebSocket connection and clean up state.
+
+        Closes the WebSocket connection to the Deepgram Flux API and stops all
+        metrics collection. Handles disconnection errors gracefully.
+        """
+        try:
+            await self.stop_all_metrics()
+
+            if self._websocket:
+                await self._send_close_stream()
+                logger.debug("Disconnecting from Deepgram Flux Websocket")
+                await self._websocket.close()
+        except Exception as e:
+            logger.error(f"{self} error closing websocket: {e}")
+        finally:
+            self._websocket = None
+            await self._call_event_handler("on_disconnected")
+
+    async def _send_close_stream(self) -> None:
+        """Sends a CloseStream control message to the Deepgram Flux WebSocket API.
+
+        This signals to the server that no more audio data will be sent.
+        """
+        if self._websocket:
+            logger.debug("Sending CloseStream message to Deepgram Flux")
+            message = {"type": "CloseStream"}
+            await self._websocket.send(json.dumps(message))
+
+    def can_generate_metrics(self) -> bool:
+        """Check if this service can generate processing metrics.
+
+        Returns:
+            True, as Deepgram service supports metrics generation.
+        """
+        return True
+
+    async def start(self, frame: StartFrame):
+        """Start the Deepgram Flux STT service.
+
+        Initializes the service by constructing the WebSocket URL with all configured
+        parameters and establishing the connection to begin transcription processing.
+
+        Args:
+            frame: The start frame containing initialization parameters and metadata.
+        """
+        await super().start(frame)
+
+        url_params = [
+            f"model={self._model}",
+            f"sample_rate={self.sample_rate}",
+            f"encoding={self._flux_encoding}",
+        ]
+
+        if self._params.eager_eot_threshold is not None:
+            url_params.append(f"eager_eot_threshold={self._params.eager_eot_threshold}")
+
+        if self._params.eot_threshold is not None:
+            url_params.append(f"eot_threshold={self._params.eot_threshold}")
+
+        if self._params.eot_timeout_ms is not None:
+            url_params.append(f"eot_timeout_ms={self._params.eot_timeout_ms}")
+
+        if self._params.mip_opt_out is not None:
+            url_params.append(f"mip_opt_out={str(self._params.mip_opt_out).lower()}")
+
+        # Add keyterm parameters (can have multiple)
+        for keyterm in self._params.keyterm:
+            url_params.append(f"keyterm={keyterm}")
+
+        # Add tag parameters (can have multiple)
+        for tag_value in self._params.tag:
+            url_params.append(f"tag={tag_value}")
+
+        self._websocket_url = f"{self._url}?{'&'.join(url_params)}"
+        await self._connect()
+
+    async def stop(self, frame: EndFrame):
+        """Stop the Deepgram Flux STT service.
+
+        Args:
+            frame: The end frame.
+        """
+        await super().stop(frame)
+        await self._disconnect()
+
+    async def cancel(self, frame: CancelFrame):
+        """Cancel the Deepgram Flux STT service.
+
+        Args:
+            frame: The cancel frame.
+        """
+        await super().cancel(frame)
+        await self._disconnect()
+
+    async def run_stt(self, audio: bytes) -> AsyncGenerator[Frame, None]:
+        """Send audio data to Deepgram Flux for transcription.
+
+        Transmits raw audio bytes to the Deepgram Flux API for real-time speech
+        recognition. Transcription results are received asynchronously through
+        WebSocket callbacks and processed in the background.
+
+        Args:
+            audio: Raw audio bytes in linear16 format (signed little-endian 16-bit PCM).
+
+        Yields:
+            Frame: None (transcription results are delivered via WebSocket callbacks
+                rather than as return values from this method).
+
+        Raises:
+            Exception: If the WebSocket connection is not established or if there
+                are issues sending the audio data.
+        """
+        if not self._websocket:
+            logger.error("Not connected to Deepgram Flux.")
