example: realtime with transcripts

PipelineTask: force constructor keyword arguments

.github/workflows/coverage.yaml

@@ -0,0 +1,54 @@
+name: coverage
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - "**"
+    paths-ignore:
+      - "docs/**"
+
+jobs:
+  coverage:
+    name: "Coverage"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+      - name: Set up Python
+        id: setup_python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Cache virtual environment
+        uses: actions/cache@v3
+        with:
+          # We are hashing dev-requirements.txt and test-requirements.txt which
+          # contain all dependencies needed to run the tests.
+          key: venv-${{ runner.os }}-${{ steps.setup_python.outputs.python-version}}-${{ hashFiles('dev-requirements.txt') }}-${{ hashFiles('test-requirements.txt') }}
+          path: .venv
+      - name: Install system packages
+        id: install_system_packages
+        run: |
+          sudo apt-get install -y portaudio19-dev
+      - name: Setup virtual environment
+        run: |
+          python -m venv .venv
+      - name: Install basic Python dependencies
+        run: |
+          source .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r dev-requirements.txt -r test-requirements.txt
+      - name: Run tests with coverage
+        run: |
+          source .venv/bin/activate
+          coverage run
+          coverage xml
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          slug: pipecat-ai/pipecat

.gitignore

@@ -32,6 +32,21 @@ fly.toml
 
 # Example files
 pipecat/examples/twilio-chatbot/templates/streams.xml
+pipecat/examples/bot-ready-signalling/client/react-native/node_modules/
+pipecat/examples/bot-ready-signalling/client/react-native/.expo/
+pipecat/examples/bot-ready-signalling/client/react-native/dist/
+pipecat/examples/bot-ready-signalling/client/react-native/npm-debug.*
+pipecat/examples/bot-ready-signalling/client/react-native/*.jks
+pipecat/examples/bot-ready-signalling/client/react-native/*.p8
+pipecat/examples/bot-ready-signalling/client/react-native/*.p12
+pipecat/examples/bot-ready-signalling/client/react-native/*.key
+pipecat/examples/bot-ready-signalling/client/react-native/*.mobileprovision
+pipecat/examples/bot-ready-signalling/client/react-native/*.orig.*
+pipecat/examples/bot-ready-signalling/client/react-native/web-build/
+
+# macOS
+.DS_Store
+
 
 # Documentation
 docs/api/_build/

CHANGELOG.md

@@ -7,13 +7,216 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+
+- Pipecat version will now be logged on every application startup. This will
+  help us identify what version we are running in case of any issues.
+
+- Added a new `StopFrame` which can be used to stop a pipeline task while
+  keeping the frame processors running. The frame processors could then be used
+  in a different pipeline. The difference between a `StopFrame` and a
+  `StopTaskFrame` is that, as with `EndFrame` and `EndTaskFrame`, the
+  `StopFrame` is pushed from the task and the `StopTaskFrame` is pushed upstream
+  inside the pipeline by any processor.
+
+- Added a new `PipelineTask` parameter `observers` that replaces the previous
+  `PipelineParams.observers`.
+
+- Added a new `PipelineTask` parameter `check_dangling_tasks` to enable or
+  disable checking for frame processors' dangling tasks when the Pipeline
+  finishes running.
+
+- Added new `on_completion_timeout` event for LLM services (all OpenAI-based
+  services, Anthropic and Google). Note that this event will only get triggered
+  if LLM timeouts are setup and if the timeout was reached. It can be useful to
+  retrigger another completion and see if the timeout was just a blip.
+
+- Added new log observers `LLMLogObserver` and `TranscriptionLogObserver` that
+  can be useful for debugging your pipelines.
+
+- Added `room_url` property to `DailyTransport`.
+
+- Added `addons` argument to `DeepgramSTTService`.
+
+- Added `exponential_backoff_time()` to `utils.network` module.
+
 ### Changed
 
-- `RTVIObserver` doesn't handle `LLMSearchResponseFrame` frames anymore. For
-  now, to handle those frames you need to create a `GoogleRTVIObserver` instead.
+- ⚠️ `PipelineTask` now requires keyword arguments (except for the first one for
+  the pipeline).
+
+- The base `TTSService` class now strips leading newlines before sending text
+  to the TTS provider. This change is to solve issues where some TTS providers,
+  like Azure, would not output text due to newlines.
+
+- `GrokLLMSService` now uses `grok-2` as the default model.
+
+- `AnthropicLLMService` now uses `claude-3-7-sonnet-20250219` as the default
+  model.
+
+- `RimeHttpTTSService` needs an `aiohttp.ClientSession` to be passed to the
+  constructor as all the other HTTP-based services.
+
+- `RimeHttpTTSService` doesn't use a default voice anymore.
+
+- `DeepgramSTTService` now uses the new `nova-3` model by default. If you want
+  to use the previous model you can pass `LiveOptions(model="nova-2-general")`.
+  (see https://deepgram.com/learn/introducing-nova-3-speech-to-text-api)
+
+```python
+stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
+```
 
