docs: add a demo showing how to track usage

runner: allow subdirectories in --folder

.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

@@ -9,6 +9,127 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- The runner `--folder` argument now supports downloading files from
+  subdirectories.
+
+### Fixed
+
+- Fixed an issue where `RimeHttpTTSService` and `PiperTTSService` could generate
+  incorrectly 16-bit aligned audio frames, potentially leading to internal
+  errors or static audio.
+
+## [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.
@@ -28,23 +149,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Deprecated
 
-- `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.
-
-### Deprecated
-
 - `DailyTransportMessageFrame` and `DailyTransportMessageUrgentFrame` are
   deprecated, use `DailyOutputTransportMessageFrame` and
   `DailyOutputTransportMessageUrgentFrame` respectively instead.
@@ -60,6 +164,21 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - `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
@@ -1381,7 +1500,7 @@ 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
 
@@ -3387,7 +3506,7 @@ 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
@@ -3574,9 +3693,9 @@ 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
 
@@ -81,7 +72,7 @@ You can connect to Pipecat from any platform using our official SDKs:
 | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | 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) |
+| 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)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
@@ -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`.

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/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/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/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/18-openai-realtime-usage.py

@@ -0,0 +1,156 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Example: Print OpenAI Realtime API Token Usage Statistics
+
+This example demonstrates how to access and print token usage statistics
+from the OpenAI Realtime API, including detailed breakdowns of input/output
+tokens, cached tokens, and audio/text token usage.
+"""
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.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
+
+load_dotenv(override=True)
+
+# We store functions so objects don't get instantiated until the desired
+# transport gets selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    """Main function demonstrating usage statistics tracking."""
+    logger.info(f"Starting bot")
+
+    # Initialize the OpenAI Realtime service
+    llm = OpenAIRealtimeLLMService(
+        api_key=os.getenv("OPENAI_API_KEY") or "",
+        model="gpt-4o-realtime-preview-2024-12-17",
+    )
+
+    # To access usage statistics, we wrap the internal response handler
+    # This is the cleanest way to intercept usage data from the realtime API
+    original_handler = llm._handle_evt_response_done
+
+    async def custom_response_done_handler(evt):
+        """Custom handler that prints usage stats before calling original handler."""
+        # Print usage statistics if available
+        if evt.response.usage:
+            usage = evt.response.usage
+
+            logger.info("\n" + "=" * 50)
+            logger.info("📊 TOKEN USAGE STATISTICS")
+            logger.info("=" * 50)
+            logger.info(f"Total tokens: {usage.total_tokens}")
+            logger.info(f"Input tokens: {usage.input_tokens}")
+            logger.info(f"Output tokens: {usage.output_tokens}")
+
+            # Input token details
+            if usage.input_token_details:
+                logger.info(f"\n📥 Input token breakdown:")
+                logger.info(f"  • Cached tokens: {usage.input_token_details.cached_tokens}")
+                logger.info(f"  • Text tokens: {usage.input_token_details.text_tokens}")
+                logger.info(f"  • Audio tokens: {usage.input_token_details.audio_tokens}")
+
+                # Cached token details if available
+                if usage.input_token_details.cached_tokens_details:
+                    logger.info(
+                        f"  • Cached text tokens: {usage.input_token_details.cached_tokens_details.text_tokens}"
+                    )
+                    logger.info(
+                        f"  • Cached audio tokens: {usage.input_token_details.cached_tokens_details.audio_tokens}"
+                    )
+
+            # Output token details
+            if usage.output_token_details:
+                logger.info(f"\n📤 Output token breakdown:")
+                logger.info(f"  • Text tokens: {usage.output_token_details.text_tokens}")
+                logger.info(f"  • Audio tokens: {usage.output_token_details.audio_tokens}")
+
+            logger.info("=" * 50 + "\n")
+
+        # Call the original handler to maintain normal functionality
+        await original_handler(evt)
+
+    # Replace the handler with our custom one
+    llm._handle_evt_response_done = custom_response_done_handler
+
+    # Create pipeline
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            llm,
+            transport.output(),
+        ]
+    )
+
+    # Create task
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info("Client connected")
+        logger.info("🎤 Speak into your microphone to interact with the assistant")
+        logger.info("📊 Usage statistics will be printed after each response")
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info("Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/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/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/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
 

pyproject.toml

@@ -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" ]

scripts/evals/run-release-evals.py

@@ -75,8 +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),
@@ -103,6 +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.
@@ -148,7 +147,10 @@ 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),
@@ -161,18 +163,18 @@ 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,
@@ -180,7 +182,13 @@ 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/pipeline/task.py

@@ -130,12 +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")
@@ -146,9 +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__(
@@ -286,6 +298,7 @@ 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:
@@ -692,12 +705,11 @@ 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/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

@@ -42,7 +42,7 @@ from pipecat.frames.frames import (
     Frame,
     FunctionCallResultFrame,
     InputAudioRawFrame,
-    InputTransportMessageUrgentFrame,
+    InputTransportMessageFrame,
     InterimTranscriptionFrame,
     LLMConfigureOutputFrame,
     LLMContextFrame,
@@ -1421,7 +1421,7 @@ class RTVIProcessor(FrameProcessor):
         elif isinstance(frame, ErrorFrame):
             await self._send_error_frame(frame)
             await self.push_frame(frame, direction)
-        elif isinstance(frame, InputTransportMessageUrgentFrame):
+        elif isinstance(frame, InputTransportMessageFrame):
             await self._handle_transport_message(frame)
         # All other system frames
         elif isinstance(frame, SystemFrame):
@@ -1484,7 +1484,7 @@ class RTVIProcessor(FrameProcessor):
             await self._handle_message(message)
             self._message_queue.task_done()
 
-    async def _handle_transport_message(self, frame: InputTransportMessageUrgentFrame):
+    async def _handle_transport_message(self, frame: InputTransportMessageFrame):
         """Handle an incoming transport message frame."""
         try:
             transport_message = frame.message

src/pipecat/runner/run.py

@@ -67,12 +67,15 @@ To run locally:
 
 import argparse
 import asyncio
+import mimetypes
 import os
 import sys
 from contextlib import asynccontextmanager
+from pathlib import Path
 from typing import Optional
 
 import aiohttp
+from fastapi.responses import FileResponse
 from loguru import logger
 
 from pipecat.runner.types import (
@@ -84,7 +87,7 @@ from pipecat.runner.types import (
 try:
     import uvicorn
     from dotenv import load_dotenv
-    from fastapi import BackgroundTasks, FastAPI, HTTPException, 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:
@@ -98,6 +101,12 @@ 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."""
@@ -152,7 +161,12 @@ 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,
+    folder: Optional[str] = None,
 ):
     """Create FastAPI app with transport-specific routes."""
     app = FastAPI()
@@ -167,19 +181,21 @@ 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)
         _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
@@ -201,6 +217,21 @@ 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
@@ -275,6 +306,7 @@ def _setup_whatsapp_routes(app: FastAPI):
     WHATSAPP_TOKEN = os.getenv("WHATSAPP_TOKEN")
     WHATSAPP_PHONE_NUMBER_ID = os.getenv("WHATSAPP_PHONE_NUMBER_ID")
     WHATSAPP_WEBHOOK_VERIFICATION_TOKEN = os.getenv("WHATSAPP_WEBHOOK_VERIFICATION_TOKEN")
+    WHATSAPP_APP_SECRET = os.getenv("WHATSAPP_APP_SECRET")
 
     if not all(
         [
@@ -325,7 +357,12 @@ def _setup_whatsapp_routes(app: FastAPI):
         summary="Handle WhatsApp webhook events",
         description="Processes incoming WhatsApp messages and call events",
     )
-    async def whatsapp_webhook(body: WhatsAppWebhookRequest, background_tasks: BackgroundTasks):
+    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
@@ -357,7 +394,10 @@ def _setup_whatsapp_routes(app: FastAPI):
 
         try:
             # Process the webhook request
-            result = await whatsapp_client.handle_webhook_request(body, connection_callback)
+            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:
@@ -376,6 +416,7 @@ def _setup_whatsapp_routes(app: FastAPI):
         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,
             )
@@ -479,7 +520,7 @@ 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 = {
@@ -582,6 +623,21 @@ 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.
 
@@ -602,14 +658,16 @@ 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",
     )
@@ -627,6 +685,7 @@ 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"
     )
@@ -649,6 +708,10 @@ 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")
@@ -679,8 +742,18 @@ 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,
+        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::
 

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/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/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/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_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/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

@@ -79,7 +79,7 @@ class DeepgramFluxSTTService(WebsocketSTTService):
         This class defines all available connection parameters for the Deepgram Flux API
         based on the official documentation.
 
-        Attributes:
+        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).
@@ -126,24 +126,24 @@ class DeepgramFluxSTTService(WebsocketSTTService):
                 If None, default parameters will be used.
             **kwargs: Additional arguments passed to the parent WebsocketSTTService class.
 
-        Example:
-            ```python
-            # Basic usage with default parameters
-            stt = DeepgramFluxSTTService(api_key="your-api-key")
+        Examples:
+            Basic usage with default parameters::
 
-            # 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
-            )
-            ```
+                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)
 

src/pipecat/services/elevenlabs/__init__.py

@@ -8,6 +8,7 @@ import sys
 
 from pipecat.services import DeprecatedModuleProxy
 
+from .stt import *
 from .tts import *
 
-sys.modules[__name__] = DeprecatedModuleProxy(globals(), "elevenlabs", "elevenlabs.tts")
+sys.modules[__name__] = DeprecatedModuleProxy(globals(), "elevenlabs", "elevenlabs.[stt,tts]")