+            yield ErrorFrame("Not connected to Deepgram Flux.", fatal=True)
+            return
+
+        try:
+            await self._websocket.send(audio)
+        except Exception as e:
+            logger.error(f"Failed to send audio to Flux: {e}")
+            yield ErrorFrame(f"Failed to send audio to Flux:  {e}")
+            return
+
+        yield None
+
+    async def start_metrics(self):
+        """Start TTFB and processing metrics collection."""
+        # TTFB (Time To First Byte) metrics are currently disabled for Deepgram Flux.
+        # Ideally, TTFB should measure the time from when a user starts speaking
+        # until we receive the first transcript. However, Deepgram Flux delivers
+        # both the "user started speaking" event and the first transcript simultaneously,
+        # making this timing measurement meaningless in this context.
+        # await self.start_ttfb_metrics()
+        await self.start_processing_metrics()
+
+    @traced_stt
+    async def _handle_transcription(
+        self, transcript: str, is_final: bool, language: Optional[Language] = None
+    ):
+        """Handle a transcription result with tracing."""
+        pass
+
+    def _get_websocket(self):
+        """Get the current WebSocket connection.
+
+        Returns the active WebSocket connection instance, raising an exception
+        if no connection is currently established.
+
+        Returns:
+            The active WebSocket connection instance.
+
+        Raises:
+            Exception: If no WebSocket connection is currently active.
+        """
+        if self._websocket:
+            return self._websocket
+        raise Exception("Websocket not connected")
+
+    def _validate_message(self, data: Dict[str, Any]) -> bool:
+        """Validate basic message structure from Deepgram Flux.
+
+        Ensures the received message has the expected structure before processing.
+
+        Args:
+            data: The parsed JSON message data to validate.
+
+        Returns:
+            True if the message structure is valid, False otherwise.
+        """
+        if not isinstance(data, dict):
+            logger.warning("Message is not a dictionary")
+            return False
+
+        if "type" not in data:
+            logger.warning("Message missing 'type' field")
+            return False
+
+        return True
+
+    async def _receive_messages(self):
+        """Receive and process messages from WebSocket.
+
+        Continuously receives messages from the Deepgram Flux WebSocket connection
+        and processes various message types including connection status, transcription
+        results, turn information, and error conditions. Handles different event types
+        such as StartOfTurn, EndOfTurn, EagerEndOfTurn, and Update events.
+        """
+        async for message in self._get_websocket():
+            if isinstance(message, str):
+                try:
+                    data = json.loads(message)
+                    await self._handle_message(data)
+                except json.JSONDecodeError as e:
+                    logger.error(f"Failed to decode JSON message: {e}")
+                    # Skip malformed messages
+                    continue
+                except Exception as e:
+                    logger.error(f"Error processing message: {e}")
+                    # Error will be handled inside WebsocketService->_receive_task_handler
+                    raise
+            else:
+                logger.warning(f"Received non-string message: {type(message)}")
+
+    async def _handle_message(self, data: Dict[str, Any]):
+        """Handle a parsed WebSocket message from Deepgram Flux.
+
+        Routes messages to appropriate handlers based on their type. Validates
+        message structure before processing.
+
+        Args:
+            data: The parsed JSON message data from the WebSocket.
+        """
+        if not self._validate_message(data):
+            return
+
+        message_type = data.get("type")
+
+        try:
+            flux_message_type = FluxMessageType(message_type)
+        except ValueError:
+            logger.debug(f"Unhandled message type: {message_type or 'unknown'}")
+            return
+
+        match flux_message_type:
+            case FluxMessageType.RECEIVE_CONNECTED:
+                await self._handle_connection_established()
+            case FluxMessageType.RECEIVE_FATAL_ERROR:
+                await self._handle_fatal_error(data)
+            case FluxMessageType.TURN_INFO:
+                await self._handle_turn_info(data)
+
+    async def _handle_connection_established(self):
+        """Handle successful connection establishment to Deepgram Flux.