 ### Deprecated
 
+- `PipelineParams.observers` is now deprecated, you the new `PipelineTask`
+  parameter `observers`.
+
+### Removed
+
+- Remove `TransportParams.audio_out_is_live` since it was not being used at all.
+
+### Fixed
+
+- Fixed an `AudioContextWordTTSService` issue that would cause an `EndFrame` to
+  disconnect from the TTS service before audio from all the contexts was
+  received. This affected services like Cartesia and Rime.
+
+- Fixed an issue that was not allowing to pass an `OpenAILLMContext` to create
+  `GoogleLLMService`'s context aggregators.
+
+- Fixed a `ElevenLabsTTSService`, `FishAudioTTSService`, `LMNTTTSService` and
+  `PlayHTTTSService` issue that was resulting in audio requested before an
+  interruption being played after an interruption.
+
+- Fixed `match_endofsentence` support for ellipses.
+
+- Fixed an issue that would cause undesired interruptions via
+  `EmulateUserStartedSpeakingFrame` when only interim transcriptions (i.e. no
+  final transcriptions) where received.
+
+- Fixed an issue where `EndTaskFrame` was not triggering
+  `on_client_disconnected` or closing the WebSocket in FastAPI.
+
+- Fixed an issue in `DeepgramSTTService` where the `sample_rate` passed to the
+  `LiveOptions` was not being used, causing the service to use the default
+  sample rate of pipeline.
+
+- Fixed a context aggregator issue that would not append the LLM text response
+  to the context if a function call happened in the same LLM turn.
+
+- Fixed an issue that was causing HTTP TTS services to push `TTSStoppedFrame`
+  more than once.
+
+- Fixed a `FishAudioTTSService` issue where `TTSStoppedFrame` was not being
+  pushed.
+
+- Fixed an issue that `start_callback` was not invoked for some LLM services.
+
+- Fixed an issue that would cause `DeepgramSTTService` to stop working after an
+  error occurred (e.g. sudden network loss). If the network recovered we would
+  not reconnect.
+
+- Fixed a `STTMuteFilter` issue that would not mute user audio frames causing
+  transcriptions to be generated by the STT service.
+
+### Other
+
+- Added Gemini support to `examples/phone-chatbot`.
+
+## [0.0.57] - 2025-02-14
+
+### Added
+
+- Added new `AudioContextWordTTSService`. This is a TTS base class for TTS
+  services that handling multiple separate audio requests.
+
+- Added new frames `EmulateUserStartedSpeakingFrame` and
+  `EmulateUserStoppedSpeakingFrame` which can be used to emulated VAD behavior
+  without VAD being present or not being triggered.
+
+- Added a new `audio_in_stream_on_start` field to `TransportParams`.
+
+- Added a new method `start_audio_in_streaming` in the `BaseInputTransport`.
+
+  - This method should be used to start receiving the input audio in case the
+    field `audio_in_stream_on_start` is set to `false`.
+
+- Added support for the `RTVIProcessor` to handle buffered audio in `base64`
+  format, converting it into InputAudioRawFrame for transport.
+
+- Added support for the `RTVIProcessor` to trigger `start_audio_in_streaming`
+  only after the `client-ready` message.
+
+- Added new `MUTE_UNTIL_FIRST_BOT_COMPLETE` strategy to `STTMuteStrategy`. This
+  strategy starts muted and remains muted until the first bot speech completes,
+  ensuring the bot's first response cannot be interrupted. This complements the
+  existing `FIRST_SPEECH` strategy which only mutes during the first detected
+  bot speech.
+
+- Added support for Google Cloud Speech-to-Text V2 through `GoogleSTTService`.
+
+- Added `RimeTTSService`, a new `WordTTSService`. Updated the foundational
+  example `07q-interruptible-rime.py` to use `RimeTTSService`.
+
+- Added support for Groq's Whisper API through the new `GroqSTTService` and
+  OpenAI's Whisper API through the new `OpenAISTTService`. Introduced a new
+  base class `BaseWhisperSTTService` to handle common Whisper API
+  functionality.
+
+- Added `PerplexityLLMService` for Perplexity NIM API integration, with an
+  OpenAI-compatible interface. Also, added foundational example
+  `14n-function-calling-perplexity.py`.
+
+- Added `DailyTransport.update_remote_participants()`. This allows you to update
+  remote participant's settings, like their permissions or which of their
+  devices are enabled. Requires that the local participant have participant
+  admin permission.
+
+### Changed
+
+- We don't consider a colon `:` and end of sentence any more.
+
+- Updated `DailyTransport` to respect the `audio_in_stream_on_start` field,
+  ensuring it only starts receiving the audio input if it is enabled.
+
+- Updated `FastAPIWebsocketOutputTransport` to send `TransportMessageFrame` and
+  `TransportMessageUrgentFrame` to the serializer.
+
+- Updated `WebsocketServerOutputTransport` to send `TransportMessageFrame` and
+  `TransportMessageUrgentFrame` to the serializer.
+
+- Enhanced `STTMuteConfig` to validate strategy combinations, preventing
+  `MUTE_UNTIL_FIRST_BOT_COMPLETE` and `FIRST_SPEECH` from being used together
+  as they handle first bot speech differently.
+
+- Updated foundational example `07n-interruptible-google.py` to use all Google
+  services.
+
+- `RimeHttpTTSService` now uses the `mistv2` model by default.
+
+- Improved error handling in `AzureTTSService` to properly detect and log
+  synthesis cancellation errors.
+
+- Enhanced `WhisperSTTService` with full language support and improved model
+  documentation.
+
+- Updated foundation example `14f-function-calling-groq.py` to use
+  `GroqSTTService` for transcription.
+
+- Updated `GroqLLMService` to use `llama-3.3-70b-versatile` as the default
+  model.
+
+- `RTVIObserver` doesn't handle `LLMSearchResponseFrame` frames anymore. For
+  now, to handle those frames you need to create a `GoogleRTVIObserver`
+  instead.
+
+### Deprecated
+
+- `STTMuteFilter` constructor's `stt_service` parameter is now deprecated and
+  will be removed in a future version. The filter now manages mute state
+  internally instead of querying the STT service.
+
 - `RTVI.observer()` is now deprecated, instantiate an `RTVIObserver` directly
   instead.
 
@@ -21,6 +224,52 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   `RTVIBotLLMProcessor`) are now deprecated, instantiate an `RTVIObserver`
   instead.
 
+### Fixed
+
+- Fixed a `FalImageGenService` issue that was causing the event loop to be
+  blocked while loading the downloadded image.
+
+- Fixed a `CartesiaTTSService` service issue that would cause audio overlapping
+  in some cases.
+
+- Fixed a websocket-based service issue (e.g. `CartesiaTTSService`) that was
+  preventing a reconnection after the server disconnected cleanly, which was
+  causing an inifite loop instead.
+
+- Fixed a `BaseOutputTransport` issue that was causing upstream frames to no be
+  pushed upstream.
+
+- Fixed multiple issue where user transcriptions where not being handled
+  properly. It was possible for short utterances to not trigger VAD which would
+  cause user transcriptions to be ignored. It was also possible for one or more
+  transcriptions to be generated after VAD in which case they would also be
+  ignored.
+
+- Fixed an issue that was causing `BotStoppedSpeakingFrame` to be generated too
+  late. This could then cause issues unblocking `STTMuteFilter` later than
+  desired.
+
+- Fixed an issue that was causing `AudioBufferProcessor` to not record
+  synchronized audio.
+
+- Fixed an `RTVI` issue that was causing `bot-tts-text` messages to be sent
+  before being processed by the output transport.
+
+- Fixed an issue[#1192] in 11labs where we are trying to reconnect/disconnect
+  the websocket connection even when the connection is already closed.
+
+- Fixed an issue where `has_regular_messages` condition was always true in
+  `GoogleLLMContext` due to `Part` having `function_call` & `function_response`
+  with `None` values.
+
+### Other
+
+- Added new `instant-voice` example. This example showcases how to enable
+  instant voice communication as soon as a user connects.
+
+- Added new `local-input-select-stt` example. This examples allows you to play
+  with local audio inputs by slecting them through a nice text interface.
+
 ## [0.0.56] - 2025-02-06
 
 ### Changed
@@ -40,7 +289,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   logging setup.
 
 - Fixed a `SentryMetrics` issue that was preventing any metrics to be sent to
-  Sentry and also was preventing from metrics frames to be pushed to the pipeline.
+  Sentry and also was preventing from metrics frames to be pushed to the
+  pipeline.
 