src/pipecat/services/gemini_multimodal_live/events.py

@@ -4,527 +4,41 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""Event models and utilities for Google Gemini Multimodal Live API."""
-
-import base64
-import io
-import json
-from enum import Enum
-from typing import List, Literal, Optional
-
-from PIL import Image
-from pydantic import BaseModel, Field
-
-from pipecat.frames.frames import ImageRawFrame
-
-#
-# Client events
-#
-
-
-class MediaChunk(BaseModel):
-    """Represents a chunk of media data for transmission.
-
-    Parameters:
-        mimeType: MIME type of the media content.
-        data: Base64-encoded media data.
-    """
-
-    mimeType: str
-    data: str
-
-
-class ContentPart(BaseModel):
-    """Represents a part of content that can contain text or media.
-
-    Parameters:
-        text: Text content. Defaults to None.
-        inlineData: Inline media data. Defaults to None.
-    """
-
-    text: Optional[str] = Field(default=None, validate_default=False)
-    inlineData: Optional[MediaChunk] = Field(default=None, validate_default=False)
-    fileData: Optional["FileData"] = Field(default=None, validate_default=False)
-
-
-class FileData(BaseModel):
-    """Represents a file reference in the Gemini File API."""
-
-    mimeType: str
-    fileUri: str
-
-
-ContentPart.model_rebuild()  # Rebuild model to resolve forward reference
-
-
-class Turn(BaseModel):
-    """Represents a conversational turn in the dialogue.
-
-    Parameters:
-        role: The role of the speaker, either "user" or "model". Defaults to "user".
-        parts: List of content parts that make up the turn.
-    """
-
-    role: Literal["user", "model"] = "user"
-    parts: List[ContentPart]
-
-
-class StartSensitivity(str, Enum):
-    """Determines how start of speech is detected."""
-
-    UNSPECIFIED = "START_SENSITIVITY_UNSPECIFIED"  # Default is HIGH
-    HIGH = "START_SENSITIVITY_HIGH"  # Detect start of speech more often
-    LOW = "START_SENSITIVITY_LOW"  # Detect start of speech less often
-
-
-class EndSensitivity(str, Enum):
-    """Determines how end of speech is detected."""
-
-    UNSPECIFIED = "END_SENSITIVITY_UNSPECIFIED"  # Default is HIGH
-    HIGH = "END_SENSITIVITY_HIGH"  # End speech more often
-    LOW = "END_SENSITIVITY_LOW"  # End speech less often
-
-
-class AutomaticActivityDetection(BaseModel):
-    """Configures automatic detection of voice activity.
-
-    Parameters:
-        disabled: Whether automatic activity detection is disabled. Defaults to None.
-        start_of_speech_sensitivity: Sensitivity for detecting speech start. Defaults to None.
-        prefix_padding_ms: Padding before speech start in milliseconds. Defaults to None.
-        end_of_speech_sensitivity: Sensitivity for detecting speech end. Defaults to None.
-        silence_duration_ms: Duration of silence to detect speech end. Defaults to None.
-    """
-
-    disabled: Optional[bool] = None
-    start_of_speech_sensitivity: Optional[StartSensitivity] = None
-    prefix_padding_ms: Optional[int] = None
-    end_of_speech_sensitivity: Optional[EndSensitivity] = None
-    silence_duration_ms: Optional[int] = None
-
-
-class RealtimeInputConfig(BaseModel):
-    """Configures the realtime input behavior.
-
-    Parameters:
-        automatic_activity_detection: Voice activity detection configuration. Defaults to None.
-    """
-
-    automatic_activity_detection: Optional[AutomaticActivityDetection] = None
-
-
-class RealtimeInput(BaseModel):
-    """Contains realtime input media chunks and text.
-
-    Parameters:
-        mediaChunks: List of media chunks for realtime processing.
-        text: Text for realtime processing.
-    """
-
-    mediaChunks: Optional[List[MediaChunk]] = None
-    text: Optional[str] = None
-
-
-class ClientContent(BaseModel):
-    """Content sent from client to the Gemini Live API.
-
-    Parameters:
-        turns: List of conversation turns. Defaults to None.
-        turnComplete: Whether the client's turn is complete. Defaults to False.
-    """
-
-    turns: Optional[List[Turn]] = None
-    turnComplete: bool = False
-
-
-class AudioInputMessage(BaseModel):
-    """Message containing audio input data.
-
-    Parameters:
-        realtimeInput: Realtime input containing audio chunks.
-    """
-
-    realtimeInput: RealtimeInput
-
-    @classmethod
-    def from_raw_audio(cls, raw_audio: bytes, sample_rate: int) -> "AudioInputMessage":
-        """Create an audio input message from raw audio data.
-
-        Args:
-            raw_audio: Raw audio bytes.
-            sample_rate: Audio sample rate in Hz.
-
-        Returns:
-            AudioInputMessage instance with encoded audio data.
-        """
-        data = base64.b64encode(raw_audio).decode("utf-8")
-        return cls(
-            realtimeInput=RealtimeInput(
-                mediaChunks=[MediaChunk(mimeType=f"audio/pcm;rate={sample_rate}", data=data)]
-            )
-        )
-
-
-class VideoInputMessage(BaseModel):
-    """Message containing video/image input data.
-
-    Parameters:
-        realtimeInput: Realtime input containing video/image chunks.
-    """
-
-    realtimeInput: RealtimeInput
-
-    @classmethod
-    def from_image_frame(cls, frame: ImageRawFrame) -> "VideoInputMessage":
-        """Create a video input message from an image frame.
-
-        Args:
-            frame: Image frame to encode.
-
-        Returns:
-            VideoInputMessage instance with encoded image data.
-        """
-        buffer = io.BytesIO()
-        Image.frombytes(frame.format, frame.size, frame.image).save(buffer, format="JPEG")
-        data = base64.b64encode(buffer.getvalue()).decode("utf-8")
-        return cls(
-            realtimeInput=RealtimeInput(mediaChunks=[MediaChunk(mimeType=f"image/jpeg", data=data)])
-        )
-
-
-class TextInputMessage(BaseModel):
-    """Message containing text input data."""
-
-    realtimeInput: RealtimeInput
-
-    @classmethod
-    def from_text(cls, text: str) -> "TextInputMessage":
-        """Create a text input message from a string.
-
-        Args:
-            text: The text to send.
-
-        Returns:
-            A TextInputMessage instance.
-        """
-        return cls(realtimeInput=RealtimeInput(text=text))
-
-
-class ClientContentMessage(BaseModel):
-    """Message containing client content for the API.
-
-    Parameters:
-        clientContent: The client content to send.
-    """
-
-    clientContent: ClientContent
-
-
-class SystemInstruction(BaseModel):
-    """System instruction for the model.
-
-    Parameters:
-        parts: List of content parts that make up the system instruction.
-    """
-
-    parts: List[ContentPart]
-
-
-class AudioTranscriptionConfig(BaseModel):
-    """Configuration for audio transcription."""
-
-    pass
-
-
-class Setup(BaseModel):
-    """Setup configuration for the Gemini Live session.
-
-    Parameters:
-        model: Model identifier to use.
-        system_instruction: System instruction for the model. Defaults to None.
-        tools: List of available tools/functions. Defaults to None.
-        generation_config: Generation configuration parameters. Defaults to None.
-        input_audio_transcription: Input audio transcription config. Defaults to None.
-        output_audio_transcription: Output audio transcription config. Defaults to None.
-        realtime_input_config: Realtime input configuration. Defaults to None.
-    """
-
-    model: str
-    system_instruction: Optional[SystemInstruction] = None
-    tools: Optional[List[dict]] = None
-    generation_config: Optional[dict] = None
-    input_audio_transcription: Optional[AudioTranscriptionConfig] = None
-    output_audio_transcription: Optional[AudioTranscriptionConfig] = None
-    realtime_input_config: Optional[RealtimeInputConfig] = None
-
-
-class Config(BaseModel):
-    """Configuration message for session setup.
-
-    Parameters:
-        setup: Setup configuration for the session.
-    """
-
-    setup: Setup
-
-
-#
-# Grounding metadata models
-#
-
-
-class SearchEntryPoint(BaseModel):
-    """Represents the search entry point with rendered content for search suggestions."""
-
-    renderedContent: Optional[str] = None
-
-
-class WebSource(BaseModel):
-    """Represents a web source from grounding chunks."""
-
-    uri: Optional[str] = None
-    title: Optional[str] = None
-
-
-class GroundingChunk(BaseModel):
-    """Represents a grounding chunk containing web source information."""
-
-    web: Optional[WebSource] = None
-
-
-class GroundingSegment(BaseModel):
-    """Represents a segment of text that is grounded."""
-
-    startIndex: Optional[int] = None
-    endIndex: Optional[int] = None
-    text: Optional[str] = None
-
-
-class GroundingSupport(BaseModel):
-    """Represents support information for grounded text segments."""
-
-    segment: Optional[GroundingSegment] = None
-    groundingChunkIndices: Optional[List[int]] = None
-    confidenceScores: Optional[List[float]] = None
-
-
-class GroundingMetadata(BaseModel):
-    """Represents grounding metadata from Google Search."""
-
-    searchEntryPoint: Optional[SearchEntryPoint] = None
-    groundingChunks: Optional[List[GroundingChunk]] = None
-    groundingSupports: Optional[List[GroundingSupport]] = None
-    webSearchQueries: Optional[List[str]] = None
-
-
-#
-# Server events
-#
-
-
-class SetupComplete(BaseModel):
-    """Indicates that session setup is complete."""
-
-    pass
-
-
-class InlineData(BaseModel):
-    """Inline data embedded in server responses.
-
-    Parameters:
-        mimeType: MIME type of the data.
-        data: Base64-encoded data content.
-    """
-
-    mimeType: str
-    data: str
-
-
-class Part(BaseModel):
-    """Part of a server response containing data or text.
-
-    Parameters:
-        inlineData: Inline binary data. Defaults to None.
-        text: Text content. Defaults to None.
-    """
-
-    inlineData: Optional[InlineData] = None
-    text: Optional[str] = None
-
-
-class ModelTurn(BaseModel):
-    """Represents a turn from the model in the conversation.
-
-    Parameters:
-        parts: List of content parts in the model's response.
-    """
-
-    parts: List[Part]
-
-
-class ServerContentInterrupted(BaseModel):
-    """Indicates server content was interrupted.
-
-    Parameters:
-        interrupted: Whether the content was interrupted.
-    """
-
-    interrupted: bool
-
-
-class ServerContentTurnComplete(BaseModel):
-    """Indicates the server's turn is complete.
-
-    Parameters:
-        turnComplete: Whether the turn is complete.
-    """
-
-    turnComplete: bool
-
-
-class BidiGenerateContentTranscription(BaseModel):
-    """Transcription data from bidirectional content generation.
-
-    Parameters:
-        text: The transcribed text content.
-    """
-
-    text: str
-
-
-class ServerContent(BaseModel):
-    """Content sent from server to client.
-
-    Parameters:
-        modelTurn: Model's conversational turn. Defaults to None.
-        interrupted: Whether content was interrupted. Defaults to None.
-        turnComplete: Whether the turn is complete. Defaults to None.
-        inputTranscription: Transcription of input audio. Defaults to None.
-        outputTranscription: Transcription of output audio. Defaults to None.
-    """
-
-    modelTurn: Optional[ModelTurn] = None
-    interrupted: Optional[bool] = None
-    turnComplete: Optional[bool] = None
-    inputTranscription: Optional[BidiGenerateContentTranscription] = None
-    outputTranscription: Optional[BidiGenerateContentTranscription] = None
-    groundingMetadata: Optional[GroundingMetadata] = None
-
-
-class FunctionCall(BaseModel):
-    """Represents a function call from the model.
-
-    Parameters:
-        id: Unique identifier for the function call.
-        name: Name of the function to call.
-        args: Arguments to pass to the function.
-    """
-
-    id: str
-    name: str
-    args: dict
-
-
-class ToolCall(BaseModel):
-    """Contains one or more function calls.
-
-    Parameters:
-        functionCalls: List of function calls to execute.
-    """
-
-    functionCalls: List[FunctionCall]
-
-
-class Modality(str, Enum):
-    """Modality types in token counts."""
-
-    UNSPECIFIED = "MODALITY_UNSPECIFIED"
-    TEXT = "TEXT"
-    IMAGE = "IMAGE"
-    AUDIO = "AUDIO"
-    VIDEO = "VIDEO"
-
-
-class ModalityTokenCount(BaseModel):
-    """Token count for a specific modality.
-
-    Parameters:
-        modality: The modality type.
-        tokenCount: Number of tokens for this modality.
-    """
-
-    modality: Modality
-    tokenCount: int
-
-
-class UsageMetadata(BaseModel):
-    """Usage metadata about the API response.
-
-    Parameters:
-        promptTokenCount: Number of tokens in the prompt. Defaults to None.
-        cachedContentTokenCount: Number of cached content tokens. Defaults to None.
-        responseTokenCount: Number of tokens in the response. Defaults to None.
-        toolUsePromptTokenCount: Number of tokens for tool use prompts. Defaults to None.
-        thoughtsTokenCount: Number of tokens for model thoughts. Defaults to None.
-        totalTokenCount: Total number of tokens used. Defaults to None.
-        promptTokensDetails: Detailed breakdown of prompt tokens by modality. Defaults to None.
-        cacheTokensDetails: Detailed breakdown of cache tokens by modality. Defaults to None.
-        responseTokensDetails: Detailed breakdown of response tokens by modality. Defaults to None.
-        toolUsePromptTokensDetails: Detailed breakdown of tool use tokens by modality. Defaults to None.
-    """
-
-    promptTokenCount: Optional[int] = None
-    cachedContentTokenCount: Optional[int] = None
-    responseTokenCount: Optional[int] = None
-    toolUsePromptTokenCount: Optional[int] = None
-    thoughtsTokenCount: Optional[int] = None
-    totalTokenCount: Optional[int] = None
-    promptTokensDetails: Optional[List[ModalityTokenCount]] = None
-    cacheTokensDetails: Optional[List[ModalityTokenCount]] = None
-    responseTokensDetails: Optional[List[ModalityTokenCount]] = None
-    toolUsePromptTokensDetails: Optional[List[ModalityTokenCount]] = None
-
-
-class ServerEvent(BaseModel):
-    """Server event received from the Gemini Live API.
-
-    Parameters:
-        setupComplete: Setup completion notification. Defaults to None.
-        serverContent: Content from the server. Defaults to None.
-        toolCall: Tool/function call request. Defaults to None.
-        usageMetadata: Token usage metadata. Defaults to None.
-    """
-
-    setupComplete: Optional[SetupComplete] = None
-    serverContent: Optional[ServerContent] = None
-    toolCall: Optional[ToolCall] = None
-    usageMetadata: Optional[UsageMetadata] = None
-
-
-def parse_server_event(str):
-    """Parse a server event from JSON string.
-
-    Args:
-        str: JSON string containing the server event.
-
-    Returns:
-        ServerEvent instance if parsing succeeds, None otherwise.
-    """
-    try:
-        evt = json.loads(str)
-        return ServerEvent.model_validate(evt)
-    except Exception as e:
-        print(f"Error parsing server event: {e}")
-        return None
-
-
-class ContextWindowCompressionConfig(BaseModel):
-    """Configuration for context window compression.
-
-    Parameters:
-        sliding_window: Whether to use sliding window compression. Defaults to True.
-        trigger_tokens: Token count threshold to trigger compression. Defaults to None.
-    """
-
-    sliding_window: Optional[bool] = Field(default=True)
-    trigger_tokens: Optional[int] = Field(default=None)
+"""Event models and utilities for Google Gemini Multimodal Live API.
+
+.. deprecated:: 0.0.90
+    Importing StartSensitivity and EndSensitivity from this module is deprecated.
+    Import them directly from google.genai.types instead.
+"""
+
+import warnings
+
+from loguru import logger
+
+try:
+    from google.genai.types import (
+        EndSensitivity as _EndSensitivity,
+    )
+    from google.genai.types import (
+        StartSensitivity as _StartSensitivity,
+    )
+except ModuleNotFoundError as e:
+    logger.error(f"Exception: {e}")
+    logger.error("In order to use Google AI, you need to `pip install pipecat-ai[google]`.")
+    raise Exception(f"Missing module: {e}")
+
+# These aliases are just here for backward compatibility, since we used to
+# define public-facing StartSensitivity and EndSensitivity enums in this
+# module.
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Importing StartSensitivity and EndSensitivity from "
+        "pipecat.services.gemini_multimodal_live.events is deprecated. "
+        "Please import them directly from google.genai.types instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )
+
+StartSensitivity = _StartSensitivity
+EndSensitivity = _EndSensitivity

src/pipecat/services/gemini_multimodal_live/file_api.py

@@ -9,181 +9,31 @@
 This module provides a client for Google's Gemini File API, enabling file
 uploads, metadata retrieval, listing, and deletion. Files uploaded through
 this API can be referenced in Gemini generative model calls.
+
+.. deprecated:: 0.0.90
+    Importing GeminiFileAPI from this module is deprecated.
+    Import it from pipecat.services.google.gemini_live.file_api instead.
 """
 
