services(playht): ignore message from a different request id

pipeline(task): cleanup Sink processor

.github/workflows/android.yaml

@@ -0,0 +1,48 @@
+name: android
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "examples/simple-chatbot/client/android/**"
+  pull_request:
+    branches:
+      - "**"
+    paths:
+      - "examples/simple-chatbot/client/android/**"
+  workflow_dispatch:
+    inputs:
+      sdk_git_ref:
+        type: string
+        description: "Which git ref of the app to build"
+
+concurrency:
+  group: build-android-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  sdk:
+    name: "Simple chatbot demo"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.inputs.sdk_git_ref || github.ref }}
+
+      - name: "Install Java"
+        uses: actions/setup-java@v4
+        with:
+          distribution: 'temurin'
+          java-version: '17'
+
+      - name: Build demo app
+        working-directory: examples/simple-chatbot/client/android
+        run: ./gradlew :simple-chatbot-client:assembleDebug
+
+      - name: Upload demo APK
+        uses: actions/upload-artifact@v4
+        with:
+          name: Simple Chatbot Android Client
+          path: examples/simple-chatbot/client/android/simple-chatbot-client/build/outputs/apk/debug/simple-chatbot-client-debug.apk

.github/workflows/format.yaml

@@ -35,7 +35,12 @@ jobs:
           python -m pip install --upgrade pip
           pip install -r dev-requirements.txt
       - name: Ruff formatter
-        id: ruff
+        id: ruff-format
         run: |
           source .venv/bin/activate
           ruff format --diff
+      - name: Ruff import linter
+        id: ruff-check
+        run: |
+          source .venv/bin/activate
+          ruff check --select I

.gitignore

@@ -28,4 +28,11 @@ share/python-wheels/
 MANIFEST
 .DS_Store
 .env
-fly.toml
+fly.toml
+
+# Example files
+pipecat/examples/twilio-chatbot/templates/streams.xml
+
+# Documentation
+docs/api/_build/
+docs/api/api

.readthedocs.yaml

@@ -0,0 +1,36 @@
+version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: '3.12'
+  apt_packages:
+    - portaudio19-dev
+    - python3-dev
+    - libasound2-dev
+  jobs:
+    pre_build:
+      - python -m pip install --upgrade pip
+      - pip install wheel setuptools
+    post_build:
+      - echo "Build completed"
+
+sphinx:
+  configuration: docs/api/conf.py
+  fail_on_warning: false
+
+python:
+  install:
+    - requirements: docs/api/requirements.txt
+    - method: pip
+      path: .
+
+search:
+  ranking:
+    api/*: 5
+    getting-started/*: 4
+    guides/*: 3
+
+submodules:
+  include: all
+  recursive: true