+
+        This event is fired when the WebSocket connection to Deepgram Flux
+        is successfully established and ready to receive audio data for
+        transcription processing.
+        """
+        logger.info("Connected to Flux - ready to stream audio")
+
+    async def _handle_fatal_error(self, data: Dict[str, Any]):
+        """Handle fatal error messages from Deepgram Flux.
+
+        Fatal errors indicate unrecoverable issues with the connection or
+        configuration that require intervention. These errors will cause
+        the connection to be terminated.
+
+        Args:
+            data: The error message data containing error details.
+
+        Raises:
+            Exception: Always raises to trigger error handling in the parent service.
+        """
+        error_msg = data.get("error", "Unknown error")
+        deepgram_error = f"Fatal error: {error_msg}"
+        logger.error(deepgram_error)
+        # Error will be handled inside WebsocketService->_receive_task_handler
+        raise Exception(deepgram_error)
+
+    async def _handle_turn_info(self, data: Dict[str, Any]):
+        """Handle TurnInfo events from Deepgram Flux.
+
+        TurnInfo messages contain various turn-based events that indicate
+        the state of speech processing, including turn boundaries, interim
+        results, and turn finalization events.
+
+        Args:
+            data: The TurnInfo message data containing event type, transcript and some extra metadata.
+        """
+        event = data.get("event")
+        transcript = data.get("transcript", "")
+
+        try:
+            flux_event_type = FluxEventType(event)
+        except ValueError:
+            logger.debug(f"Unhandled TurnInfo event: {event}")
+            return
+
+        match flux_event_type:
+            case FluxEventType.START_OF_TURN:
+                await self._handle_start_of_turn(transcript)
+            case FluxEventType.TURN_RESUMED:
+                await self._handle_turn_resumed(event)
+            case FluxEventType.END_OF_TURN:
+                await self._handle_end_of_turn(transcript, data)
+            case FluxEventType.EAGER_END_OF_TURN:
+                await self._handle_eager_end_of_turn(transcript, data)
+            case FluxEventType.UPDATE:
+                await self._handle_update(transcript)
+
+    async def _handle_start_of_turn(self, transcript: str):
+        """Handle StartOfTurn events from Deepgram Flux.
+
+        StartOfTurn events are fired when Deepgram Flux detects the beginning
+        of a new speaking turn. This triggers bot interruption to stop any
+        ongoing speech synthesis and signals the start of user speech detection.
+
+        The service will:
+        - Send a BotInterruptionFrame upstream to stop bot speech
+        - Send a UserStartedSpeakingFrame downstream to notify other components
+        - Start metrics collection for measuring response times
+
+        Args:
+            transcript: maybe the first few words of the turn.
+        """
+        logger.debug("User started speaking")
+        await self.push_interruption_task_frame_and_wait()
+        await self.push_frame(UserStartedSpeakingFrame(), FrameDirection.DOWNSTREAM)
+        await self.push_frame(UserStartedSpeakingFrame(), FrameDirection.UPSTREAM)
+        await self.start_metrics()
+        if transcript:
+            logger.trace(f"Start of turn transcript: {transcript}")
+
+    async def _handle_turn_resumed(self, event: str):
+        """Handle TurnResumed events from Deepgram Flux.
+
+        TurnResumed events indicate that speech has resumed after a brief pause
+        within the same turn. This is primarily used for logging and debugging
+        purposes and doesn't trigger any significant processing changes.
+
+        Args:
+            event: The event type string for logging purposes.
+        """
+        logger.trace(f"Received event TurnResumed: {event}")
+
+    async def _handle_end_of_turn(self, transcript: str, data: Dict[str, Any]):
+        """Handle EndOfTurn events from Deepgram Flux.
+
+        EndOfTurn events are fired when Deepgram Flux determines that a speaking
+        turn has concluded, either due to sufficient silence or end-of-turn
+        confidence thresholds being met. This provides the final transcript
+        for the completed turn.