-import mimetypes
-from typing import Any, Dict, Optional
+import warnings
 
-import aiohttp
 from loguru import logger
 
+try:
+    from pipecat.services.google.gemini_live.file_api import GeminiFileAPI as _GeminiFileAPI
+except ModuleNotFoundError as e:
+    logger.error(f"Exception: {e}")
+    logger.error("In order to use Google AI, you need to `pip install pipecat-ai[google]`.")
+    raise Exception(f"Missing module: {e}")
 
-class GeminiFileAPI:
-    """Client for the Gemini File API.
-
-    This class provides methods for uploading, fetching, listing, and deleting files
-    through Google's Gemini File API.
-
-    Files uploaded through this API remain available for 48 hours and can be referenced
-    in calls to the Gemini generative models. Maximum file size is 2GB, with total
-    project storage limited to 20GB.
-    """
-
-    def __init__(
-        self, api_key: str, base_url: str = "https://generativelanguage.googleapis.com/v1beta/files"
-    ):
-        """Initialize the Gemini File API client.
-
-        Args:
-            api_key: Google AI API key
-            base_url: Base URL for the Gemini File API (default is the v1beta endpoint)
-        """
-        self._api_key = api_key
-        self._base_url = base_url
-        # Upload URL uses the /upload/ path
-        self.upload_base_url = "https://generativelanguage.googleapis.com/upload/v1beta/files"
-
-    async def upload_file(
-        self, file_path: str, display_name: Optional[str] = None
-    ) -> Dict[str, Any]:
-        """Upload a file to the Gemini File API using the correct resumable upload protocol.
-
-        Args:
-            file_path: Path to the file to upload
-            display_name: Optional display name for the file
-
-        Returns:
-            File metadata including uri, name, and display_name
-        """
-        logger.info(f"Uploading file: {file_path}")
-
-        async with aiohttp.ClientSession() as session:
-            # Determine the file's MIME type
-            mime_type, _ = mimetypes.guess_type(file_path)
-            if not mime_type:
-                mime_type = "application/octet-stream"
-
-            # Read the file
-            with open(file_path, "rb") as f:
-                file_data = f.read()
-
-            # Create the metadata payload
-            metadata = {}
-            if display_name:
-                metadata = {"file": {"display_name": display_name}}
-
-            # Step 1: Initial resumable request to get upload URL
-            headers = {
-                "X-Goog-Upload-Protocol": "resumable",
-                "X-Goog-Upload-Command": "start",
-                "X-Goog-Upload-Header-Content-Length": str(len(file_data)),
-                "X-Goog-Upload-Header-Content-Type": mime_type,
-                "Content-Type": "application/json",
-            }
-
-            logger.debug(f"Step 1: Getting upload URL from {self.upload_base_url}")
-            async with session.post(
-                f"{self.upload_base_url}?key={self._api_key}", headers=headers, json=metadata
-            ) as response:
-                if response.status != 200:
-                    error_text = await response.text()
-                    logger.error(f"Error initiating file upload: {error_text}")
-                    raise Exception(f"Failed to initiate upload: {response.status} - {error_text}")
-
-                # Get the upload URL from the response header
-                upload_url = response.headers.get("X-Goog-Upload-URL")
-                if not upload_url:
-                    logger.error(f"Response headers: {dict(response.headers)}")
-                    raise Exception("No upload URL in response headers")
-
-                logger.debug(f"Got upload URL: {upload_url}")
-
-            # Step 2: Upload the actual file data
-            upload_headers = {
-                "Content-Length": str(len(file_data)),
-                "X-Goog-Upload-Offset": "0",
-                "X-Goog-Upload-Command": "upload, finalize",
-            }
-
-            logger.debug(f"Step 2: Uploading file data to {upload_url}")
-            async with session.post(upload_url, headers=upload_headers, data=file_data) as response:
-                if response.status != 200:
-                    error_text = await response.text()
-                    logger.error(f"Error uploading file data: {error_text}")
-                    raise Exception(f"Failed to upload file: {response.status} - {error_text}")
-
-                file_info = await response.json()
-                logger.info(f"File uploaded successfully: {file_info.get('file', {}).get('name')}")
-                return file_info
-
-    async def get_file(self, name: str) -> Dict[str, Any]:
-        """Get metadata for a file.
-
-        Args:
-            name: File name (or full path)
-
-        Returns:
-            File metadata
-        """
-        # Extract just the name part if a full path is provided
-        if "/" in name:
-            name = name.split("/")[-1]
-
-        async with aiohttp.ClientSession() as session:
-            async with session.get(f"{self._base_url}/{name}?key={self._api_key}") as response:
-                if response.status != 200:
-                    error_text = await response.text()
-                    logger.error(f"Error getting file metadata: {error_text}")
-                    raise Exception(f"Failed to get file metadata: {response.status}")
-
-                file_info = await response.json()
-                return file_info
-
-    async def list_files(
-        self, page_size: int = 10, page_token: Optional[str] = None
-    ) -> Dict[str, Any]:
-        """List uploaded files.
-
-        Args:
-            page_size: Number of files to return per page
-            page_token: Token for pagination
-
-        Returns:
-            List of files and next page token if available
-        """
-        params = {"key": self._api_key, "pageSize": page_size}
-
-        if page_token:
-            params["pageToken"] = page_token
-
-        async with aiohttp.ClientSession() as session:
-            async with session.get(self._base_url, params=params) as response:
-                if response.status != 200:
-                    error_text = await response.text()
-                    logger.error(f"Error listing files: {error_text}")
-                    raise Exception(f"Failed to list files: {response.status}")
-
-                result = await response.json()
-                return result
-
-    async def delete_file(self, name: str) -> bool:
-        """Delete a file.
-
-        Args:
-            name: File name (or full path)
-
-        Returns:
-            True if deleted successfully
-        """
-        # Extract just the name part if a full path is provided
-        if "/" in name:
-            name = name.split("/")[-1]
-
-        async with aiohttp.ClientSession() as session:
-            async with session.delete(f"{self._base_url}/{name}?key={self._api_key}") as response:
-                if response.status != 200:
-                    error_text = await response.text()
-                    logger.error(f"Error deleting file: {error_text}")
-                    raise Exception(f"Failed to delete file: {response.status}")
-
-                return True
+# These aliases are just here for backward compatibility, since we used to
+# define public-facing StartSensitivity and EndSensitivity enums in this
+# module.
+warnings.warn(
+    "Importing GeminiFileAPI from "
+    "pipecat.services.gemini_multimodal_live.file_api is deprecated. "
+    "Please import it from pipecat.services.google.gemini_live.file_api instead.",
+    DeprecationWarning,
+    stacklevel=2,
+)
+GeminiFileAPI = _GeminiFileAPI

src/pipecat/services/google/__init__.py

@@ -9,6 +9,7 @@ import sys
 from pipecat.services import DeprecatedModuleProxy
 
 from .frames import *
+from .gemini_live import *
 from .image import *
 from .llm import *
 from .llm_openai import *

src/pipecat/services/google/gemini_live/__init__.py

@@ -0,0 +1,3 @@
+from .file_api import GeminiFileAPI
+from .llm import GeminiLiveLLMService
+from .llm_vertex import GeminiLiveVertexLLMService

src/pipecat/services/google/gemini_live/file_api.py

@@ -0,0 +1,189 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Gemini File API client for uploading and managing files.
+
+This module provides a client for Google's Gemini File API, enabling file
+uploads, metadata retrieval, listing, and deletion. Files uploaded through
+this API can be referenced in Gemini generative model calls.
+"""
+
+import mimetypes
+from typing import Any, Dict, Optional
+
+import aiohttp
+from loguru import logger
+
+
+class GeminiFileAPI:
+    """Client for the Gemini File API.
+
+    This class provides methods for uploading, fetching, listing, and deleting files
+    through Google's Gemini File API.
+
+    Files uploaded through this API remain available for 48 hours and can be referenced
+    in calls to the Gemini generative models. Maximum file size is 2GB, with total
+    project storage limited to 20GB.
+    """
+
+    def __init__(
+        self, api_key: str, base_url: str = "https://generativelanguage.googleapis.com/v1beta/files"
+    ):
+        """Initialize the Gemini File API client.
+
+        Args:
+            api_key: Google AI API key
+            base_url: Base URL for the Gemini File API (default is the v1beta endpoint)
+        """
+        self._api_key = api_key
+        self._base_url = base_url
+        # Upload URL uses the /upload/ path
+        self.upload_base_url = "https://generativelanguage.googleapis.com/upload/v1beta/files"
+
+    async def upload_file(
+        self, file_path: str, display_name: Optional[str] = None
+    ) -> Dict[str, Any]:
+        """Upload a file to the Gemini File API using the correct resumable upload protocol.
+
+        Args:
+            file_path: Path to the file to upload
+            display_name: Optional display name for the file
+
+        Returns:
+            File metadata including uri, name, and display_name
+        """
+        logger.info(f"Uploading file: {file_path}")
+
+        async with aiohttp.ClientSession() as session:
+            # Determine the file's MIME type
+            mime_type, _ = mimetypes.guess_type(file_path)
+            if not mime_type:
+                mime_type = "application/octet-stream"
+
+            # Read the file
+            with open(file_path, "rb") as f:
+                file_data = f.read()
+
+            # Create the metadata payload
+            metadata = {}
+            if display_name:
+                metadata = {"file": {"display_name": display_name}}
+
+            # Step 1: Initial resumable request to get upload URL
+            headers = {
+                "X-Goog-Upload-Protocol": "resumable",
+                "X-Goog-Upload-Command": "start",
+                "X-Goog-Upload-Header-Content-Length": str(len(file_data)),
+                "X-Goog-Upload-Header-Content-Type": mime_type,
+                "Content-Type": "application/json",
+            }
+
+            logger.debug(f"Step 1: Getting upload URL from {self.upload_base_url}")
+            async with session.post(
+                f"{self.upload_base_url}?key={self._api_key}", headers=headers, json=metadata
+            ) as response:
+                if response.status != 200:
+                    error_text = await response.text()
+                    logger.error(f"Error initiating file upload: {error_text}")
+                    raise Exception(f"Failed to initiate upload: {response.status} - {error_text}")
+
+                # Get the upload URL from the response header
+                upload_url = response.headers.get("X-Goog-Upload-URL")
+                if not upload_url:
+                    logger.error(f"Response headers: {dict(response.headers)}")
+                    raise Exception("No upload URL in response headers")
+
+                logger.debug(f"Got upload URL: {upload_url}")
+
+            # Step 2: Upload the actual file data
+            upload_headers = {
+                "Content-Length": str(len(file_data)),
+                "X-Goog-Upload-Offset": "0",
+                "X-Goog-Upload-Command": "upload, finalize",
+            }
+
+            logger.debug(f"Step 2: Uploading file data to {upload_url}")
+            async with session.post(upload_url, headers=upload_headers, data=file_data) as response:
+                if response.status != 200:
+                    error_text = await response.text()
+                    logger.error(f"Error uploading file data: {error_text}")
+                    raise Exception(f"Failed to upload file: {response.status} - {error_text}")
+
+                file_info = await response.json()
+                logger.info(f"File uploaded successfully: {file_info.get('file', {}).get('name')}")
+                return file_info
+
+    async def get_file(self, name: str) -> Dict[str, Any]:
+        """Get metadata for a file.
+
+        Args:
+            name: File name (or full path)
+
+        Returns:
+            File metadata
+        """
+        # Extract just the name part if a full path is provided
+        if "/" in name:
+            name = name.split("/")[-1]
+
+        async with aiohttp.ClientSession() as session:
+            async with session.get(f"{self._base_url}/{name}?key={self._api_key}") as response:
+                if response.status != 200:
+                    error_text = await response.text()
+                    logger.error(f"Error getting file metadata: {error_text}")
+                    raise Exception(f"Failed to get file metadata: {response.status}")
+
+                file_info = await response.json()
+                return file_info
+
+    async def list_files(
+        self, page_size: int = 10, page_token: Optional[str] = None
+    ) -> Dict[str, Any]:
+        """List uploaded files.
+
+        Args:
+            page_size: Number of files to return per page
+            page_token: Token for pagination
+
+        Returns:
+            List of files and next page token if available
+        """
+        params = {"key": self._api_key, "pageSize": page_size}
+
+        if page_token:
+            params["pageToken"] = page_token
+
+        async with aiohttp.ClientSession() as session:
+            async with session.get(self._base_url, params=params) as response:
+                if response.status != 200:
+                    error_text = await response.text()
+                    logger.error(f"Error listing files: {error_text}")
+                    raise Exception(f"Failed to list files: {response.status}")
+
+                result = await response.json()
+                return result
+
+    async def delete_file(self, name: str) -> bool:
+        """Delete a file.
+
+        Args:
+            name: File name (or full path)
+
+        Returns:
+            True if deleted successfully
+        """
+        # Extract just the name part if a full path is provided
+        if "/" in name:
+            name = name.split("/")[-1]
+
+        async with aiohttp.ClientSession() as session:
+            async with session.delete(f"{self._base_url}/{name}?key={self._api_key}") as response:
+                if response.status != 200:
+                    error_text = await response.text()
+                    logger.error(f"Error deleting file: {error_text}")
+                    raise Exception(f"Failed to delete file: {response.status}")
+
+                return True