CHANGELOG.md

@@ -9,6 +9,367 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added `DeepSeekLLMService` for DeepSeek integration with an OpenAI-compatible
+  interface. Added foundational example `14l-function-calling-deepseek.py`.
+
+- Added `FunctionCallResultProperties` dataclass to provide a structured way to
+  control function call behavior, including:
+
+  - `run_llm`: Controls whether to trigger LLM completion
+  - `on_context_updated`: Optional callback triggered after context update
+
+- Added a new foundational example `07e-interruptible-playht-http.py` for easy
+  testing of `PlayHTHttpTTSService`.
+
+- Added support for Google TTS Journey voices in `GoogleTTSService`.
+
+- Added `29-livekit-audio-chat.py`, as a new foundational examples for
+  `LiveKitTransportLayer`.
+
+- Added `enable_prejoin_ui`, `max_participants` and `start_video_off` params
+  to `DailyRoomProperties`.
+
+- Added `session_timeout` to `FastAPIWebsocketTransport` and
+  `WebsocketServerTransport` for configuring session timeouts (in
+  seconds). Triggers `on_session_timeout` for custom timeout handling.
+  See [examples/websocket-server/bot.py](https://github.com/pipecat-ai/pipecat/blob/main/examples/websocket-server/bot.py).
+
+- Added the new modalities option and helper function to set Gemini output
+  modalities.
+
+- Added `examples/foundational/26d-gemini-multimodal-live-text.py` which is
+  using Gemini as TEXT modality and using another TTS provider for TTS process.
+
+### Changed
+
+- Modified `OpenAIAssistantContextAggregator` to support controlled completions
+  and to emit context update callbacks via `FunctionCallResultProperties`.
+
+- Added `aws_session_token` to the `PollyTTSService`.
+
+- Changed the default model for `PlayHTHttpTTSService` to `Play3.0-mini-http`.
+
+- `api_key`, `aws_access_key_id` and `region` are no longer required parameters
+  for the PollyTTSService (AWSTTSService)
+
+- Added `session_timeout` example in `examples/websocket-server/bot.py` to
+  handle session timeout event.
+
+- Changed `InputParams` in
+  `src/pipecat/services/gemini_multimodal_live/gemini.py` to support different
+  modalities.
+
+### Fixed
+
+- Fixed a `PipelineTask` issue that would cause a dangling task after stopping
+  the pipeline with an `EndFrame`.
+
+- Fixed an import issue for `PlayHTHttpTTSService`.
+
+- Fixed an issue where languages couldn't be used with the `PlayHTHttpTTSService`.
+
+- Fixed an issue where `OpenAIRealtimeBetaLLMService` audio chunks were hitting
+  an error when truncating audio content.
+
+- Fixed an issue where setting the voice and model for `RimeHttpTTSService`
+  wasn't working.
+
+## [0.0.52] - 2024-12-24
+
+### Added
+
+- Constructor arguments for GoogleLLMService to directly set tools and tool_config.
+
+- Smart turn detection example (`22d-natural-conversation-gemini-audio.py`) that
+  leverages Gemini 2.0 capabilities ().
+  (see https://x.com/kwindla/status/1870974144831275410)
+
+- Added `DailyTransport.send_dtmf()` to send dial-out DTMF tones.
+
+- Added `DailyTransport.sip_call_transfer()` to forward SIP and PSTN calls to
+  another address or number. For example, transfer a SIP call to a different
+  SIP address or transfer a PSTN phone number to a different PSTN phone number.
+
+- Added `DailyTransport.sip_refer()` to transfer incoming SIP/PSTN calls from
+  outside Daily to another SIP/PSTN address.
+
+- Added an `auto_mode` input parameter to `ElevenLabsTTSService`. `auto_mode`
+  is set to `True` by default. Enabling this setting disables the chunk
+  schedule and all buffers, which reduces latency.
+
+- Added `KoalaFilter` which implement on device noise reduction using Koala
+  Noise Suppression.
+  (see https://picovoice.ai/platform/koala/)
+
+- Added `CerebrasLLMService` for Cerebras integration with an OpenAI-compatible
+  interface. Added foundational example `14k-function-calling-cerebras.py`.
+
+- Pipecat now supports Python 3.13. We had a dependency on the `audioop` package
+  which was deprecated and now removed on Python 3.13. We are now using
+  `audioop-lts` (https://github.com/AbstractUmbra/audioop) to provide the same
+  functionality.
+
+- Added timestamped conversation transcript support:
+
+  - New `TranscriptProcessor` factory provides access to user and assistant
+    transcript processors.
+  - `UserTranscriptProcessor` processes user speech with timestamps from
+    transcription.
+  - `AssistantTranscriptProcessor` processes assistant responses with LLM
+    context timestamps.
+  - Messages emitted with ISO 8601 timestamps indicating when they were spoken.
+  - Supports all LLM formats (OpenAI, Anthropic, Google) via standard message
+    format.
+  - New examples: `28a-transcription-processor-openai.py`,
+    `28b-transcription-processor-anthropic.py`, and
+    `28c-transcription-processor-gemini.py`.
+
+- Add support for more languages to ElevenLabs (Arabic, Croatian, Filipino,
+  Tamil) and PlayHT (Afrikans, Albanian, Amharic, Arabic, Bengali, Croatian,