 - Fixed an issue in `BaseOutputTransport` where incoming audio would not be
   resampled to the desired output sample rate.
@@ -199,7 +449,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Added `enable_recording` and `geo` parameters to `DailyRoomProperties`.
 
-- Added `RecordingsBucketConfig` to `DailyRoomProperties` to upload recordings to a custom AWS bucket.
+- Added `RecordingsBucketConfig` to `DailyRoomProperties` to upload recordings
+  to a custom AWS bucket.
 
 ### Changed
 

README.md

@@ -2,7 +2,7 @@
  <img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
 </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) [![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.pipecat.ai) [![Discord](https://img.shields.io/discord/1239284677165056021)](https://discord.gg/pipecat) <a href="https://app.commanddash.io/agent/github_pipecat-ai_pipecat"><img src="https://img.shields.io/badge/AI-Code%20Agent-EB9FDA"></a>
+[![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)
 
 Pipecat is an open source Python framework for building voice and multimodal conversational agents. It handles the complex orchestration of AI services, network transport, audio processing, and multimodal interactions, letting you focus on creating engaging experiences.
 
@@ -55,17 +55,17 @@ pip install "pipecat-ai[option,...]"
 
 ### Available services
 
-| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | Install Command Example                 |
-| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                                                                                                                                                                                                                            | `pip install "pipecat-ai[deepgram]"`    |
-| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [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), [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), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | `pip install "pipecat-ai[openai]"`      |
-| Text-to-Speech      | [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), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                              | `pip install "pipecat-ai[cartesia]"`    |
-| Speech-to-Speech    | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | `pip install "pipecat-ai[openai]"`      |
-| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `pip install "pipecat-ai[daily]"`       |
-| Video               | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | `pip install "pipecat-ai[tavus,simli]"` |
-| Vision & Image      | [Moondream](https://docs.pipecat.ai/server/services/vision/moondream), [fal](https://docs.pipecat.ai/server/services/image-generation/fal)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | `pip install "pipecat-ai[moondream]"`   |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[silero]"`      |
-| Analytics & Metrics | [Canonical AI](https://docs.pipecat.ai/server/services/analytics/canonical), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | `pip install "pipecat-ai[canonical]"`   |
+| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | Install Command Example                 |
+| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [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), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[deepgram]"`    |
+| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [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), [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), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | `pip install "pipecat-ai[openai]"`      |
+| Text-to-Speech      | [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), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                                                                                                                                                                          | `pip install "pipecat-ai[cartesia]"`    |
+| Speech-to-Speech    | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | `pip install "pipecat-ai[google]"`      |
+| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      | `pip install "pipecat-ai[daily]"`       |
+| Video               | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[tavus,simli]"` |
+| Vision & Image      | [Moondream](https://docs.pipecat.ai/server/services/vision/moondream), [fal](https://docs.pipecat.ai/server/services/image-generation/fal)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[moondream]"`   |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `pip install "pipecat-ai[silero]"`      |
+| Analytics & Metrics | [Canonical AI](https://docs.pipecat.ai/server/services/analytics/canonical), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | `pip install "pipecat-ai[canonical]"`   |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 
@@ -149,36 +149,40 @@ Sign up [here](https://dashboard.daily.co/u/signup) and [create a room](https://
 
 ## Hacking on the framework itself
 
-_Note that you may need to set up a virtual environment before following the instructions below. For instance, you might need to run the following from the root of the repo:_
+_Note: You may need to set up a virtual environment before following these instructions. From the root of the repo:_
 
 ```shell
 python3 -m venv venv
 source venv/bin/activate
 ```
 
-From the root of this repo, run the following:
+Install the development dependencies:
 
 ```shell
 pip install -r dev-requirements.txt
 ```
 
-This will install the necessary development dependencies. Also, make sure you install the git pre-commit hooks:
+Install the git pre-commit hooks (these help ensure your code follows project rules):
 
 ```shell
 pre-commit install
 ```
 
-The hooks will just save you time when you submit a PR by making sure your code follows the project rules.
-
-To use the package locally (e.g. to run sample files), run:
+Install the `pipecat-ai` package locally in editable mode:
 
 ```shell
-pip install --editable ".[option,...]"
+pip install -e .
 ```
 
-The `--editable` option makes sure you don't have to run `pip install` again and you can just edit the project files locally.
+The `-e` or `--editable` option allows you to modify the code without reinstalling.
 