src/pipecat/services/google/gemini_live/llm_vertex.py

@@ -0,0 +1,184 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Service for accessing Gemini Live via Google Vertex AI.
+
+This module provides integration with Google's Gemini Live model via
+Vertex AI, supporting both text and audio modalities with voice transcription,
+streaming responses, and tool usage.
+"""
+
+import json
+from typing import List, Optional, Union
+
+from loguru import logger
+
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+from pipecat.services.google.gemini_live.llm import (
+    GeminiLiveLLMService,
+    HttpOptions,
+    InputParams,
+)
+
+try:
+    from google.auth import default
+    from google.auth.exceptions import GoogleAuthError
+    from google.auth.transport.requests import Request
+    from google.genai import Client
+    from google.oauth2 import service_account
+
+except ModuleNotFoundError as e:
+    logger.error(f"Exception: {e}")
+    logger.error("In order to use Google Vertex AI, you need to `pip install pipecat-ai[google]`.")
+    raise Exception(f"Missing module: {e}")
+
+
+class GeminiLiveVertexLLMService(GeminiLiveLLMService):
+    """Provides access to Google's Gemini Live model via Vertex AI.
+
+    This service enables real-time conversations with Gemini, supporting both
+    text and audio modalities. It handles voice transcription, streaming audio
+    responses, and tool usage.
+    """
+
+    def __init__(
+        self,
+        *,
+        credentials: Optional[str] = None,
+        credentials_path: Optional[str] = None,
+        location: str,
+        project_id: str,
+        model="google/gemini-2.0-flash-live-preview-04-09",
+        voice_id: str = "Charon",
+        start_audio_paused: bool = False,
+        start_video_paused: bool = False,
+        system_instruction: Optional[str] = None,
+        tools: Optional[Union[List[dict], ToolsSchema]] = None,
+        params: Optional[InputParams] = None,
+        inference_on_context_initialization: bool = True,
+        file_api_base_url: str = "https://generativelanguage.googleapis.com/v1beta/files",
+        http_options: Optional[HttpOptions] = None,
+        **kwargs,
+    ):
+        """Initialize the service for accessing Gemini Live via Google Vertex AI.
+
+        Args:
+            credentials: JSON string of service account credentials.
+            credentials_path: Path to the service account JSON file.
+            location: GCP region for Vertex AI endpoint (e.g., "us-east4").
+            project_id: Google Cloud project ID.
+            model: Model identifier to use. Defaults to "models/gemini-2.0-flash-live-preview-04-09".
+            voice_id: TTS voice identifier. Defaults to "Charon".
+            start_audio_paused: Whether to start with audio input paused. Defaults to False.
+            start_video_paused: Whether to start with video input paused. Defaults to False.
+            system_instruction: System prompt for the model. Defaults to None.
+            tools: Tools/functions available to the model. Defaults to None.
+            params: Configuration parameters for the model along with Vertex AI
+                location and project ID.
+            inference_on_context_initialization: Whether to generate a response when context
+                is first set. Defaults to True.
+            file_api_base_url: Base URL for the Gemini File API. Defaults to the official endpoint.
+            http_options: HTTP options for the client.
+            **kwargs: Additional arguments passed to parent GeminiLiveLLMService.
+        """
+        # Check if user incorrectly passed api_key, which is used by parent
+        # class but not here.
+        if "api_key" in kwargs:
+            logger.error(
+                "GeminiLiveVertexLLMService does not accept 'api_key' parameter. "
+                "Use 'credentials' or 'credentials_path' instead for Vertex AI authentication."
+            )
+            raise ValueError(
+                "Invalid parameter 'api_key'. Use 'credentials' or 'credentials_path' for Vertex AI authentication."
+            )
+
+        # These need to be set before calling super().__init__() because
+        # super().__init__() invokes create_client(), which needs these.
+        self._credentials = self._get_credentials(credentials, credentials_path)
+        self._project_id = project_id
+        self._location = location
+
+        # Call parent constructor with the obtained API key
+        super().__init__(
+            # api_key is required by parent class, but actually not used with
+            # Vertex
+            api_key="dummy",
+            model=model,
+            voice_id=voice_id,
+            start_audio_paused=start_audio_paused,
+            start_video_paused=start_video_paused,
+            system_instruction=system_instruction,
+            tools=tools,
+            params=params,
+            inference_on_context_initialization=inference_on_context_initialization,
+            file_api_base_url=file_api_base_url,
+            http_options=http_options,
+            **kwargs,
+        )
+
+    def create_client(self):
+        """Create the Gemini client instance."""
+        self._client = Client(
+            vertexai=True,
+            credentials=self._credentials,
+            project=self._project_id,
+            location=self._location,
+        )
+
+    @property
+    def file_api(self):
+        """Gemini File API is not supported with Vertex AI."""
+        raise NotImplementedError(
+            "When using Vertex AI, the recommended approach is to use Google Cloud Storage for file handling. The Gemini File API is not directly supported in this context."
+        )
+
+    @staticmethod
+    def _get_credentials(credentials: Optional[str], credentials_path: Optional[str]) -> str:
+        """Retrieve Credentials using Google service account credentials JSON.
+
+        Supports multiple authentication methods:
+        1. Direct JSON credentials string
+        2. Path to service account JSON file
+        3. Default application credentials (ADC)
+
+        Args:
+            credentials: JSON string of service account credentials.
+            credentials_path: Path to the service account JSON file.
+
+        Returns:
+            OAuth token for API authentication.
+
+        Raises:
+            ValueError: If no valid credentials are provided or found.
+        """
+        creds: Optional[service_account.Credentials] = None
+
+        if credentials:
+            # Parse and load credentials from JSON string
+            creds = service_account.Credentials.from_service_account_info(
+                json.loads(credentials),
+                scopes=["https://www.googleapis.com/auth/cloud-platform"],
+            )
+        elif credentials_path:
+            # Load credentials from JSON file
+            creds = service_account.Credentials.from_service_account_file(
+                credentials_path,
+                scopes=["https://www.googleapis.com/auth/cloud-platform"],
+            )
+        else:
+            try:
+                creds, project_id = default(
+                    scopes=["https://www.googleapis.com/auth/cloud-platform"]
+                )
+            except GoogleAuthError:
+                pass
+
+        if not creds:
+            raise ValueError("No valid credentials provided.")
+
+        creds.refresh(Request())  # Ensure token is up-to-date, lifetime is 1 hour.
+
+        return creds

src/pipecat/services/google/llm.py

@@ -35,6 +35,7 @@ from pipecat.frames.frames import (
     LLMMessagesFrame,
     LLMTextFrame,
     LLMUpdateSettingsFrame,
+    OutputImageRawFrame,
     UserImageRawFrame,
 )
 from pipecat.metrics.metrics import LLMTokenUsage
@@ -72,6 +73,9 @@ try:
         HttpOptions,
         Part,
     )
+
+    # Temporary hack to be able to process Nano Banana returned images.
+    genai._api_client.READ_BUFFER_SIZE = 5 * 1024 * 1024
 except ModuleNotFoundError as e:
     logger.error(f"Exception: {e}")
     logger.error("In order to use Google AI, you need to `pip install pipecat-ai[google]`.")
@@ -682,7 +686,7 @@ class GoogleLLMService(LLMService):
         self,
         *,
         api_key: str,
-        model: str = "gemini-2.0-flash",
+        model: str = "gemini-2.5-flash",
         params: Optional[InputParams] = None,
         system_instruction: Optional[str] = None,
         tools: Optional[List[Dict[str, Any]]] = None,
@@ -710,6 +714,7 @@ class GoogleLLMService(LLMService):
         self._api_key = api_key
         self._system_instruction = system_instruction
         self._http_options = http_options
+
         self._create_client(api_key, http_options)
         self._settings = {
             "max_tokens": params.max_tokens,
@@ -788,6 +793,9 @@ class GoogleLLMService(LLMService):
             # and can be configured to turn it off.
             if not self._model_name.startswith("gemini-2.5-flash"):
                 return
+            # If we have an image model, we don't use a budget either.
+            if "image" in self._model_name:
+                return
             # If thinking_config is already set, don't override it.
             if "thinking_config" in generation_params:
                 return
@@ -927,6 +935,12 @@ class GoogleLLMService(LLMService):
                                         arguments=function_call.args or {},
                                     )
                                 )
+                            elif part.inline_data and part.inline_data.data:
+                                image = Image.open(io.BytesIO(part.inline_data.data))
+                                frame = OutputImageRawFrame(
+                                    image=image.tobytes(), size=image.size, format="RGB"
+                                )
+                                await self.push_frame(frame)
 
                     if (
                         candidate.grounding_metadata

src/pipecat/services/google/llm_openai.py

@@ -94,9 +94,9 @@ class GoogleLLMOpenAIBetaService(OpenAILLMService):
         async for chunk in chunk_stream:
             if chunk.usage:
                 tokens = LLMTokenUsage(
-                    prompt_tokens=chunk.usage.prompt_tokens,
-                    completion_tokens=chunk.usage.completion_tokens,
-                    total_tokens=chunk.usage.total_tokens,
+                    prompt_tokens=chunk.usage.prompt_tokens or 0,
+                    completion_tokens=chunk.usage.completion_tokens or 0,
+                    total_tokens=chunk.usage.total_tokens or 0,
                 )
                 await self.start_llm_usage_metrics(tokens)
 

src/pipecat/services/google/llm_vertex.py

@@ -53,12 +53,44 @@ class GoogleVertexLLMService(OpenAILLMService):
 
         Parameters:
             location: GCP region for Vertex AI endpoint (e.g., "us-east4").
+
+                .. deprecated:: 0.0.90
+                    Use `location` as a direct argument to
+                    `GoogleVertexLLMService.__init__()` instead.
+
             project_id: Google Cloud project ID.
+
+                .. deprecated:: 0.0.90
+                    Use `project_id` as a direct argument to
+                    `GoogleVertexLLMService.__init__()` instead.
         """
 
         # https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations
-        location: str = "us-east4"
-        project_id: str
+        location: Optional[str] = None
+        project_id: Optional[str] = None
+
+        def __init__(self, **kwargs):
+            """Initializes the InputParams."""
+            import warnings
+
+            with warnings.catch_warnings():
+                warnings.simplefilter("always")
+                if "location" in kwargs and kwargs["location"] is not None:
+                    warnings.warn(
+                        "GoogleVertexLLMService.InputParams.location is deprecated. "
+                        "Please provide 'location' as a direct argument to GoogleVertexLLMService.__init__() instead.",
+                        DeprecationWarning,
+                        stacklevel=2,
+                    )
+
+                if "project_id" in kwargs and kwargs["project_id"] is not None:
+                    warnings.warn(
+                        "GoogleVertexLLMService.InputParams.project_id is deprecated. "
+                        "Please provide 'project_id' as a direct argument to GoogleVertexLLMService.__init__() instead.",
+                        DeprecationWarning,
+                        stacklevel=2,
+                    )
+            super().__init__(**kwargs)
 
     def __init__(
         self,
@@ -66,7 +98,8 @@ class GoogleVertexLLMService(OpenAILLMService):
         credentials: Optional[str] = None,
         credentials_path: Optional[str] = None,
         model: str = "google/gemini-2.0-flash-001",
-        params: Optional[InputParams] = None,
+        location: Optional[str] = None,
+        project_id: Optional[str] = None,
         **kwargs,
     ):
         """Initializes the VertexLLMService.
@@ -75,33 +108,60 @@ class GoogleVertexLLMService(OpenAILLMService):
             credentials: JSON string of service account credentials.
             credentials_path: Path to the service account JSON file.
             model: Model identifier (e.g., "google/gemini-2.0-flash-001").
-            params: Vertex AI input parameters including location and project.
+            location: GCP region for Vertex AI endpoint (e.g., "us-east4").
+            project_id: Google Cloud project ID.
             **kwargs: Additional arguments passed to OpenAILLMService.
         """
-        params = params or OpenAILLMService.InputParams()
-        base_url = self._get_base_url(params)
+        # Handle deprecated InputParams fields
+        if "params" in kwargs and isinstance(kwargs["params"], GoogleVertexLLMService.InputParams):
+            params = kwargs["params"]
+            # Extract location and project_id from params if not provided
+            # directly, for backward compatibility
+            if project_id is None:
+                project_id = params.project_id
+            if location is None:
+                location = params.location
+            # Convert to base InputParams
+            params = OpenAILLMService.InputParams(
+                **params.model_dump(exclude={"location", "project_id"}, exclude_unset=True)
+            )
+            kwargs["params"] = params
+
+        # Validate project_id and location parameters
+        # NOTE: once we remove Vertex-spcific InputParams class, we can update
+        #       __init__() signature as follows:
+        #       - location: str = "us-east4",
+        #       - project_id: str,
+        #       But for now, we need them as-is to maintain proper backward
+        #       compatibility.
+        if project_id is None:
+            raise ValueError("project_id is required")
+        if location is None:
+            # If location is not provided, default to "us-east4".
+            # Note: this is legacy behavior; ideally location would be
+            # required.
+            logger.warning("location is not provided. Defaulting to 'us-east4'.")
+            location = "us-east4"  # Default location if not provided
+
+        base_url = self._get_base_url(location, project_id)
         self._api_key = self._get_api_token(credentials, credentials_path)
 
         super().__init__(
             api_key=self._api_key,
             base_url=base_url,
             model=model,
-            params=params,
             **kwargs,
         )
 