+  Galician, Hebrew, Mandarin, Serbian, Tagalog, Urdu, Xhosa).
+
+### Changed
+
+- `PlayHTTTSService` uses the new v4 websocket API, which also fixes an issue
+  where text inputted to the TTS didn't return audio.
+
+- The default model for `ElevenLabsTTSService` is now `eleven_flash_v2_5`.
+
+- `OpenAIRealtimeBetaLLMService` now takes a `model` parameter in the
+  constructor.
+
+- Updated the default model for the `OpenAIRealtimeBetaLLMService`.
+
+- Room expiration (`exp`) in `DailyRoomProperties` is now optional (`None`) by
+  default instead of automatically setting a 5-minute expiration time. You must
+  explicitly set expiration time if desired.
+
+### Deprecated
+
+- `AWSTTSService` is now deprecated, use `PollyTTSService` instead.
+
+### Fixed
+
+- Fixed token counting in `GoogleLLMService`. Tokens were summed incorrectly
+  (double-counted in many cases).
+
+- Fixed an issue that could cause the bot to stop talking if there was a user
+  interruption before getting any audio from the TTS service.
+
+- Fixed an issue that would cause `ParallelPipeline` to handle `EndFrame`
+  incorrectly causing the main pipeline to not terminate or terminate too early.
+
+- Fixed an audio stuttering issue in `FastPitchTTSService`.
+
+- Fixed a `BaseOutputTransport` issue that was causing non-audio frames being
+  processed before the previous audio frames were played. This will allow, for
+  example, sending a frame `A` after a `TTSSpeakFrame` and the frame `A` will
+  only be pushed downstream after the audio generated from `TTSSpeakFrame` has
+  been spoken.
+
+- Fixed a `DeepgramSTTService` issue that was causing language to be passed as
+  an object instead of a string resulting in the connection to fail.
+
+## [0.0.51] - 2024-12-16
+
+### Fixed
+
+- Fixed an issue in websocket-based TTS services that was causing infinite
+  reconnections (Cartesia, ElevenLabs, PlayHT and LMNT).
+
+## [0.0.50] - 2024-12-11
+
+### Added
+
+- Added `GeminiMultimodalLiveLLMService`. This is an integration for Google's
+  Gemini Multimodal Live API, supporting:
+
+  - Real-time audio and video input processing
+  - Streaming text responses with TTS
+  - Audio transcription for both user and bot speech
+  - Function calling
+  - System instructions and context management
+  - Dynamic parameter updates (temperature, top_p, etc.)
+
+- Added `AudioTranscriber` utility class for handling audio transcription with
+  Gemini models.
+
+- Added new context classes for Gemini:
+
+  - `GeminiMultimodalLiveContext`
+  - `GeminiMultimodalLiveUserContextAggregator`
+  - `GeminiMultimodalLiveAssistantContextAggregator`
+  - `GeminiMultimodalLiveContextAggregatorPair`
+
+- Added new foundational examples for `GeminiMultimodalLiveLLMService`:
+
+  - `26-gemini-multimodal-live.py`
+  - `26a-gemini-multimodal-live-transcription.py`
+  - `26b-gemini-multimodal-live-video.py`
+  - `26c-gemini-multimodal-live-video.py`
+
+- Added `SimliVideoService`. This is an integration for Simli AI avatars.
+  (see https://www.simli.com)
+
+- Added NVIDIA Riva's `FastPitchTTSService` and `ParakeetSTTService`.
+  (see https://www.nvidia.com/en-us/ai-data-science/products/riva/)
+
+- Added `IdentityFilter`. This is the simplest frame filter that lets through
+  all incoming frames.
+
+- New `STTMuteStrategy` called `FUNCTION_CALL` which mutes the STT service
+  during LLM function calls.
+
+- `DeepgramSTTService` now exposes two event handlers `on_speech_started` and
+  `on_utterance_end` that could be used to implement interruptions. See new
+  example `examples/foundational/07c-interruptible-deepgram-vad.py`.
+
+- Added `GroqLLMService`, `GrokLLMService`, and `NimLLMService` for Groq, Grok,
+  and NVIDIA NIM API integration, with an OpenAI-compatible interface.
+
+- New examples demonstrating function calling with Groq, Grok, Azure OpenAI,
+  Fireworks, and NVIDIA NIM: `14f-function-calling-groq.py`,
+  `14g-function-calling-grok.py`, `14h-function-calling-azure.py`,
+  `14i-function-calling-fireworks.py`, and `14j-function-calling-nvidia.py`.
+
+- In order to obtain the audio stored by the `AudioBufferProcessor` you can now
+  also register an `on_audio_data` event handler. The `on_audio_data` handler
+  will be called every time `buffer_size` (a new constructor argument) is
+  reached. If `buffer_size` is 0 (default) you need to manually get the audio as
+  before using `AudioBufferProcessor.merge_audio_buffers()`.
+
+```
+@audiobuffer.event_handler("on_audio_data")
+async def on_audio_data(processor, audio, sample_rate, num_channels):
+    await save_audio(audio, sample_rate, num_channels)
+```
+
+- Added a new RTVI message called `disconnect-bot`, which when handled pushes
+  an `EndFrame` to trigger the pipeline to stop.
+
+### Changed
+
+- `STTMuteFilter` now supports multiple simultaneous muting strategies.
+
+- `XTTSService` language now defaults to `Language.EN`.
+
+- `SoundfileMixer` doesn't resample input files anymore to avoid startup