+
+        The service will:
+        - Create and send a final TranscriptionFrame with the complete transcript
+        - Trigger transcription handling with tracing for metrics
+        - Stop processing metrics collection
+        - Send a UserStoppedSpeakingFrame to signal turn completion
+
+        Args:
+            transcript: The final transcript text for the completed turn.
+            data: The TurnInfo message data containing event type, transcript and some extra metadata.
+        """
+        logger.debug("User stopped speaking")
+
+        await self.push_frame(
+            TranscriptionFrame(
+                transcript,
+                self._user_id,
+                time_now_iso8601(),
+                self._language,
+                result=data,
+            )
+        )
+        await self._handle_transcription(transcript, True, self._language)
+        await self.stop_processing_metrics()
+        await self.push_frame(UserStoppedSpeakingFrame(), FrameDirection.DOWNSTREAM)
+        await self.push_frame(UserStoppedSpeakingFrame(), FrameDirection.UPSTREAM)
+
+    async def _handle_eager_end_of_turn(self, transcript: str, data: Dict[str, Any]):
+        """Handle EagerEndOfTurn events from Deepgram Flux.
+
+        EagerEndOfTurn events are fired when the end-of-turn confidence reaches the
+        EagerEndOfTurn threshold but hasn't yet reached the full end-of-turn threshold.
+        These provide interim transcripts that can be used for faster response
+        generation while still allowing the user to continue speaking.
+
+        EagerEndOfTurn events enable more responsive conversational AI by allowing
+        the LLM to start processing likely final transcripts before the turn
+        is definitively ended.
+
+        Args:
+            transcript: The interim transcript text that triggered the EagerEndOfTurn event.
+            data: The TurnInfo message data containing event type, transcript and some extra metadata.
+        """
+        logger.trace(f"EagerEndOfTurn - {transcript}")
+        # Deepgram's EagerEndOfTurn feature enables lower-latency voice agents by sending
+        # medium-confidence transcripts before EndOfTurn certainty, allowing LLM processing to
+        # begin early.
+        #
+        # However, if speech resumes or the transcripts differ from the final EndOfTurn, the
+        # EagerEndOfTurn response should be cancelled to avoid incorrect or partial responses.
+        #
+        # Pipecat doesn't yet provide built-in Gate/control mechanisms to:
+        # 1. Start LLM/TTS processing early on EagerEndOfTurn events
+        # 2. Cancel in-flight processing when TurnResumed occurs
+        #
+        # By pushing EagerEndOfTurn transcripts as InterimTranscriptionFrame, we enable
+        # developers to implement custom EagerEndOfTurn handling in their applications while
+        # maintaining compatibility with existing interim transcription workflows.
+        #
+        # TODO: Implement proper EagerEndOfTurn support with cancellable processing pipeline
+        # that can start response generation on EagerEndOfTurn and cancel or confirm it.
+        await self.push_frame(
+            InterimTranscriptionFrame(
+                transcript,
+                self._user_id,
+                time_now_iso8601(),
+                self._language,
+                result=data,
+            )
+        )
+
+    async def _handle_update(self, transcript: str):
+        """Handle Update events from Deepgram Flux.
+
+        Update events provide incremental transcript updates during an ongoing
+        turn. These events allow for real-time display of transcription progress
+        and can be used to provide visual feedback to users about what's being
+        recognized.
+
+        The service stops TTFB (Time To First Byte) metrics when the first
+        substantial update is received, indicating successful processing start.
+
+        Args:
+            transcript: The current partial transcript text for the ongoing turn.
+        """
+        if transcript:
+            logger.trace(f"Update event: {transcript}")
+            # TTFB (Time To First Byte) metrics are currently disabled for Deepgram Flux.
+            # Ideally, TTFB should measure the time from when a user starts speaking
+            # until we receive the first transcript. However, Deepgram Flux delivers
+            # both the "user started speaking" event and the first transcript simultaneously,
+            # making this timing measurement meaningless in this context.
+            # await self.stop_ttfb_metrics()