     @staticmethod
-    def _get_base_url(params: InputParams) -> str:
+    def _get_base_url(location: str, project_id: str) -> str:
         """Construct the base URL for Vertex AI API."""
         # Determine the correct API host based on location
-        if params.location == "global":
+        if location == "global":
             api_host = "aiplatform.googleapis.com"
         else:
-            api_host = f"{params.location}-aiplatform.googleapis.com"
-        return (
-            f"https://{api_host}/v1/"
-            f"projects/{params.project_id}/locations/{params.location}/endpoints/openapi"
-        )
+            api_host = f"{location}-aiplatform.googleapis.com"
+        return f"https://{api_host}/v1/projects/{project_id}/locations/{location}/endpoints/openapi"
 
     @staticmethod
     def _get_api_token(credentials: Optional[str], credentials_path: Optional[str]) -> str:

src/pipecat/services/hume/__init__.py

@@ -0,0 +1,5 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#

src/pipecat/services/hume/tts.py

@@ -0,0 +1,220 @@
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+
+"""Hume Text-to-Speech service implementation."""
+
+import base64
+import os
+from typing import Any, AsyncGenerator, Optional
+
+from loguru import logger
+from pydantic import BaseModel
+
+from pipecat.frames.frames import (
+    ErrorFrame,
+    Frame,
+    StartFrame,
+    TTSAudioRawFrame,
+    TTSStartedFrame,
+    TTSStoppedFrame,
+)
+from pipecat.services.tts_service import TTSService
+from pipecat.utils.tracing.service_decorators import traced_tts
+
+try:
+    from hume import AsyncHumeClient
+    from hume.tts import (
+        FormatPcm,
+        PostedUtterance,
+        PostedUtteranceVoiceWithId,
+    )
+except ModuleNotFoundError as e:  # pragma: no cover - import-time guidance
+    logger.error(f"Exception: {e}")
+    logger.error("In order to use Hume, you need to `pip install pipecat-ai[hume]`.")
+    raise Exception(f"Missing module: {e}")
+
+
+HUME_SAMPLE_RATE = 48_000  # Hume TTS streams at 48 kHz
+
+
+class HumeTTSService(TTSService):
+    """Hume Octave Text-to-Speech service.
+
+    Streams PCM audio via Hume's HTTP output streaming (JSON chunks) endpoint
+    using the Python SDK and emits ``TTSAudioRawFrame`` frames suitable for Pipecat transports.
+
+    Supported features:
+
+    - Generates speech from text using Hume TTS.
+    - Streams PCM audio.
+    - Supports dynamic updates of voice and synthesis parameters at runtime.
+    - Provides metrics for Time To First Byte (TTFB) and TTS usage.
+    """
+
+    class InputParams(BaseModel):
+        """Optional synthesis parameters for Hume TTS.
+
+        Parameters:
+            description: Natural-language acting directions (up to 100 characters).
+            speed: Speaking-rate multiplier (0.5-2.0).
+            trailing_silence: Seconds of silence to append at the end (0-5).
+        """
+
+        description: Optional[str] = None
+        speed: Optional[float] = None
+        trailing_silence: Optional[float] = None
+
+    def __init__(
+        self,
+        *,
+        api_key: Optional[str] = None,
+        voice_id: str,
+        params: Optional[InputParams] = None,
+        sample_rate: Optional[int] = HUME_SAMPLE_RATE,
+        **kwargs,
+    ) -> None:
+        """Initialize the HumeTTSService.
+
+        Args:
+            api_key: Hume API key. If omitted, reads the ``HUME_API_KEY`` environment variable.
+            voice_id: ID of the voice to use. Only voice IDs are supported; voice names are not.
+            params: Optional synthesis controls (acting instructions, speed, trailing silence).
+            sample_rate: Output sample rate for emitted PCM frames. Defaults to 48_000 (Hume).
+            **kwargs: Additional arguments passed to the parent class.
+        """
+        api_key = api_key or os.getenv("HUME_API_KEY")
+        if not api_key:
+            raise ValueError("HumeTTSService requires an API key (env HUME_API_KEY or api_key=)")
+
+        if sample_rate != HUME_SAMPLE_RATE:
+            logger.warning(
+                f"Hume TTS streams at {HUME_SAMPLE_RATE} Hz; configured sample_rate={sample_rate}"
+            )
+
+        super().__init__(sample_rate=sample_rate, **kwargs)
+
+        self._client = AsyncHumeClient(api_key=api_key)
+        self._params = params or HumeTTSService.InputParams()
+
+        # Store voice in the base class (mirrors other services)
+        self.set_voice(voice_id)
+
+        self._audio_bytes = b""
+
+    def can_generate_metrics(self) -> bool:
+        """Can generate metrics.
+
+        Returns:
+            True if metrics can be generated, False otherwise.
+        """
+        return True
+
+    async def start(self, frame: StartFrame) -> None:
+        """Start the service.
+
+        Args:
+            frame: The start frame.
+        """
+        await super().start(frame)
+
+    async def update_setting(self, key: str, value: Any) -> None:
+        """Runtime updates via `TTSUpdateSettingsFrame`.
+
+        Args:
+            key: The name of the setting to update. Recognized keys are:
+                - "voice_id"
+                - "description"
+                - "speed"
+                - "trailing_silence"
+            value: The new value for the setting.
+        """
+        key_l = (key or "").lower()
+
+        if key_l == "voice_id":
+            self.set_voice(str(value))
+            logger.info(f"HumeTTSService voice_id set to: {self.voice}")
+        elif key_l == "description":
+            self._params.description = None if value is None else str(value)
+        elif key_l == "speed":
+            self._params.speed = None if value is None else float(value)
+        elif key_l == "trailing_silence":
+            self._params.trailing_silence = None if value is None else float(value)
+        else:
+            # Defer unknown keys to the base class
+            await super().update_setting(key, value)
+
+    @traced_tts
+    async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
+        """Generate speech from text using Hume TTS.
+
+        Args:
+            text: The text to be synthesized.
+
+        Returns:
+            An async generator that yields `Frame` objects, including
+            `TTSStartedFrame`, `TTSAudioRawFrame`, `ErrorFrame`, and
+            `TTSStoppedFrame`.
+        """
+        logger.debug(f"{self}: Generating Hume TTS: [{text}]")
+
+        # Build the request payload
+        utterance_kwargs: dict[str, Any] = {
+            "text": text,
+            "voice": PostedUtteranceVoiceWithId(id=self._voice_id),
+        }
+        if self._params.description is not None:
+            utterance_kwargs["description"] = self._params.description
+        if self._params.speed is not None:
+            utterance_kwargs["speed"] = self._params.speed
+        if self._params.trailing_silence is not None:
+            utterance_kwargs["trailing_silence"] = self._params.trailing_silence
+
+        utterance = PostedUtterance(**utterance_kwargs)
+
+        # Request raw PCM chunks in the streaming JSON
+        pcm_fmt = FormatPcm(type="pcm")
+
+        await self.start_ttfb_metrics()
+        await self.start_tts_usage_metrics(text)
+        yield TTSStartedFrame()
+
+        try:
+            # Instant mode is always enabled here (not user-configurable)
+            # Hume emits mono PCM at 48 kHz; downstream can resample if needed.
+            # We buffer audio bytes before sending to prevent glitches.
+            self._audio_bytes = b""
+            async for chunk in self._client.tts.synthesize_json_streaming(
+                utterances=[utterance],
+                format=pcm_fmt,
+                instant_mode=True,
+                version="2",
+            ):
+                audio_b64 = getattr(chunk, "audio", None)
+                if not audio_b64:
+                    continue
+
+                pcm_bytes = base64.b64decode(audio_b64)
+                self._audio_bytes += pcm_bytes
+
+                # Buffer audio until we have enough to avoid glitches
+                if len(self._audio_bytes) < self.chunk_size:
+                    continue
+
+                frame = TTSAudioRawFrame(
+                    audio=self._audio_bytes,
+                    sample_rate=self.sample_rate,
+                    num_channels=1,
+                )
+
+                yield frame
+
+                self._audio_bytes = b""
+
+        except Exception as e:
+            logger.exception(f"{self} error generating TTS: {e}")
+            await self.push_error(ErrorFrame(f"Error generating TTS: {e}"))
+        finally:
+            # Ensure TTFB timer is stopped even on early failures
+            await self.stop_ttfb_metrics()
+            yield TTSStoppedFrame()

src/pipecat/services/openai/__init__.py

@@ -10,6 +10,7 @@ from pipecat.services import DeprecatedModuleProxy
 
 from .image import *
 from .llm import *
+from .realtime import *
 from .stt import *
 from .tts import *
 

src/pipecat/services/openai/base_llm.py

@@ -66,6 +66,7 @@ class BaseOpenAILLMService(LLMService):
             top_p: Top-p (nucleus) sampling parameter (0.0 to 1.0).
             max_tokens: Maximum tokens in response (deprecated, use max_completion_tokens).
             max_completion_tokens: Maximum completion tokens to generate.
+            service_tier: Service tier to use (e.g., "auto", "flex", "priority").
             extra: Additional model-specific parameters.
         """
 
@@ -83,6 +84,7 @@ class BaseOpenAILLMService(LLMService):
         top_p: Optional[float] = Field(default_factory=lambda: NOT_GIVEN, ge=0.0, le=1.0)
         max_tokens: Optional[int] = Field(default_factory=lambda: NOT_GIVEN, ge=1)
         max_completion_tokens: Optional[int] = Field(default_factory=lambda: NOT_GIVEN, ge=1)
+        service_tier: Optional[str] = Field(default_factory=lambda: NOT_GIVEN)
         extra: Optional[Dict[str, Any]] = Field(default_factory=dict)
 
     def __init__(
@@ -125,6 +127,7 @@ class BaseOpenAILLMService(LLMService):
             "top_p": params.top_p,
             "max_tokens": params.max_tokens,
             "max_completion_tokens": params.max_completion_tokens,
+            "service_tier": params.service_tier,
             "extra": params.extra if isinstance(params.extra, dict) else {},
         }
         self._retry_timeout_secs = retry_timeout_secs
@@ -236,6 +239,7 @@ class BaseOpenAILLMService(LLMService):
             "top_p": self._settings["top_p"],
             "max_tokens": self._settings["max_tokens"],
             "max_completion_tokens": self._settings["max_completion_tokens"],
+            "service_tier": self._settings["service_tier"],
         }
 