+  delays. The sample rate of the provided sound files now need to match the
+  sample rate of the output transport.
+
+- Input frames (audio, image and transport messages) are now system frames. This
+  means they are processed immediately by all processors instead of being queued
+  internally.
+
+- Expanded the transcriptions.language module to support a superset of
+  languages.
+
+- Updated STT and TTS services with language options that match the supported
+  languages for each service.
+
+- Updated the `AzureLLMService` to use the `OpenAILLMService`. Updated the
+  `api_version` to `2024-09-01-preview`.
+
+- Updated the `FireworksLLMService` to use the `OpenAILLMService`. Updated the
+  default model to `accounts/fireworks/models/firefunction-v2`.
+
+- Updated the `simple-chatbot` example to include a Javascript and React client
+  example, using RTVI JS and React.
+
+### Removed
+
+- Removed `AppFrame`. This was used as a special user custom frame, but there's
+  actually no use case for that.
+
+### Fixed
+
+- Fixed a `ParallelPipeline` issue that would cause system frames to be queued.
+
+- Fixed `FastAPIWebsocketTransport` so it can work with binary data (e.g. using
+  the protobuf serializer).
+
+- Fixed an issue in `CartesiaTTSService` that could cause previous audio to be
+  received after an interruption.
+
+- Fixed Cartesia, ElevenLabs, LMNT and PlayHT TTS websocket
+  reconnection. Before, if an error occurred no reconnection was happening.
+
+- Fixed a `BaseOutputTransport` issue that was causing audio to be discarded
+  after an `EndFrame` was received.
+
+- Fixed an issue in `WebsocketServerTransport` and `FastAPIWebsocketTransport`
+  that would cause a busy loop when using audio mixer.
+
+- Fixed a `DailyTransport` and `LiveKitTransport` issue where connections were
+  being closed in the input transport prematurely. This was causing frames
+  queued inside the pipeline being discarded.
+
+- Fixed an issue in `DailyTransport` that would cause some internal callbacks to
+  not be executed.
+
+- Fixed an issue where other frames were being processed while a `CancelFrame`
+  was being pushed down the pipeline.
+
+- `AudioBufferProcessor` now handles interruptions properly.
+
+- Fixed a `WebsocketServerTransport` issue that would prevent interruptions with
+  `TwilioSerializer` from working.
+
+- `DailyTransport.capture_participant_video` now allows capturing user's screen
+  share by simply passing `video_source="screenVideo"`.
+
+- Fixed Google Gemini message handling to properly convert appended messages to
+  Gemini's required format.
+
+- Fixed an issue with `FireworksLLMService` where chat completions were failing
+  by removing the `stream_options` from the chat completion options.
+
+## [0.0.49] - 2024-11-17
+
+### Added
+
+- Added RTVI `on_bot_started` event which is useful in a single turn
+  interaction.
+
+- Added `DailyTransport` events `dialin-connected`, `dialin-stopped`,
+  `dialin-error` and `dialin-warning`. Needs daily-python >= 0.13.0.
+
+- Added `RimeHttpTTSService` and the `07q-interruptible-rime.py` foundational
+  example.
+
+- Added `STTMuteFilter`, a general-purpose processor that combines STT
+  muting and interruption control. When active, it prevents both transcription
+  and interruptions during bot speech. The processor supports multiple
+  strategies: `FIRST_SPEECH` (mute only during bot's first
+  speech), `ALWAYS` (mute during all bot speech), or `CUSTOM` (using provided
+  callback).
+
+- Added `STTMuteFrame`, a control frame that enables/disables speech
+  transcription in STT services.
+
+## [0.0.48] - 2024-11-10 "Antonio release"
+
+### Added
+
+- There's now an input queue in each frame processor. When you call
+  `FrameProcessor.push_frame()` this will internally call
+  `FrameProcessor.queue_frame()` on the next processor (upstream or downstream)
+  and the frame will be internally queued (except system frames). Then, the
+  queued frames will get processed. With this input queue it is also possible
+  for FrameProcessors to block processing more frames by calling
+  `FrameProcessor.pause_processing_frames()`. The way to resume processing
+  frames is by calling `FrameProcessor.resume_processing_frames()`.
+
+- Added audio filter `NoisereduceFilter`.
+
+- Introduce input transport audio filters (`BaseAudioFilter`). Audio filters can
+  be used to remove background noises before audio is sent to VAD.
+
+- Introduce output transport audio mixers (`BaseAudioMixer`). Output transport
+  audio mixers can be used, for example, to add background sounds or any other
+  audio mixing functionality before the output audio is actually written to the
+  transport.
+
 - Added `GatedOpenAILLMContextAggregator`. This aggregator keeps the last
   received OpenAI LLM context frame and it doesn't let it through until the
   notifier is notified.
@@ -31,6 +392,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   grained control of what media subscriptions you want for each participant in a
   room.
 