-If you want to use this package from another directory, you can run:
+To include optional dependencies, add them to the install command. For example:
+
+```shell
+pip install -e ".[daily,deepgram,cartesia,openai,silero]"     # Updated for the services you're using
+```
+
+If you want to use this package from another directory:
 
 ```shell
 pip install "path_to_this_repo[option,...]"

codecov.yml

@@ -0,0 +1,11 @@
+coverage:
+  range: 50..90 # coverage lower than 50 is red, higher than 90 green, between color code
+
+  status:
+    project:
+      default:
+        target: auto # auto % coverage target
+        threshold: 5%  # allow for 5% reduction of coverage without failing
+
+    # do not run coverage on patch nor changes
+    patch: false

dev-requirements.txt

@@ -1,11 +1,12 @@
 build~=1.2.2
+coverage~=7.6.12
 grpcio-tools~=1.67.1
 pip-tools~=7.4.1
 pre-commit~=4.0.1
-pyright~=1.1.393
+pyright~=1.1.394
 pytest~=8.3.4
-pytest-asyncio~=0.25.2
-ruff~=0.9.5
+pytest-asyncio~=0.25.3
+ruff~=0.9.7
 setuptools~=70.0.0
 setuptools_scm~=8.1.0
 python-dotenv~=1.0.1

dot-env.template

@@ -18,6 +18,9 @@ AZURE_DALLE_API_KEY=...
 AZURE_DALLE_ENDPOINT=https://...
 AZURE_DALLE_MODEL=...
 
+# Cartesia
+CARTESIA_API_KEY=...
+
 # Daily
 DAILY_API_KEY=...
 DAILY_SAMPLE_ROOM_URL=https://...

examples/bot-ready-signalling/client/javascript/package-lock.json

@@ -12,7 +12,7 @@
         "@daily-co/daily-js": "0.74.0"
       },
       "devDependencies": {
-        "vite": "^6.0.2"
+        "vite": "^6.0.9"
       }
     },
     "node_modules/@babel/runtime": {
@@ -1007,15 +1007,14 @@
       }
     },
     "node_modules/vite": {
-      "version": "6.0.7",
-      "resolved": "https://registry.npmjs.org/vite/-/vite-6.0.7.tgz",
-      "integrity": "sha512-RDt8r/7qx9940f8FcOIAH9PTViRrghKaK2K1jY3RaAURrEUbm9Du1mJ72G+jlhtG3WwodnfzY8ORQZbBavZEAQ==",
+      "version": "6.1.0",
+      "resolved": "https://registry.npmjs.org/vite/-/vite-6.1.0.tgz",
+      "integrity": "sha512-RjjMipCKVoR4hVfPY6GQTgveinjNuyLw+qruksLDvA5ktI1150VmcMBKmQaEWJhg/j6Uaf6dNCNA0AfdzUb/hQ==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
         "esbuild": "^0.24.2",
-        "postcss": "^8.4.49",
-        "rollup": "^4.23.0"
+        "postcss": "^8.5.1",
+        "rollup": "^4.30.1"
       },
       "bin": {
         "vite": "bin/vite.js"

examples/bot-ready-signalling/client/javascript/package.json

@@ -12,7 +12,7 @@
   "license": "ISC",
   "description": "",
   "devDependencies": {
-    "vite": "^6.0.2"
+    "vite": "^6.0.9"
   },
   "dependencies": {
     "@daily-co/daily-js": "0.74.0"

examples/bot-ready-signalling/client/react-native/.nvmrc

@@ -0,0 +1 @@
+22.14

examples/bot-ready-signalling/client/react-native/README.md

@@ -0,0 +1,60 @@
+# React Native Implementation
+
+Basic implementation using the [Pipecat React Native SDK](https://docs.pipecat.ai/client/react-native/introduction).
+
+## Usage
+
+### Expo requirements
+
+This project cannot be used with an [Expo Go](https://docs.expo.dev/workflow/expo-go/) app because [it requires custom native code](https://docs.expo.io/workflow/customizing/).
+
+When a project requires custom native code or a config plugin, we need to transition from using [Expo Go](https://docs.expo.dev/workflow/expo-go/) 
+to a [development build](https://docs.expo.dev/development/introduction/).
+
+More details about the custom native code used by this demo can be found in [rn-daily-js-expo-config-plugin](https://github.com/daily-co/rn-daily-js-expo-config-plugin).
+
+### Building remotely
+
+If you do not have experience with Xcode and Android Studio builds or do not have them installed locally on your computer, you will need to follow [this guide from Expo to use EAS Build](https://docs.expo.dev/development/create-development-builds/#create-and-install-eas-build).
+
+### Building locally
+
+You will need to have installed locally on your computer:
+- [Xcode](https://developer.apple.com/xcode/) to build for iOS;
+- [Android Studio](https://developer.android.com/studio) to build for Android;
+
+#### Install the demo dependencies
+
+```bash
+# Use the version of node specified in .nvmrc
+nvm i
+
+# Install dependencies
+npm i
+
+# Before a native app can be compiled, the native source code must be generated.
+npx expo prebuild
+
+# Configure the environment variable to connect to the local server
+cp env.example .env
+# edit .env and add your local ip address, for example: http://192.168.1.16:7860
+```
+
+#### Running on Android
+
+After plugging in an Android device [configured for debugging](https://developer.android.com/studio/debug/dev-options), run the following command:
+
+```
+npm run android
+```
+
+#### Running on iOS
+
+Run the following command:
+
+```
+npm run ios
+```
+
+#### Connect to the server
+Use the http://localhost:5173 in your app.

examples/bot-ready-signalling/client/react-native/app.json

@@ -0,0 +1,75 @@
+{
+  "expo": {
+    "name": "bot-ready-rn",
+    "slug": "bot-ready-rn",
+    "version": "1.0.0",
+    "orientation": "portrait",
+    "icon": "./assets/icon.png",
+    "userInterfaceStyle": "light",
+    "splash": {
+      "image": "./assets/splash.png",
+      "resizeMode": "contain",
+      "backgroundColor": "#ffffff"
+    },
+    "updates": {
+      "fallbackToCacheTimeout": 0
+    },
+    "assetBundlePatterns": [
+      "**/*"
+    ],
+    "ios": {
+      "supportsTablet": true,
+      "bitcode": false,
+      "bundleIdentifier": "co.daily.expo.BotReady",
+      "infoPlist": {
+        "UIBackgroundModes": [
+          "voip"
+        ]
+      },
+      "appleTeamId": "EEBGKV9N3N"
+    },
+    "android": {
+      "adaptiveIcon": {
+        "foregroundImage": "./assets/adaptive-icon.png",
+        "backgroundColor": "#FFFFFF"
+      },
+      "package": "co.daily.expo.BotReady",
+      "permissions": [
+        "android.permission.ACCESS_NETWORK_STATE",
+        "android.permission.BLUETOOTH",
+        "android.permission.CAMERA",
+        "android.permission.INTERNET",
+        "android.permission.MODIFY_AUDIO_SETTINGS",
+        "android.permission.RECORD_AUDIO",
+        "android.permission.SYSTEM_ALERT_WINDOW",
+        "android.permission.WAKE_LOCK",
+        "android.permission.FOREGROUND_SERVICE",
+        "android.permission.FOREGROUND_SERVICE_CAMERA",
+        "android.permission.FOREGROUND_SERVICE_MICROPHONE",
+        "android.permission.FOREGROUND_SERVICE_MEDIA_PROJECTION",
+        "android.permission.POST_NOTIFICATIONS"
+      ]
+    },
+    "web": {
+      "favicon": "./assets/favicon.png"
+    },
+    "plugins": [
+      "@config-plugins/react-native-webrtc",
+      "@daily-co/config-plugin-rn-daily-js",
+      [
+        "expo-build-properties",
+        {
+          "android": {
+            "minSdkVersion": 24,
+            "compileSdkVersion": 35,
+            "targetSdkVersion": 34,
+            "buildToolsVersion": "35.0.0"
+          },
+          "ios": {
+            "deploymentTarget": "15.1"
+          }
+        }
+      ]
+    ]
+  }
+}

examples/bot-ready-signalling/client/react-native/babel.config.js

@@ -0,0 +1,7 @@
+module.exports = function(api) {
+  api.cache(true);
+  return {
+    presets: ['babel-preset-expo'],
+    plugins: [["module:react-native-dotenv"]],
+  };
+};

examples/bot-ready-signalling/client/react-native/env.example

@@ -0,0 +1 @@
+API_BASE_URL=http://YOUR_LOCAL_IP:7860

examples/bot-ready-signalling/client/react-native/index.js

@@ -0,0 +1,7 @@
+import { registerRootComponent } from "expo";
+
+import App from "./src/App";
+
+// registerRootComponent calls AppRegistry.registerComponent('main', () => App);
+// It also ensures that the environment is set up appropriately