         # Messages, tools, tool_choice

src/pipecat/services/openai/realtime/context.py

@@ -0,0 +1,272 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""OpenAI Realtime LLM context and aggregator implementations."""
+
+import copy
+import json
+
+from loguru import logger
+
+from pipecat.frames.frames import (
+    Frame,
+    FunctionCallResultFrame,
+    InterimTranscriptionFrame,
+    LLMMessagesUpdateFrame,
+    LLMSetToolsFrame,
+    LLMTextFrame,
+    TranscriptionFrame,
+)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.frame_processor import FrameDirection
+from pipecat.services.openai.llm import (
+    OpenAIAssistantContextAggregator,
+    OpenAIUserContextAggregator,
+)
+
+from . import events
+from .frames import RealtimeFunctionCallResultFrame, RealtimeMessagesUpdateFrame
+
+
+class OpenAIRealtimeLLMContext(OpenAILLMContext):
+    """OpenAI Realtime LLM context with session management and message conversion.
+
+    Extends the standard OpenAI LLM context to support real-time session properties,
+    instruction management, and conversion between standard message formats and
+    realtime conversation items.
+    """
+
+    def __init__(self, messages=None, tools=None, **kwargs):
+        """Initialize the OpenAIRealtimeLLMContext.
+
+        Args:
+            messages: Initial conversation messages. Defaults to None.
+            tools: Available function tools. Defaults to None.
+            **kwargs: Additional arguments passed to parent OpenAILLMContext.
+        """
+        super().__init__(messages=messages, tools=tools, **kwargs)
+        self.__setup_local()
+
+    def __setup_local(self):
+        self.llm_needs_settings_update = True
+        self.llm_needs_initial_messages = True
+        self._session_instructions = ""
+
+        return
+
+    @staticmethod
+    def upgrade_to_realtime(obj: OpenAILLMContext) -> "OpenAIRealtimeLLMContext":
+        """Upgrade a standard OpenAI LLM context to a realtime context.
+
+        Args:
+            obj: The OpenAILLMContext instance to upgrade.
+
+        Returns:
+            The upgraded OpenAIRealtimeLLMContext instance.
+        """
+        if isinstance(obj, OpenAILLMContext) and not isinstance(obj, OpenAIRealtimeLLMContext):
+            obj.__class__ = OpenAIRealtimeLLMContext
+            obj.__setup_local()
+        return obj
+
+    # todo
+    #   - finish implementing all frames
+
+    def from_standard_message(self, message):
+        """Convert a standard message format to a realtime conversation item.
+
+        Args:
+            message: The standard message dictionary to convert.
+
+        Returns:
+            A ConversationItem instance for the realtime API.
+        """
+        if message.get("role") == "user":
+            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}"
+                        )
+            return events.ConversationItem(
+                role="user",
+                type="message",
+                content=[events.ItemContent(type="input_text", text=content)],
+            )
+        if message.get("role") == "assistant" and message.get("tool_calls"):
+            tc = message.get("tool_calls")[0]
+            return events.ConversationItem(
+                type="function_call",
+                call_id=tc["id"],
+                name=tc["function"]["name"],
+                arguments=tc["function"]["arguments"],
+            )
+        logger.error(f"Unhandled message type in from_standard_message: {message}")
+
+    def get_messages_for_initializing_history(self):
+        """Get conversation items for initializing the realtime session history.
+
+        Converts the context's messages to a format suitable for the realtime API,
+        handling system instructions and conversation history packaging.
+
+        Returns:
+            List of conversation items for session initialization.
+        """
+        # We can't load a long conversation history into the openai realtime api yet. (The API/model
+        # forgets that it can do audio, if you do a series of `conversation.item.create` calls.) So
+        # our general strategy until this is fixed is just to put everything into a first "user"
+        # message as a single input.
+        if not self.messages:
+            return []
+
+        messages = copy.deepcopy(self.messages)
+
+        # If we have a "system" message as our first message, let's pull that out into session
+        # "instructions"
+        if messages[0].get("role") == "system":
+            self.llm_needs_settings_update = True
+            system = messages.pop(0)
+            content = system.get("content")
+            if isinstance(content, str):
+                self._session_instructions = content
+            elif isinstance(content, list):
+                self._session_instructions = content[0].get("text")
+            if not messages:
+                return []
+
+        # If we have just a single "user" item, we can just send it normally
+        if len(messages) == 1 and messages[0].get("role") == "user":
+            return [self.from_standard_message(messages[0])]
+
+        # Otherwise, let's pack everything into a single "user" message with a bit of
+        # explanation for the LLM
+        intro_text = """
+        This is a previously saved conversation. Please treat this conversation history as a
+        starting point for the current conversation."""
+
+        trailing_text = """
+        This is the end of the previously saved conversation. Please continue the conversation
+        from here. If the last message is a user instruction or question, act on that instruction
+        or answer the question. If the last message is an assistant response, simple say that you
+        are ready to continue the conversation."""
+
+        return [
+            {
+                "role": "user",
+                "type": "message",
+                "content": [
+                    {
+                        "type": "input_text",
+                        "text": "\n\n".join(
+                            [intro_text, json.dumps(messages, indent=2), trailing_text]
+                        ),
+                    }
+                ],
+            }
+        ]
+
+    def add_user_content_item_as_message(self, item):
+        """Add a user content item as a standard message to the context.
+
+        Args:
+            item: The conversation item to add as a user message.
+        """
+        message = {
+            "role": "user",
+            "content": [{"type": "text", "text": item.content[0].transcript}],
+        }
+        self.add_message(message)
+
+
+class OpenAIRealtimeUserContextAggregator(OpenAIUserContextAggregator):
+    """User context aggregator for OpenAI Realtime API.
+
+    Handles user input frames and generates appropriate context updates
+    for the realtime conversation, including message updates and tool settings.
+
+    Args:
+        context: The OpenAI realtime LLM context.
+        **kwargs: Additional arguments passed to parent aggregator.
+    """
+
+    async def process_frame(
+        self, frame: Frame, direction: FrameDirection = FrameDirection.DOWNSTREAM
+    ):
+        """Process incoming frames and handle realtime-specific frame types.
+
+        Args:
+            frame: The frame to process.
+            direction: The direction of frame flow in the pipeline.
+        """
+        await super().process_frame(frame, direction)
+        # Parent does not push LLMMessagesUpdateFrame. This ensures that in a typical pipeline,
+        # messages are only processed by the user context aggregator, which is generally what we want. But
+        # we also need to send new messages over the websocket, so the openai realtime API has them
+        # in its context.
+        if isinstance(frame, LLMMessagesUpdateFrame):
+            await self.push_frame(RealtimeMessagesUpdateFrame(context=self._context))
+
+        # Parent also doesn't push the LLMSetToolsFrame.
+        if isinstance(frame, LLMSetToolsFrame):
+            await self.push_frame(frame, direction)
+
+    async def push_aggregation(self):
+        """Push user input aggregation.
+
+        Currently ignores all user input coming into the pipeline as realtime
+        audio input is handled directly by the service.
+        """
+        # for the moment, ignore all user input coming into the pipeline.
+        # todo: think about whether/how to fix this to allow for text input from
+        #       upstream (transport/transcription, or other sources)
+        pass
+
+
+class OpenAIRealtimeAssistantContextAggregator(OpenAIAssistantContextAggregator):
+    """Assistant context aggregator for OpenAI Realtime API.
+
+    Handles assistant output frames from the realtime service, filtering
+    out duplicate text frames and managing function call results.
+
+    Args:
+        context: The OpenAI realtime LLM context.
+        **kwargs: Additional arguments passed to parent aggregator.
+    """
+
+    # The LLMAssistantContextAggregator uses TextFrames to aggregate the LLM output,
+    # but the OpenAIRealtimeLLMService pushes LLMTextFrames and TTSTextFrames. We
+    # need to override this proces_frame for LLMTextFrame, so that only the TTSTextFrames
+    # are process. This ensures that the context gets only one set of messages.
+    # OpenAIRealtimeLLMService also pushes TranscriptionFrames and InterimTranscriptionFrames,
+    # so we need to ignore pushing those as well, as they're also TextFrames.
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        """Process assistant frames, filtering out duplicate text content.
+
+        Args:
+            frame: The frame to process.
+            direction: The direction of frame flow in the pipeline.
+        """
+        if not isinstance(frame, (LLMTextFrame, TranscriptionFrame, InterimTranscriptionFrame)):
+            await super().process_frame(frame, direction)
+
+    async def handle_function_call_result(self, frame: FunctionCallResultFrame):
+        """Handle function call result and notify the realtime service.
+
+        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 openai realtime api context. Let's push a
+        # special frame to do that.
+        await self.push_frame(
+            RealtimeFunctionCallResultFrame(result_frame=frame), FrameDirection.UPSTREAM
+        )

src/pipecat/services/openai/realtime/frames.py

@@ -0,0 +1,37 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Custom frame types for OpenAI Realtime API integration."""
+
+from dataclasses import dataclass
+from typing import TYPE_CHECKING
+
+from pipecat.frames.frames import DataFrame, FunctionCallResultFrame
+
+if TYPE_CHECKING:
+    from pipecat.services.openai.realtime.context import OpenAIRealtimeLLMContext
+
+
+@dataclass
+class RealtimeMessagesUpdateFrame(DataFrame):
+    """Frame indicating that the realtime context messages have been updated.
+
+    Parameters:
+        context: The updated OpenAI realtime LLM context.
+    """
+
+    context: "OpenAIRealtimeLLMContext"
+
+
+@dataclass
+class RealtimeFunctionCallResultFrame(DataFrame):
+    """Frame containing function call results for the realtime service.
+
+    Parameters:
+        result_frame: The function call result frame to send to the realtime API.
+    """
+
+    result_frame: FunctionCallResultFrame

src/pipecat/services/openai_realtime/__init__.py

@@ -1,9 +1,27 @@
-from .azure import AzureRealtimeLLMService
-from .events import (
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import warnings
+
+from pipecat.services.azure.realtime.llm import AzureRealtimeLLMService
+from pipecat.services.openai.realtime.events import (
     InputAudioNoiseReduction,
     InputAudioTranscription,
     SemanticTurnDetection,
     SessionProperties,
     TurnDetection,
 )
-from .openai import OpenAIRealtimeLLMService
+from pipecat.services.openai.realtime.llm import OpenAIRealtimeLLMService
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.openai_realtime are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.openai.realtime instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

src/pipecat/services/openai_realtime/azure.py

@@ -1,67 +1,21 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 """Azure OpenAI Realtime LLM service implementation."""
 
-from loguru import logger
+import warnings
 
-from .openai import OpenAIRealtimeLLMService
+from pipecat.services.azure.realtime.llm import *
 
-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 OpenAI, you need to `pip install pipecat-ai[openai]`. Also, set `OPENAI_API_KEY` environment variable."
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.openai_realtime.azure are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.azure.realtime.llm instead.",
+        DeprecationWarning,
+        stacklevel=2,
     )
-    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/openai_realtime/context.py

@@ -1,272 +1,21 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 """OpenAI Realtime LLM context and aggregator implementations."""
 
-import copy
-import json
+import warnings
 
-from loguru import logger
+from pipecat.services.openai.realtime.context import *
 