+- Added audio filter `KrispFilter`.
+
 ### Changed
 
 - The following `DailyTransport` functions are now `async` which means they need
@@ -42,8 +405,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   output to 24000 and also the default output transport sample rate. This
   improves audio quality at the cost of some extra bandwidth.
 
+- `AzureTTSService` now uses Azure websockets instead of HTTP requests.
+
+- The previous `AzureTTSService` HTTP implementation is now
+  `AzureHttpTTSService`.
+
 ### Fixed
 
+- Websocket transports (FastAPI and Websocket) now synchronize with time before
+  sending data. This allows for interruptions to just work out of the box.
+
 - Improved bot speaking detection for all TTS services by using actual bot
   audio.
 
@@ -55,9 +426,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Fixed an issue with PlayHTTTSService, where the TTFB metrics were reporting
   very small time values.
 
+- Fixed an issue where AzureTTSService wasn't initializing the specified
+  language.
+
 ### Other
 
-- Added a new foundational example 22-natural-conversation.py. This examples
+- Add `23-bot-background-sound.py` foundational example.
+
+- Added a new foundational example `22-natural-conversation.py`. This example
   shows how to achieve a more natural conversation detecting when the user ends
   statement.
 

LICENSE

@@ -1,6 +1,6 @@
 BSD 2-Clause License
 
-Copyright (c) 2024, Daily
+Copyright (c) 2024–2025, Daily
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:

README.md

@@ -1,14 +1,21 @@
-<div align="center">
+<h1><div align="center">
  <img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
-</div>
+</div></h1>
 
-# Pipecat
+[![PyPI](https://img.shields.io/pypi/v/pipecat-ai)](https://pypi.org/project/pipecat-ai) [![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) [![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>
+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.
 
-`pipecat` is a framework for building voice (and multimodal) conversational agents. Things like personal coaches, meeting assistants, [story-telling toys for kids](https://storytelling-chatbot.fly.dev/), customer support bots, [intake flows](https://www.youtube.com/watch?v=lDevgsp9vn0), and snarky social companions.
+## What you can build
 
-Take a look at some example apps:
+- **Voice Assistants**: [Natural, real-time conversations with AI](https://demo.dailybots.ai/)
+- **Interactive Agents**: Personal coaches and meeting assistants
+- **Multimodal Apps**: Combine voice, video, images, and text
+- **Creative Tools**: [Story-telling experiences](https://storytelling-chatbot.fly.dev/) and social companions
+- **Business Solutions**: [Customer intake flows](https://www.youtube.com/watch?v=lDevgsp9vn0) and support bots
+- **Complex conversational flows**: [Refer to Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) to learn more
+
+## See it in action
 
 <p float="left">
     <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/simple-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/simple-chatbot/image.png" width="280" /></a>&nbsp;
@@ -18,33 +25,54 @@ Take a look at some example apps:
     <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/moondream-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/moondream-chatbot/image.png" width="280" /></a>
 </p>
 