+registerRootComponent(App);

examples/bot-ready-signalling/client/react-native/metro.config.js

@@ -0,0 +1,4 @@
+// Learn more https://docs.expo.io/guides/customizing-metro
+const { getDefaultConfig } = require('expo/metro-config');
+
+module.exports = getDefaultConfig(__dirname);

examples/bot-ready-signalling/client/react-native/package.json

@@ -0,0 +1,31 @@
+{
+  "name": "bot-ready-rn",
+  "version": "1.0.0",
+  "scripts": {
+    "start": "expo start --dev-client",
+    "android": "expo run:android --device",
+    "ios": "expo run:ios --device",
+    "web": "expo start --web"
+  },
+  "dependencies": {
+    "@config-plugins/react-native-webrtc": "^10.0.0",
+    "@daily-co/config-plugin-rn-daily-js": "0.0.7",
+    "@daily-co/react-native-daily-js": "^0.70.0",
+    "@daily-co/react-native-webrtc": "^118.0.3-daily.2",
+    "@react-native-async-storage/async-storage": "1.23.1",
+    "expo": "^52.0.0",
+    "expo-build-properties": "~0.13.1",
+    "expo-dev-client": "~5.0.5",
+    "expo-splash-screen": "~0.29.16",
+    "expo-status-bar": "~2.0.0",
+    "react": "18.3.1",
+    "react-native": "0.76.3",
+    "react-native-background-timer": "^2.4.1",
+    "react-native-dotenv": "^3.4.11",
+    "react-native-get-random-values": "^1.11.0"
+  },
+  "devDependencies": {
+    "@babel/core": "^7.12.9"
+  },
+  "private": true
+}

examples/bot-ready-signalling/client/react-native/src/App.js

@@ -0,0 +1,121 @@
+import React, { useState, useEffect } from 'react';
+import {SafeAreaView, View, Text, Button, StyleSheet, ScrollView} from 'react-native';
+import Daily from "@daily-co/react-native-daily-js";
+import { API_BASE_URL } from "@env";
+
+const CallScreen = () => {
+  const [connectionStatus, setConnectionStatus] = useState('Disconnected');
+  const [isConnected, setIsConnected] = useState(false);
+  const [callObject, setCallObject] = useState(null);
+  const [logs, setLogs] = useState([]);
+
+  useEffect(() => {
+    if (callObject) {
+      setupTrackListeners(callObject);
+    }
+  }, [callObject]);
+
+  const log = (message) => {
+    setLogs((prevLogs) => [...prevLogs, `${new Date().toISOString()} - ${message}`]);
+    console.log(message);
+  };
+
+  const setupTrackListeners = (callObject) => {
+    callObject.on("joined-meeting", () => {
+      setConnectionStatus('Connected');
+      setIsConnected(true);
+      log('Client connected');
+    });
+    callObject.on("left-meeting", () => {
+      setConnectionStatus('Disconnected');
+      setIsConnected(false);
+      log('Client disconnected');
+    });
+    callObject.on("participant-left", () => {
+      // When the bot leaves, we are also disconnecting from the call
+      disconnect().catch((err) => {
+        log(`Failed to disconnect ${err}`);
+      })
+    });
+    // Trigger so the bot can start sending audio
+    callObject.on("track-started", (evt) => {
+      if (evt.track.kind === "audio" && evt.participant.local === false) {
+        handleEventToConsole(evt)
+        log("Sending the message that will trigger the bot to play the audio.")
+        callObject.sendAppMessage("playable")
+      }
+    });
+    callObject.on("error", (evt) => log(`Error: ${evt.error}`));
+    // Other events just for awareness
+    callObject.on("track-stopped", handleEventToConsole);
+    callObject.on("participant-joined", handleEventToConsole);
+    callObject.on("participant-updated", handleEventToConsole);
+  };
+
+  const handleEventToConsole = (evt) => {
+    log(`Received event: ${evt.action}`);
+  };
+
+  const connect = async () => {
+    try {
+      const callObject = Daily.createCallObject({ subscribeToTracksAutomatically: true });
+      setCallObject(callObject);
+      const connectionUrl = `${API_BASE_URL}/connect`
+      const res = await fetch(connectionUrl, { method: "POST", headers: { "Content-Type": "application/json" } });
+      const roomInfo = await res.json();
+      await callObject.join({ url: roomInfo.room_url });
+    } catch (error) {
+      log(`Error connecting: ${error.message}`);
+    }
+  };
+
+  const disconnect = async () => {
+    if (callObject) {
+      try {
+        await callObject.leave();
+        await callObject.destroy();
+        setCallObject(null);
+      } catch (error) {
+        log(`Error disconnecting: ${error.message}`);
+      }
+    }
+  };
+
+  return (
+      <SafeAreaView style={styles.safeArea}>
+        <View style={styles.container}>
+          <View style={styles.statusBar}>
+            <Text>Status: <Text style={styles.status}>{connectionStatus}</Text></Text>
+            <View style={styles.controls}>
+              <Button
+                title={isConnected ? "Disconnect" : "Connect"}
+                onPress={isConnected ? disconnect : connect}
+              />
+            </View>
+          </View>
+
+          <View style={styles.debugPanel}>
+            <Text style={styles.debugTitle}>Debug Info</Text>
+            <ScrollView style={styles.debugLog}>
+              {logs.map((logEntry, index) => (
+                  <Text key={index} style={styles.logText}>{logEntry}</Text>
+              ))}
+            </ScrollView>
+          </View>
+        </View>
+      </SafeAreaView>
+  );
+};
+
+const styles = StyleSheet.create({
+  safeArea: { flex: 1, backgroundColor: '#f0f0f0', padding: 20 },
+  container: { flex: 1, margin: 20 },
+  statusBar: { flexDirection: 'row', justifyContent: 'space-between', alignItems: 'center', padding: 10, backgroundColor: '#fff', borderRadius: 8, marginBottom: 20 },
+  status: { fontWeight: 'bold' },
+  controls: { flexDirection: 'row', gap: 10 },
+  debugPanel: { height: '80%', backgroundColor: '#fff', borderRadius: 8, padding: 20},
+  debugTitle: { fontSize: 16, fontWeight: 'bold' },
+  debugLog: { height: '100%', overflow: 'scroll', backgroundColor: '#f8f8f8', padding: 10, borderRadius: 4, fontFamily: 'monospace', fontSize: 12, lineHeight: 1.4 },
+});
+
+export default CallScreen;

examples/bot-ready-signalling/server/signalling_bot.py

@@ -17,7 +17,7 @@ from runner import configure
 from pipecat.frames.frames import AudioRawFrame, EndFrame, OutputAudioRawFrame, TTSSpeakFrame
 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.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 

examples/canonical-metrics/bot.py

@@ -119,7 +119,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/chatbot-audio-recording/bot.py

@@ -124,7 +124,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
         @audiobuffer.event_handler("on_audio_data")
         async def on_audio_data(buffer, audio, sample_rate, num_channels):

examples/deployment/flyio-example/bot.py

@@ -70,7 +70,7 @@ async def main(room_url: str, token: str):
         ]
     )
 
-    task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+    task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):

examples/deployment/modal-example/bot.py

@@ -62,7 +62,7 @@ async def main(room_url: str, token: str):
 
     task = PipelineTask(
         pipeline,
-        PipelineParams(
+        params=PipelineParams(
             allow_interruptions=True,
             enable_metrics=True,
             enable_usage_metrics=True,

examples/foundational/01a-local-audio.py

@@ -16,8 +16,7 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.transports.base_transport import TransportParams
-from pipecat.transports.local.audio import LocalAudioTransport
+from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
 
 load_dotenv(override=True)
 
@@ -26,7 +25,7 @@ logger.add(sys.stderr, level="DEBUG")
 
 
 async def main():
-    transport = LocalAudioTransport(TransportParams(audio_out_enabled=True))