-from pipecat.frames.frames import (
-    Frame,
-    FunctionCallResultFrame,
-    InterimTranscriptionFrame,
-    LLMMessagesUpdateFrame,
-    LLMSetToolsFrame,
-    LLMTextFrame,
-    TranscriptionFrame,
-)
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.processors.frame_processor import FrameDirection
-from pipecat.services.openai.llm import (
-    OpenAIAssistantContextAggregator,
-    OpenAIUserContextAggregator,
-)
-
-from . import events
-from .frames import RealtimeFunctionCallResultFrame, RealtimeMessagesUpdateFrame
-
-
-class OpenAIRealtimeLLMContext(OpenAILLMContext):
-    """OpenAI Realtime LLM context with session management and message conversion.
-
-    Extends the standard OpenAI LLM context to support real-time session properties,
-    instruction management, and conversion between standard message formats and
-    realtime conversation items.
-    """
-
-    def __init__(self, messages=None, tools=None, **kwargs):
-        """Initialize the OpenAIRealtimeLLMContext.
-
-        Args:
-            messages: Initial conversation messages. Defaults to None.
-            tools: Available function tools. Defaults to None.
-            **kwargs: Additional arguments passed to parent OpenAILLMContext.
-        """
-        super().__init__(messages=messages, tools=tools, **kwargs)
-        self.__setup_local()
-
-    def __setup_local(self):
-        self.llm_needs_settings_update = True
-        self.llm_needs_initial_messages = True
-        self._session_instructions = ""
-
-        return
-
-    @staticmethod
-    def upgrade_to_realtime(obj: OpenAILLMContext) -> "OpenAIRealtimeLLMContext":
-        """Upgrade a standard OpenAI LLM context to a realtime context.
-
-        Args:
-            obj: The OpenAILLMContext instance to upgrade.
-
-        Returns:
-            The upgraded OpenAIRealtimeLLMContext instance.
-        """
-        if isinstance(obj, OpenAILLMContext) and not isinstance(obj, OpenAIRealtimeLLMContext):
-            obj.__class__ = OpenAIRealtimeLLMContext
-            obj.__setup_local()
-        return obj
-
-    # todo
-    #   - finish implementing all frames
-
-    def from_standard_message(self, message):
-        """Convert a standard message format to a realtime conversation item.
-
-        Args:
-            message: The standard message dictionary to convert.
-
-        Returns:
-            A ConversationItem instance for the realtime API.
-        """
-        if message.get("role") == "user":
-            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}"
-                        )
-            return events.ConversationItem(
-                role="user",
-                type="message",
-                content=[events.ItemContent(type="input_text", text=content)],
-            )
-        if message.get("role") == "assistant" and message.get("tool_calls"):
-            tc = message.get("tool_calls")[0]
-            return events.ConversationItem(
-                type="function_call",
-                call_id=tc["id"],
-                name=tc["function"]["name"],
-                arguments=tc["function"]["arguments"],
-            )
-        logger.error(f"Unhandled message type in from_standard_message: {message}")
-
-    def get_messages_for_initializing_history(self):
-        """Get conversation items for initializing the realtime session history.
-
-        Converts the context's messages to a format suitable for the realtime API,
-        handling system instructions and conversation history packaging.
-
-        Returns:
-            List of conversation items for session initialization.
-        """
-        # We can't load a long conversation history into the openai realtime api yet. (The API/model
-        # forgets that it can do audio, if you do a series of `conversation.item.create` calls.) So
-        # our general strategy until this is fixed is just to put everything into a first "user"
-        # message as a single input.
-        if not self.messages:
-            return []
-
-        messages = copy.deepcopy(self.messages)
-
-        # If we have a "system" message as our first message, let's pull that out into session
-        # "instructions"
-        if messages[0].get("role") == "system":
-            self.llm_needs_settings_update = True
-            system = messages.pop(0)
-            content = system.get("content")
-            if isinstance(content, str):
-                self._session_instructions = content
-            elif isinstance(content, list):
-                self._session_instructions = content[0].get("text")
-            if not messages:
-                return []
-
-        # If we have just a single "user" item, we can just send it normally
-        if len(messages) == 1 and messages[0].get("role") == "user":
-            return [self.from_standard_message(messages[0])]
-
-        # Otherwise, let's pack everything into a single "user" message with a bit of
-        # explanation for the LLM
-        intro_text = """
-        This is a previously saved conversation. Please treat this conversation history as a
-        starting point for the current conversation."""
-
-        trailing_text = """
-        This is the end of the previously saved conversation. Please continue the conversation
-        from here. If the last message is a user instruction or question, act on that instruction
-        or answer the question. If the last message is an assistant response, simple say that you
-        are ready to continue the conversation."""
-
-        return [
-            {
-                "role": "user",
-                "type": "message",
-                "content": [
-                    {
-                        "type": "input_text",
-                        "text": "\n\n".join(
-                            [intro_text, json.dumps(messages, indent=2), trailing_text]
-                        ),
-                    }
-                ],
-            }
-        ]
-
-    def add_user_content_item_as_message(self, item):
-        """Add a user content item as a standard message to the context.
-
-        Args:
-            item: The conversation item to add as a user message.
-        """
-        message = {
-            "role": "user",
-            "content": [{"type": "text", "text": item.content[0].transcript}],
-        }
-        self.add_message(message)
-
-
-class OpenAIRealtimeUserContextAggregator(OpenAIUserContextAggregator):
-    """User context aggregator for OpenAI Realtime API.
-
-    Handles user input frames and generates appropriate context updates
-    for the realtime conversation, including message updates and tool settings.
-
-    Args:
-        context: The OpenAI realtime LLM context.
-        **kwargs: Additional arguments passed to parent aggregator.
-    """
-
-    async def process_frame(
-        self, frame: Frame, direction: FrameDirection = FrameDirection.DOWNSTREAM
-    ):
-        """Process incoming frames and handle realtime-specific frame types.
-
-        Args:
-            frame: The frame to process.
-            direction: The direction of frame flow in the pipeline.
-        """
-        await super().process_frame(frame, direction)
-        # Parent does not push LLMMessagesUpdateFrame. This ensures that in a typical pipeline,
-        # messages are only processed by the user context aggregator, which is generally what we want. But
-        # we also need to send new messages over the websocket, so the openai realtime API has them
-        # in its context.
-        if isinstance(frame, LLMMessagesUpdateFrame):
-            await self.push_frame(RealtimeMessagesUpdateFrame(context=self._context))
-
-        # Parent also doesn't push the LLMSetToolsFrame.
-        if isinstance(frame, LLMSetToolsFrame):
-            await self.push_frame(frame, direction)
-
-    async def push_aggregation(self):
-        """Push user input aggregation.
-
-        Currently ignores all user input coming into the pipeline as realtime
-        audio input is handled directly by the service.
-        """
-        # for the moment, ignore all user input coming into the pipeline.
-        # todo: think about whether/how to fix this to allow for text input from
-        #       upstream (transport/transcription, or other sources)
-        pass
-
-
-class OpenAIRealtimeAssistantContextAggregator(OpenAIAssistantContextAggregator):
-    """Assistant context aggregator for OpenAI Realtime API.
-
-    Handles assistant output frames from the realtime service, filtering
-    out duplicate text frames and managing function call results.
-
-    Args:
-        context: The OpenAI realtime LLM context.
-        **kwargs: Additional arguments passed to parent aggregator.
-    """
-
-    # The LLMAssistantContextAggregator uses TextFrames to aggregate the LLM output,
-    # but the OpenAIRealtimeLLMService pushes LLMTextFrames and TTSTextFrames. We
-    # need to override this proces_frame for LLMTextFrame, so that only the TTSTextFrames
-    # are process. This ensures that the context gets only one set of messages.
-    # OpenAIRealtimeLLMService also pushes TranscriptionFrames and InterimTranscriptionFrames,
-    # so we need to ignore pushing those as well, as they're also TextFrames.
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        """Process assistant frames, filtering out duplicate text content.
-
-        Args:
-            frame: The frame to process.
-            direction: The direction of frame flow in the pipeline.
-        """
-        if not isinstance(frame, (LLMTextFrame, TranscriptionFrame, InterimTranscriptionFrame)):
-            await super().process_frame(frame, direction)
-
-    async def handle_function_call_result(self, frame: FunctionCallResultFrame):
-        """Handle function call result and notify the realtime service.
-
-        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 openai realtime api context. Let's push a
-        # special frame to do that.
-        await self.push_frame(
-            RealtimeFunctionCallResultFrame(result_frame=frame), FrameDirection.UPSTREAM
-        )
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.openai_realtime.context are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.openai.realtime.context instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

src/pipecat/services/openai_realtime/frames.py

@@ -1,37 +1,21 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 """Custom frame types for OpenAI Realtime API integration."""
 
-from dataclasses import dataclass
-from typing import TYPE_CHECKING
+import warnings
 
-from pipecat.frames.frames import DataFrame, FunctionCallResultFrame
+from pipecat.services.openai.realtime.frames import *
 
-if TYPE_CHECKING:
-    from pipecat.services.openai_realtime_beta.context import OpenAIRealtimeLLMContext
-
-
-@dataclass
-class RealtimeMessagesUpdateFrame(DataFrame):
-    """Frame indicating that the realtime context messages have been updated.
-
-    Parameters:
-        context: The updated OpenAI realtime LLM context.
-    """
-
-    context: "OpenAIRealtimeLLMContext"
-
-
-@dataclass
-class RealtimeFunctionCallResultFrame(DataFrame):
-    """Frame containing function call results for the realtime service.
-
-    Parameters:
-        result_frame: The function call result frame to send to the realtime API.
-    """
-
-    result_frame: FunctionCallResultFrame
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.openai_realtime.frames are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.openai.realtime.frames instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

src/pipecat/services/piper/tts.py

@@ -14,7 +14,6 @@ from loguru import logger
 from pipecat.frames.frames import (
     ErrorFrame,
     Frame,
-    TTSAudioRawFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
 )
@@ -99,16 +98,15 @@ class PiperTTSService(TTSService):
 
                 await self.start_tts_usage_metrics(text)
 
+                yield TTSStartedFrame()
+
                 CHUNK_SIZE = self.chunk_size
 
-                yield TTSStartedFrame()
-                async for chunk in response.content.iter_chunked(CHUNK_SIZE):
-                    # remove wav header if present
-                    if chunk.startswith(b"RIFF"):
-                        chunk = chunk[44:]
-                    if len(chunk) > 0:
-                        await self.stop_ttfb_metrics()
-                        yield TTSAudioRawFrame(chunk, self.sample_rate, 1)
+                async for frame in self._stream_audio_frames_from_iterator(
+                    response.content.iter_chunked(CHUNK_SIZE), strip_wav_header=True
+                ):
+                    await self.stop_ttfb_metrics()
+                    yield frame
         except Exception as e:
             logger.error(f"Error in run_tts: {e}")
             yield ErrorFrame(error=str(e))

src/pipecat/services/playht/tts.py

@@ -14,6 +14,7 @@ import io
 import json
 import struct
 import uuid
+import warnings
 from typing import AsyncGenerator, Optional
 
 import aiohttp
@@ -110,6 +111,11 @@ def language_to_playht_language(language: Language) -> Optional[str]:
 class PlayHTTTSService(InterruptibleTTSService):
     """PlayHT WebSocket-based text-to-speech service.
 
+    .. deprecated:: 0.0.88
+
+        This class is deprecated and will be removed in a future version.
+        PlayHT is shutting down their API on December 31st, 2025.
+
     Provides real-time text-to-speech synthesis using PlayHT's WebSocket API.
     Supports streaming audio generation with configurable voice engines and
     language settings.
@@ -158,6 +164,15 @@ class PlayHTTTSService(InterruptibleTTSService):
             **kwargs,
         )
 
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "PlayHT is shutting down their API on December 31st, 2025. "
+                "'PlayHTTTSService' is deprecated and will be removed in a future version.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
         params = params or PlayHTTTSService.InputParams()
 
         self._api_key = api_key
@@ -401,6 +416,11 @@ class PlayHTTTSService(InterruptibleTTSService):
 class PlayHTHttpTTSService(TTSService):
     """PlayHT HTTP-based text-to-speech service.
 
+    .. deprecated:: 0.0.88
+
+        This class is deprecated and will be removed in a future version.
+        PlayHT is shutting down their API on December 31st, 2025.
+
     Provides text-to-speech synthesis using PlayHT's HTTP API for simpler,
     non-streaming synthesis. Suitable for use cases where streaming is not
     required and simpler integration is preferred.
@@ -454,8 +474,6 @@ class PlayHTHttpTTSService(TTSService):
 
         # Warn about deprecated protocol parameter if explicitly provided
         if protocol:
-            import warnings
-
             with warnings.catch_warnings():
                 warnings.simplefilter("always")
                 warnings.warn(
@@ -464,6 +482,15 @@ class PlayHTHttpTTSService(TTSService):
                     stacklevel=2,
                 )
 
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "PlayHT is shutting down their API on December 31st, 2025. "
+                "'PlayHTHttpTTSService' is deprecated and will be removed in a future version.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
         params = params or PlayHTHttpTTSService.InputParams()
 
         self._user_id = user_id

src/pipecat/services/rime/tts.py

@@ -553,15 +553,13 @@ class RimeHttpTTSService(TTSService):
 
                 CHUNK_SIZE = self.chunk_size
 
-                async for chunk in response.content.iter_chunked(CHUNK_SIZE):
-                    if need_to_strip_wav_header and chunk.startswith(b"RIFF"):
-                        chunk = chunk[44:]
-                        need_to_strip_wav_header = False
+                async for frame in self._stream_audio_frames_from_iterator(
+                    response.content.iter_chunked(CHUNK_SIZE),
+                    strip_wav_header=need_to_strip_wav_header,
+                ):
+                    await self.stop_ttfb_metrics()
+                    yield frame
 
-                    if len(chunk) > 0:
-                        await self.stop_ttfb_metrics()
-                        frame = TTSAudioRawFrame(chunk, self.sample_rate, 1)
-                        yield frame
         except Exception as e:
             logger.exception(f"Error generating TTS: {e}")
             yield ErrorFrame(error=f"Rime TTS error: {str(e)}")

src/pipecat/services/tts_service.py

@@ -8,7 +8,17 @@
 
 import asyncio
 from abc import abstractmethod
-from typing import Any, AsyncGenerator, Dict, List, Mapping, Optional, Sequence, Tuple
+from typing import (
+    Any,
+    AsyncGenerator,
+    AsyncIterator,
+    Dict,
+    List,
+    Mapping,
+    Optional,
+    Sequence,
+    Tuple,
+)
 
 from loguru import logger
 
@@ -374,6 +384,36 @@ class TTSService(AIService):
         ):
             await self._stop_frame_queue.put(frame)
 
+    async def _stream_audio_frames_from_iterator(
+        self, iterator: AsyncIterator[bytes], *, strip_wav_header: bool
+    ) -> AsyncGenerator[Frame, None]:
+        buffer = bytearray()
+        need_to_strip_wav_header = strip_wav_header
+        async for chunk in iterator:
+            if need_to_strip_wav_header and chunk.startswith(b"RIFF"):
+                chunk = chunk[44:]
+                need_to_strip_wav_header = False
+
+            # Append to current buffer.
+            buffer.extend(chunk)
+
+            # Round to nearest even number.
+            aligned_length = len(buffer) & ~1  # 111111111...11110
+            if aligned_length > 0:
+                aligned_chunk = buffer[:aligned_length]
+                buffer = buffer[aligned_length:]  # keep any leftover byte
+
+                if len(aligned_chunk) > 0:
+                    frame = TTSAudioRawFrame(bytes(aligned_chunk), self.sample_rate, 1)
+                    yield frame
+
+        if len(buffer) > 0:
+            # Make sure we don't need an extra padding byte.
+            if len(buffer) % 2 == 1:
+                buffer.extend(b"\x00")
+            frame = TTSAudioRawFrame(bytes(buffer), self.sample_rate, 1)
+            yield frame
+
     async def _handle_interruption(self, frame: InterruptionFrame, direction: FrameDirection):
         self._processing_text = False
         await self._text_aggregator.handle_interruption()

src/pipecat/transports/livekit/transport.py

@@ -354,10 +354,10 @@ class LiveKitTransportClient:
             logger.error(f"Error sending data: {e}")
 
     async def send_dtmf(self, digit: str):
-        """Send DTMF tone to the room.
+        r"""Send DTMF tone to the room.
 