-## Getting started with voice agents
+## Key features
+
+- **Voice-first Design**: Built-in speech recognition, TTS, and conversation handling
+- **Flexible Integration**: Works with popular AI services (OpenAI, ElevenLabs, etc.)
+- **Pipeline Architecture**: Build complex apps from simple, reusable components
+- **Real-time Processing**: Frame-based pipeline architecture for fluid interactions
+- **Production Ready**: Enterprise-grade WebRTC and Websocket support
+
+💡 Looking to build structured conversations? Check out [Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) for managing complex conversational states and transitions.
+
+## Getting started
 
 You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you’re ready. You can also add a 📞 telephone number, 🖼️ image output, 📺 video input, use different LLMs, and more.
 
 ```shell
-# install the module
+# Install the module
 pip install pipecat-ai
 
-# set up an .env file with API keys
+# Set up your environment
 cp dot-env.template .env
 ```
 
-By default, in order to minimize dependencies, only the basic framework functionality is available. Some third-party AI services require additional dependencies that you can install with:
+To keep things lightweight, only the core framework is included by default. If you need support for third-party AI services, you can add the necessary dependencies with:
 
 ```shell
 pip install "pipecat-ai[option,...]"
 ```
 
-Your project may or may not need these, so they're made available as optional requirements. Here is a list:
+Available options include:
 
-- **AI services**: `anthropic`, `assemblyai`, `aws`, `azure`, `deepgram`, `gladia`, `google`, `fal`, `lmnt`, `moondream`, `openai`, `openpipe`, `playht`, `silero`, `whisper`, `xtts`
-- **Transports**: `local`, `websocket`, `daily`
+| 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), [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]"`   |
+
+📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 
 ## Code examples
 
-- [foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational) — small snippets that build on each other, introducing one or two concepts at a time
-- [example apps](https://github.com/pipecat-ai/pipecat/tree/main/examples/) — complete applications that you can use as starting points for development
+- [Foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational) — small snippets that build on each other, introducing one or two concepts at a time
+- [Example apps](https://github.com/pipecat-ai/pipecat/tree/main/examples/) — complete applications that you can use as starting points for development
 
 ## A simple voice agent running locally
 
@@ -109,7 +137,7 @@ Run it with:
 python app.py
 ```
 
-Daily provides a prebuilt WebRTC user interface. Whilst the app is running, you can visit at `https://<yourdomain>.daily.co/<room_url>` and listen to the bot say hello!
+Daily provides a prebuilt WebRTC user interface. While the app is running, you can visit at `https://<yourdomain>.daily.co/<room_url>` and listen to the bot say hello!
 
 ## WebRTC for production use
 
@@ -119,16 +147,6 @@ One way to get up and running quickly with WebRTC is to sign up for a Daily deve
 
 Sign up [here](https://dashboard.daily.co/u/signup) and [create a room](https://docs.daily.co/reference/rest-api/rooms) in the developer Dashboard.
 
-## What is VAD?
-
-Voice Activity Detection &mdash; very important for knowing when a user has finished speaking to your bot. If you are not using press-to-talk, and want Pipecat to detect when the user has finished talking, VAD is an essential component for a natural feeling conversation.
-
-Pipecat makes use of WebRTC VAD by default when using a WebRTC transport layer. Optionally, you can use Silero VAD for improved accuracy at the cost of higher CPU usage.
-
-```shell
-pip install pipecat-ai[silero]
-```
-
 ## 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:_
@@ -179,9 +197,7 @@ You can use [use-package](https://github.com/jwiegley/use-package) to install [e
   :hook ((python-mode . lazy-ruff-mode))
   :config
   (setq lazy-ruff-format-command "ruff format")
-  (setq lazy-ruff-only-format-block t)
-  (setq lazy-ruff-only-format-region t)
-  (setq lazy-ruff-only-format-buffer t))
+  (setq lazy-ruff-check-command "ruff check --select I"))
 ```
 