+    transport = LocalAudioTransport(LocalAudioTransportParams(audio_out_enabled=True))
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
@@ -41,7 +40,7 @@ async def main():
         await asyncio.sleep(1)
         await task.queue_frames([TTSSpeakFrame("Hello there, how is it going!"), EndFrame()])
 
-    runner = PipelineRunner()
+    runner = PipelineRunner(handle_sigint=False if sys.platform == "win32" else True)
 
     await asyncio.gather(runner.run(task), say_something())
 

examples/foundational/03a-local-still-frame.py

@@ -18,8 +18,7 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.services.fal import FalImageGenService
-from pipecat.transports.base_transport import TransportParams
-from pipecat.transports.local.tk import TkLocalTransport
+from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
 
 load_dotenv(override=True)
 
@@ -34,7 +33,9 @@ async def main():
 
         transport = TkLocalTransport(
             tk_root,
-            TransportParams(camera_out_enabled=True, camera_out_width=1024, camera_out_height=1024),
+            TkTransportParams(
+                camera_out_enabled=True, camera_out_width=1024, camera_out_height=1024
+            ),
         )
 
         imagegen = FalImageGenService(

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

@@ -44,7 +44,8 @@ async def main():
         runner = PipelineRunner()
 
         task = PipelineTask(
-            Pipeline([imagegen, transport.output()]), PipelineParams(enable_metrics=True)
+            Pipeline([imagegen, transport.output()]),
+            params=PipelineParams(enable_metrics=True),
         )
 
         @transport.event_handler("on_first_participant_joined")

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

@@ -30,8 +30,7 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaHttpTTSService
 from pipecat.services.fal import FalImageGenService
 from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.base_transport import TransportParams
-from pipecat.transports.local.tk import TkLocalTransport, TkOutputTransport
+from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
 
 load_dotenv(override=True)
 
@@ -152,7 +151,7 @@ async def main():
 
         transport = TkLocalTransport(
             tk_root,
-            TransportParams(
+            TkTransportParams(
                 audio_out_enabled=True,
                 camera_out_enabled=True,
                 camera_out_width=1024,

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

@@ -105,7 +105,10 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(enable_metrics=True, enable_usage_metrics=True),
+            params=PipelineParams(
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
         )
 
         @transport.event_handler("on_first_participant_joined")

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

@@ -27,7 +27,7 @@ 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, FrameProcessor
-from pipecat.services.cartesia import CartesiaHttpTTSService
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
@@ -91,7 +91,7 @@ async def main():
             ),
         )
 
-        tts = CartesiaHttpTTSService(
+        tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
         )
@@ -127,7 +127,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07-interruptible-vad.py

@@ -76,7 +76,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07-interruptible.py

@@ -74,7 +74,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -79,7 +79,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -103,7 +103,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -81,7 +81,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -74,7 +74,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -74,7 +74,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -75,7 +75,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -77,7 +77,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -83,7 +83,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -81,7 +81,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -81,7 +81,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -75,7 +75,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -80,7 +80,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -71,7 +71,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -88,7 +88,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -81,7 +81,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -18,9 +18,7 @@ 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.services.deepgram import DeepgramSTTService
-from pipecat.services.google import GoogleTTSService
-from pipecat.services.openai import OpenAILLMService
+from pipecat.services.google import GoogleLLMService, GoogleSTTService, GoogleTTSService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
@@ -46,14 +44,16 @@ async def main():
             ),
         )
 
-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+        stt = GoogleSTTService(
+            params=GoogleSTTService.InputParams(languages=Language.EN_US),
+        )
 
         tts = GoogleTTSService(
             voice_id="en-US-Journey-F",
             params=GoogleTTSService.InputParams(language=Language.EN_US),
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
 
         messages = [
             {
@@ -79,7 +79,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -80,7 +80,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -76,7 +76,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -19,7 +19,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.openai import OpenAILLMService
-from pipecat.services.rime import RimeHttpTTSService
+from pipecat.services.rime import RimeTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -44,10 +44,9 @@ async def main():
             ),
         )
 
-        tts = RimeHttpTTSService(
+        tts = RimeTTSService(
             api_key=os.getenv("RIME_API_KEY", ""),
             voice_id="rex",
-            params=RimeHttpTTSService.InputParams(reduce_latency=True),
         )
 
         llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
@@ -75,7 +74,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07r-interruptible-riva-nim.py

@@ -74,7 +74,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

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

@@ -251,7 +251,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -74,7 +74,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/09-mirror.py

@@ -78,7 +78,11 @@ async def main():
         runner = PipelineRunner()
 
         task = PipelineTask(
-            pipeline, PipelineParams(audio_in_sample_rate=24000, audio_out_sample_rate=24000)
+            pipeline,
+            params=PipelineParams(
+                audio_in_sample_rate=24000,
+                audio_out_sample_rate=24000,
+            ),
         )
 
         await runner.run(task)

examples/foundational/09a-local-mirror.py

@@ -24,8 +24,7 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.transports.base_transport import TransportParams
-from pipecat.transports.local.tk import TkLocalTransport
+from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -67,7 +66,7 @@ async def main():
 
         tk_transport = TkLocalTransport(
             tk_root,
-            TransportParams(
+            TkTransportParams(
                 audio_out_enabled=True,
                 camera_out_enabled=True,
                 camera_out_is_live=True,
@@ -83,7 +82,11 @@ async def main():
         pipeline = Pipeline([daily_transport.input(), MirrorProcessor(), tk_transport.output()])
 
         task = PipelineTask(
-            pipeline, PipelineParams(audio_in_sample_rate=24000, audio_out_sample_rate=24000)