         Args:
-            digit: The DTMF digit to send (0-9, *, #).
+            digit: The DTMF digit to send (0-9, \*, #).
         """
         if not self._connected:
             return

src/pipecat/transports/smallwebrtc/request_handler.py

@@ -116,6 +116,10 @@ class SmallWebRTCRequestHandler:
                 detail="Cannot create new connection with existing connection active",
             )
 
+    def update_ice_servers(self, ice_servers: Optional[List[IceServer]] = None):
+        """Update the list of ICE servers used for WebRTC connections."""
+        self._ice_servers = ice_servers
+
     async def handle_web_request(
         self,
         request: SmallWebRTCRequest,

src/pipecat/transports/whatsapp/api.py

@@ -241,6 +241,14 @@ class WhatsAppApi:
         self._whatsapp_url = f"{self.BASE_URL}{phone_number_id}/calls"
         self._whatsapp_token = whatsapp_token
 
+    def update_whatsapp_token(self, whatsapp_token: str):
+        """Update the WhatsApp access token for authentication."""
+        self._whatsapp_token = whatsapp_token
+
+    def update_whatsapp_phone_number_id(self, phone_number_id: str):
+        """Update the WhatsApp phone number ID for authentication."""
+        self._phone_number_id = phone_number_id
+
     async def answer_call_to_whatsapp(self, call_id: str, action: str, sdp: str, from_: str):
         """Answer an incoming WhatsApp call.
 

src/pipecat/transports/whatsapp/client.py

@@ -12,6 +12,8 @@ WhatsApp call events.
 """
 
 import asyncio
+import hashlib
+import hmac
 from typing import Awaitable, Callable, Dict, List, Optional
 
 import aiohttp
@@ -47,6 +49,7 @@ class WhatsAppClient:
         phone_number_id: str,
         session: aiohttp.ClientSession,
         ice_servers: Optional[List[IceServer]] = None,
+        whatsapp_secret: Optional[str] = None,
     ) -> None:
         """Initialize the WhatsApp client.
 
@@ -56,10 +59,12 @@ class WhatsAppClient:
             session: aiohttp session for making HTTP requests
             ice_servers: List of ICE servers for WebRTC connections. If None,
                         defaults to Google's public STUN server
+            whatsapp_secret: WhatsApp APP secret for validating that the webhook request came from WhatsApp.
         """
         self._whatsapp_api = WhatsAppApi(
             whatsapp_token=whatsapp_token, phone_number_id=phone_number_id, session=session
         )
+        self._whatsapp_secret = whatsapp_secret
         self._ongoing_calls_map: Dict[str, SmallWebRTCConnection] = {}
 
         # Set default ICE servers if none provided
@@ -68,6 +73,22 @@ class WhatsAppClient:
         else:
             self._ice_servers = ice_servers
 
+    def update_ice_servers(self, ice_servers: Optional[List[IceServer]] = None):
+        """Update the list of ICE servers used for WebRTC connections."""
+        self._ice_servers = ice_servers
+
+    def update_whatsapp_secret(self, whatsapp_secret: Optional[str] = None):
+        """Update the WhatsApp APP secret for validating that the webhook request came from WhatsApp."""
+        self._whatsapp_secret = whatsapp_secret
+
+    def update_whatsapp_token(self, whatsapp_token: str):
+        """Update the WhatsApp API access token."""
+        self._whatsapp_api.update_whatsapp_token(whatsapp_token)
+
+    def update_whatsapp_phone_number_id(self, phone_number_id: str):
+        """Update the WhatsApp phone number ID for authentication."""
+        self._whatsapp_api.update_whatsapp_phone_number_id(phone_number_id)
+
     async def terminate_all_calls(self) -> None:
         """Terminate all ongoing WhatsApp calls.
 
@@ -133,10 +154,32 @@ class WhatsAppClient:
 
         return int(challenge)
 
+    async def _validate_whatsapp_webhook_request(self, raw_body: bytes, sha256_signature: str):
+        """Common handler for both /start and /connect endpoints."""
+        # Compute HMAC SHA256 using your App Secret
+        expected_signature = hmac.new(
+            key=self._whatsapp_secret.encode("utf-8"),
+            msg=raw_body,
+            digestmod=hashlib.sha256,
+        ).hexdigest()
+
+        # Extract signature from header (strip 'sha256=' prefix)
+        if not sha256_signature:
+            raise Exception("Missing X-Hub-Signature-256 header")
+        received_signature = sha256_signature.split("sha256=")[-1]
+
+        # Compare signatures securely
+        if not hmac.compare_digest(expected_signature, received_signature):
+            raise Exception("Invalid webhook signature")
+
+        logger.debug(f"Webhook signature verified!")
+
     async def handle_webhook_request(
         self,
         request: WhatsAppWebhookRequest,
         connection_callback: Optional[Callable[[SmallWebRTCConnection], Awaitable[None]]] = None,
+        raw_body: Optional[bytes] = None,
+        sha256_signature: Optional[str] = None,
     ) -> bool:
         """Handle a webhook request from WhatsApp.
 
@@ -150,6 +193,8 @@ class WhatsAppClient:
             connection_callback: Optional callback function to invoke when a new
                                WebRTC connection is established. The callback
                                receives the SmallWebRTCConnection instance.
+            raw_body: Optional bytes containing the raw request body.
+            sha256_signature: Optional X-Hub-Signature-256 header value from the request.
 
         Returns:
             bool: True if the webhook request was handled successfully, False otherwise
@@ -159,6 +204,8 @@ class WhatsAppClient:
             Exception: If connection establishment or API calls fail
         """
         try:
+            if self._whatsapp_secret:
+                await self._validate_whatsapp_webhook_request(raw_body, sha256_signature)
             for entry in request.entry:
                 for change in entry.changes:
                     # Handle connect events

src/pipecat/utils/base_object.py

@@ -29,7 +29,7 @@ class EventHandler:
     This data class stores the event name, a list of handlers to run for this
     event, and whether these handlers will be executed in a task.
 
-    Attributes:
+    Parameters:
         name (str): The name of the event handler.
         handlers (List[Any]): A list of functions to be called when this event is triggered.
         is_sync (bool): Indicates whether the functions are executed in a task.

src/pipecat/utils/string.py

@@ -21,13 +21,24 @@ import re
 from typing import FrozenSet, Optional, Sequence, Tuple
 
 import nltk
+from loguru import logger
 from nltk.tokenize import sent_tokenize
 
 # Ensure punkt_tab tokenizer data is available
 try:
     nltk.data.find("tokenizers/punkt_tab")
 except LookupError:
-    nltk.download("punkt_tab", quiet=True)
+    try:
+        nltk.download("punkt_tab", quiet=True)
+    except (OSError, PermissionError) as e:
+        logger.error(
+            f"Failed to download NLTK 'punkt_tab' tokenizer data: {e}. "
+            "This data is required for sentence tokenization features. "
+            "The download failed due to filesystem permissions. "
+            "To resolve: pre-install the data in a location with appropriate read permissions, "
+            "or set the NLTK_DATA environment variable to point to a writable directory. "
+            "See https://www.nltk.org/data.html for more information."
+        )
 
 SENTENCE_ENDING_PUNCTUATION: FrozenSet[str] = frozenset(
     {

src/pipecat/utils/tracing/service_decorators.py

@@ -651,9 +651,9 @@ def traced_gemini_live(operation: str) -> Callable:
 
                         elif operation == "llm_tool_call" and args:
                             # Extract tool call information
-                            evt = args[0] if args else None
-                            if evt and hasattr(evt, "toolCall") and evt.toolCall.functionCalls:
-                                function_calls = evt.toolCall.functionCalls
+                            msg = args[0] if args else None
+                            if msg and hasattr(msg, "tool_call") and msg.tool_call.function_calls:
+                                function_calls = msg.tool_call.function_calls
                                 if function_calls:
                                     # Add information about the first function call
                                     call = function_calls[0]
@@ -722,19 +722,19 @@ def traced_gemini_live(operation: str) -> Callable:
 
                         elif operation == "llm_response" and args:
                             # Extract usage and response metadata from turn complete event
-                            evt = args[0] if args else None
-                            if evt and hasattr(evt, "usageMetadata") and evt.usageMetadata:
-                                usage = evt.usageMetadata
+                            msg = args[0] if args else None
+                            if msg and hasattr(msg, "usage_metadata") and msg.usage_metadata:
+                                usage = msg.usage_metadata
 
                                 # Token usage - basic attributes for span visibility
-                                if hasattr(usage, "promptTokenCount"):
-                                    operation_attrs["tokens.prompt"] = usage.promptTokenCount or 0
-                                if hasattr(usage, "responseTokenCount"):
+                                if hasattr(usage, "prompt_token_count"):
+                                    operation_attrs["tokens.prompt"] = usage.prompt_token_count or 0
+                                if hasattr(usage, "response_token_count"):
                                     operation_attrs["tokens.completion"] = (
-                                        usage.responseTokenCount or 0
+                                        usage.response_token_count or 0
                                     )
-                                if hasattr(usage, "totalTokenCount"):
-                                    operation_attrs["tokens.total"] = usage.totalTokenCount or 0
+                                if hasattr(usage, "total_token_count"):
+                                    operation_attrs["tokens.total"] = usage.total_token_count or 0
 
                             # Get output text and modality from service state
                             text = getattr(self, "_bot_text_buffer", "")
@@ -751,9 +751,9 @@ def traced_gemini_live(operation: str) -> Callable:
 
                             # Add turn completion status
                             if (
-                                evt
-                                and hasattr(evt, "serverContent")
-                                and evt.serverContent.turnComplete
+                                msg
+                                and hasattr(msg, "server_content")
+                                and msg.server_content.turn_complete
                             ):
                                 operation_attrs["turn_complete"] = True
 
@@ -772,16 +772,16 @@ def traced_gemini_live(operation: str) -> Callable:
 
                         # For llm_response operation, also handle token usage metrics
                         if operation == "llm_response" and hasattr(self, "start_llm_usage_metrics"):
-                            evt = args[0] if args else None
-                            if evt and hasattr(evt, "usageMetadata") and evt.usageMetadata:
-                                usage = evt.usageMetadata
+                            msg = args[0] if args else None
+                            if msg and hasattr(msg, "usage_metadata") and msg.usage_metadata:
+                                usage = msg.usage_metadata
                                 # Create LLMTokenUsage object
                                 from pipecat.metrics.metrics import LLMTokenUsage
 
                                 tokens = LLMTokenUsage(
-                                    prompt_tokens=usage.promptTokenCount or 0,
-                                    completion_tokens=usage.responseTokenCount or 0,
-                                    total_tokens=usage.totalTokenCount or 0,
+                                    prompt_tokens=usage.prompt_token_count or 0,
+                                    completion_tokens=usage.response_token_count or 0,
+                                    total_tokens=usage.total_token_count or 0,
                                 )
                                 _add_token_usage_to_span(current_span, tokens)
 

tests/test_pipeline.py

@@ -11,6 +11,7 @@ import unittest
 from pipecat.frames.frames import (
     CancelFrame,
     EndFrame,
+    ErrorFrame,
     Frame,
     HeartbeatFrame,
     InputAudioRawFrame,
@@ -450,3 +451,34 @@ class TestPipelineTask(unittest.IsolatedAsyncioTestCase):
             await task.run(PipelineTaskParams(loop=asyncio.get_event_loop()))
         except asyncio.CancelledError:
             assert cancelled
+
+    async def test_task_error(self):
+        class ErrorProcessor(FrameProcessor):
+            def __init__(self, **kwargs):
+                super().__init__(**kwargs)
+
+            async def process_frame(self, frame: Frame, direction: FrameDirection):
+                await super().process_frame(frame, direction)
+
+                if isinstance(frame, TextFrame):
+                    await self.push_error(ErrorFrame("Boo!"))
+
+                await self.push_frame(frame, direction)
+
+        error_received = False
+
+        pipeline = Pipeline([ErrorProcessor()])
+        task = PipelineTask(pipeline)
+
+        @task.event_handler("on_pipeline_error")
+        async def on_pipeline_error(task: PipelineTask, frame: ErrorFrame):
+            nonlocal error_received
+            error_received = True
+            await task.cancel()
+
+        await task.queue_frame(TextFrame(text="Hello from Pipecat!"))
+
+        try:
+            await task.run(PipelineTaskParams(loop=asyncio.get_event_loop()))
+        except asyncio.CancelledError:
+            assert error_received