+            pipeline,
+            params=PipelineParams(
+                audio_in_sample_rate=24000,
+                audio_out_sample_rate=24000,
+            ),
         )
 
         async def run_tk():

examples/foundational/10-wake-phrase.py

@@ -76,7 +76,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/13a-whisper-local.py

@@ -16,8 +16,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.whisper import WhisperSTTService
-from pipecat.transports.base_transport import TransportParams
-from pipecat.transports.local.audio import LocalAudioTransport
+from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
 
 load_dotenv(override=True)
 
@@ -34,7 +33,7 @@ class TranscriptionLogger(FrameProcessor):
 
 
 async def main():
-    transport = LocalAudioTransport(TransportParams(audio_in_enabled=True))
+    transport = LocalAudioTransport(LocalAudioTransportParams(audio_in_enabled=True))
 
     stt = WhisperSTTService()
 
@@ -44,7 +43,7 @@ async def main():
 
     task = PipelineTask(pipeline)
 
-    runner = PipelineRunner()
+    runner = PipelineRunner(handle_sigint=False if sys.platform == "win32" else True)
 
     await runner.run(task)
 

examples/foundational/14-function-calling.py

@@ -112,7 +112,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14a-function-calling-anthropic.py

@@ -99,7 +99,13 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

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

@@ -153,7 +153,13 @@ If you need to use a tool, simply use the tool. Do not tell the user the tool yo
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/14e-function-calling-gemini.py

@@ -14,6 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -30,6 +31,12 @@ logger.add(sys.stderr, level="DEBUG")
 video_participant_id = None
 
 
+async def start_fetch_weather(function_name, llm, context):
+    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
+    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
 async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
     location = arguments["location"]
     await result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
@@ -63,7 +70,7 @@ async def main():
         )
 
         llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
-        llm.register_function("get_weather", get_weather)
+        llm.register_function("get_weather", get_weather, start_fetch_weather)
         llm.register_function("get_image", get_image)
 
         tools = [
@@ -145,7 +152,7 @@ indicate you should use the get_image tool are:
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14f-function-calling-groq.py

@@ -20,7 +20,7 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.services.groq import GroqLLMService
+from pipecat.services.groq import GroqLLMService, GroqSTTService
 from pipecat.services.openai import OpenAILLMContext
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
@@ -50,20 +50,20 @@ async def main():
             "Respond bot",
             DailyParams(
                 audio_out_enabled=True,
-                transcription_enabled=True,
                 vad_enabled=True,
                 vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
             ),
         )
 
+        stt = GroqSTTService(api_key=os.getenv("GROQ_API_KEY"), model="distil-whisper-large-v3-en")
+
         tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
         )
 
-        llm = GroqLLMService(
-            api_key=os.getenv("GROQ_API_KEY"), model="llama3-groq-70b-8192-tool-use-preview"
-        )
+        llm = GroqLLMService(api_key=os.getenv("GROQ_API_KEY"), model="llama-3.3-70b-versatile")
         # Register a function_name of None to get all functions
         # sent to the same callback with an additional function_name parameter.
         llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)
@@ -105,6 +105,7 @@ async def main():
         pipeline = Pipeline(
             [
                 transport.input(),
+                stt,
                 context_aggregator.user(),
                 llm,
                 tts,
@@ -115,7 +116,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -113,7 +113,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -117,7 +117,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -116,7 +116,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -116,7 +116,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14k-function-calling-cerebras.py

@@ -123,7 +123,7 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14l-function-calling-deepseek.py

@@ -123,7 +123,7 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -117,7 +117,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -0,0 +1,106 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""This example demonstrates using the Perplexity API as a drop-in replacement for OpenAI.
+
+Note that while this file is in the function-calling examples, Perplexity's API does not
+currently support function calling. The example shows basic chat completion functionality
+using Perplexity's API while maintaining compatibility with the OpenAI interface.
+"""
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from openai.types.chat import ChatCompletionToolParam
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMContext, OpenAILLMService
+from pipecat.services.perplexity import PerplexityLLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+            ),
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = PerplexityLLMService(api_key=os.getenv("PERPLEXITY_API_KEY"), model="sonar")
+
+        messages = [
+            {
+                "role": "user",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/15-switch-voices.py

@@ -133,7 +133,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/15a-switch-languages.py

@@ -126,7 +126,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/16-gpu-container-local-bot.py

@@ -85,7 +85,13 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+            ),
+        )
 
         # When a participant joins, start transcription for that participant so the
         # bot can "hear" and respond to them.

examples/foundational/17-detect-user-idle.py

@@ -108,7 +108,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 report_only_initial_ttfb=True,

examples/foundational/18-gstreamer-filesrc.py

@@ -38,7 +38,6 @@ async def main():
             "GStreamer",
             DailyParams(
                 audio_out_enabled=True,
-                audio_out_is_live=True,
                 camera_out_enabled=True,
                 camera_out_width=1280,
                 camera_out_height=720,

examples/foundational/19-openai-realtime-beta.py

@@ -16,10 +16,13 @@ from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import TranscriptionMessage, TranscriptionUpdateFrame
 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.transcript_processor import TranscriptProcessor
+from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.openai_realtime_beta import (
     InputAudioTranscription,
     OpenAIRealtimeBetaLLMService,
@@ -140,21 +143,29 @@ Remember, your responses should be short. Just one or two sentences, usually."""
             tools,
         )
 
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        # Create transcript processor and handler
+        transcript = TranscriptProcessor()
+
         context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
+                stt,
+                transcript.user(),  # User transcripts
                 context_aggregator.user(),
                 llm,  # LLM
                 context_aggregator.assistant(),
+                transcript.assistant(),  # Assistant transcripts
                 transport.output(),  # Transport bot output
             ]
         )
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,
@@ -162,9 +173,16 @@ Remember, your responses should be short. Just one or two sentences, usually."""
             ),
         )
 
+        # Register event handler for transcript updates
+        @transcript.event_handler("on_transcript_update")
+        async def on_transcript_update(processor, frame):
+            logger.debug(f"Received transcript update with {len(frame.messages)} new messages")
+            for msg in frame.messages:
+                logger.debug(msg)
+
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
+            # await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 

examples/foundational/20a-persistent-context-openai.py

@@ -212,7 +212,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -237,7 +237,7 @@ Remember, your responses should be short. Just one or two sentences, usually."""
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/20c-persistent-context-anthropic.py

@@ -209,7 +209,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/20d-persistent-context-gemini.py

@@ -263,7 +263,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/21-tavus-layer.py

@@ -87,7 +87,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 # We just use 16000 because that's what Tavus is expecting and
                 # we avoid resampling.
                 audio_in_sample_rate=16000,

examples/foundational/22-natural-conversation.py

@@ -145,7 +145,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/22b-natural-conversation-proposal.py

@@ -138,6 +138,7 @@ class OutputGate(FrameProcessor):
         self._gate_open = start_open
         self._frames_buffer = []
         self._notifier = notifier
+        self._gate_task = None
 
     def close_gate(self):
         self._gate_open = False
@@ -178,10 +179,13 @@ class OutputGate(FrameProcessor):
 
     async def _start(self):
         self._frames_buffer = []
-        self._gate_task = self.create_task(self._gate_task_handler())
+        if not self._gate_task:
+            self._gate_task = self.create_task(self._gate_task_handler())
 
     async def _stop(self):
-        await self.cancel_task(self._gate_task)
+        if self._gate_task:
+            await self.cancel_task(self._gate_task)
+            self._gate_task = None
 
     async def _gate_task_handler(self):
         while True:
@@ -351,7 +355,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/22c-natural-conversation-mixed-llms.py

@@ -342,6 +342,7 @@ class OutputGate(FrameProcessor):
         self._gate_open = start_open
         self._frames_buffer = []
         self._notifier = notifier
+        self._gate_task = None
 
     def close_gate(self):
         self._gate_open = False
@@ -382,10 +383,13 @@ class OutputGate(FrameProcessor):
 
     async def _start(self):
         self._frames_buffer = []
-        self._gate_task = self.create_task(self._gate_task_handler())
+        if not self._gate_task:
+            self._gate_task = self.create_task(self._gate_task_handler())
 
     async def _stop(self):
-        await self.cancel_task(self._gate_task)
+        if self._gate_task:
+            await self.cancel_task(self._gate_task)
+            self._gate_task = None
 
     async def _gate_task_handler(self):
         while True:
@@ -560,7 +564,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/22d-natural-conversation-gemini-audio.py

@@ -25,10 +25,8 @@ from pipecat.frames.frames import (
     InputAudioRawFrame,
     LLMFullResponseEndFrame,
     LLMFullResponseStartFrame,
-    LLMMessagesFrame,
     StartFrame,
     StartInterruptionFrame,
-    StopInterruptionFrame,
     SystemFrame,
     TextFrame,
     TranscriptionFrame,
@@ -497,7 +495,7 @@ class UserAggregatorBuffer(LLMResponseAggregator):
         if isinstance(frame, UserStartedSpeakingFrame):
             self._transcription = ""
 
-    async def _push_aggregation(self):
+    async def push_aggregation(self):
         if self._aggregation:
             self._transcription = self._aggregation
             self._aggregation = ""
@@ -555,6 +553,7 @@ class OutputGate(FrameProcessor):
         self._notifier = notifier
         self._context = context
         self._transcription_buffer = user_transcription_buffer
+        self._gate_task = None
 
     def close_gate(self):
         self._gate_open = False
@@ -602,10 +601,13 @@ class OutputGate(FrameProcessor):
 
     async def _start(self):
         self._frames_buffer = []
-        self._gate_task = self.create_task(self._gate_task_handler())
+        if not self._gate_task:
+            self._gate_task = self.create_task(self._gate_task_handler())
 
     async def _stop(self):
-        await self.cancel_task(self._gate_task)
+        if self._gate_task:
+            await self.cancel_task(self._gate_task)
+            self._gate_task = None
 
     async def _gate_task_handler(self):
         while True:
@@ -740,7 +742,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/23-bot-background-sound.py

@@ -87,7 +87,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/24-stt-mute-filter.py

@@ -61,9 +61,11 @@ async def main():
         stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
         # Configure the mute processor with both strategies
         stt_mute_processor = STTMuteFilter(
-            stt_service=stt,
             config=STTMuteConfig(
-                strategies={STTMuteStrategy.FIRST_SPEECH, STTMuteStrategy.FUNCTION_CALL}
+                strategies={
+                    STTMuteStrategy.MUTE_UNTIL_FIRST_BOT_COMPLETE,
+                    STTMuteStrategy.FUNCTION_CALL,
+                }
             ),
         )
 
@@ -120,7 +122,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/25-google-audio-in.py

@@ -143,7 +143,14 @@ class InputTranscriptionContextFilter(FrameProcessor):
             return
 
         try:
-            message = frame.context.messages[-1]
+            # Make sure we're working with a GoogleLLMContext
+            context = GoogleLLMContext.upgrade_to_google(frame.context)
+            message = context.messages[-1]
+
+            if not isinstance(message, glm.Content):
+                logger.error(f"Expected glm.Content, got {type(message)}")
+                return
+
             last_part = message.parts[-1]
             if not (
                 message.role == "user"
@@ -347,7 +354,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/26-gemini-multimodal-live.py

@@ -63,7 +63,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -89,7 +89,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -120,7 +120,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -79,7 +79,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -106,7 +106,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024-2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -34,7 +34,7 @@ search_tool = {"google_search": {}}
 tools = [search_tool]
 
 system_instruction = """
-You are an expert at providing the most recent news from any place. Your responses will be converted to audio, so avoid using special characters or overly complex formatting. 
+You are an expert at providing the most recent news from any place. Your responses will be converted to audio, so avoid using special characters or overly complex formatting.
 
 Always use the google search API to retrieve the latest news. You must also use it to check which day is today.
 
@@ -93,7 +93,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/27-simli-layer.py

@@ -83,7 +83,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
             ),