 `ruff` was installed in the `venv` environment described before, so you should be able to use [pyvenv-auto](https://github.com/ryotaro612/pyvenv-auto) to automatically load that environment inside Emacs.
@@ -191,7 +207,6 @@ You can use [use-package](https://github.com/jwiegley/use-package) to install [e
   :ensure t
   :defer t
   :hook ((python-mode . pyvenv-auto-run)))
-
 ```
 
 ### Visual Studio Code
@@ -206,8 +221,33 @@ Install the
 }
 ```
 
+### PyCharm
+
+`ruff` was installed in the `venv` environment described before, now to enable autoformatting on save, go to `File` -> `Settings` -> `Tools` -> `File Watchers` and add a new watcher with the following settings:
+
+1. **Name**: `Ruff formatter`
+2. **File type**: `Python`
+3. **Working directory**: `$ContentRoot$`
+4. **Arguments**: `format $FilePath$`
+5. **Program**: `$PyInterpreterDirectory$/ruff`
+
+## Contributing
+
+We welcome contributions from the community! Whether you're fixing bugs, improving documentation, or adding new features, here's how you can help:
+
+- **Found a bug?** Open an [issue](https://github.com/pipecat-ai/pipecat/issues)
+- **Have a feature idea?** Start a [discussion](https://discord.gg/pipecat)
+- **Want to contribute code?** Check our [CONTRIBUTING.md](CONTRIBUTING.md) guide
+- **Documentation improvements?** [Docs](https://github.com/pipecat-ai/docs) PRs are always welcome
+
+Before submitting a pull request, please check existing issues and PRs to avoid duplicates.
+
+We aim to review all contributions promptly and provide constructive feedback to help get your changes merged.
+
 ## Getting help
 
 ➡️ [Join our Discord](https://discord.gg/pipecat)
 
+➡️ [Read the docs](https://docs.pipecat.ai)
+
 ➡️ [Reach us on X](https://x.com/pipecat_ai)

dev-requirements.txt

@@ -1,8 +1,9 @@
-build~=1.2.1
-grpcio-tools~=1.62.2
+build~=1.2.2
+grpcio-tools~=1.68.1
 pip-tools~=7.4.1
-pyright~=1.1.376
-pytest~=8.3.2
-ruff~=0.6.7
-setuptools~=72.2.0
+pyright~=1.1.390
+pytest~=8.3.4
+ruff~=0.8.3
+setuptools~=75.6.0
 setuptools_scm~=8.1.0
+python-dotenv~=1.0.1

docs/api/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = .
+BUILDDIR      = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/api/README.md

@@ -0,0 +1,109 @@
+# Pipecat Documentation
+
+This directory contains the source files for auto-generating Pipecat's server API reference documentation.
+
+## Setup
+
+1. Install documentation dependencies:
+
+```bash
+pip install -r requirements.txt
+```
+
+2. Make the build scripts executable:
+
+```bash
+chmod +x build-docs.sh rtd-test.py
+```
+
+## Building Documentation
+
+From this directory, you can build the documentation in several ways:
+
+### Local Build
+
+```bash
+# Using the build script (automatically opens docs when done)
+./build-docs.sh
+
+# Or directly with sphinx-build
+sphinx-build -b html . _build/html -W --keep-going
+```
+
+### ReadTheDocs Test Build
+
+To test the documentation build process exactly as it would run on ReadTheDocs:
+
+```bash
+./rtd-test.py
+```
+
+This script:
+
+- Creates a fresh virtual environment
+- Installs all dependencies as specified in requirements files
+- Handles conflicting dependencies (like grpcio versions for Riva and PlayHT)
+- Builds the documentation in an isolated environment
+- Provides detailed logging of the build process
+
+Use this script to verify your documentation will build correctly on ReadTheDocs before pushing changes.
+
+## Viewing Documentation
+
+The built documentation will be available at `_build/html/index.html`. To open:
+
+```bash
+# On MacOS
+open _build/html/index.html
+
+# On Linux
+xdg-open _build/html/index.html
+
+# On Windows
+start _build/html/index.html
+```
+
+## Directory Structure
+
+```
+.
+├── api/            # Auto-generated API documentation
+├── _build/         # Built documentation
+├── _static/        # Static files (images, css, etc.)
+├── conf.py         # Sphinx configuration
+├── index.rst       # Main documentation entry point
+├── requirements-base.txt    # Base documentation dependencies
+├── requirements-riva.txt    # Riva-specific dependencies
+├── requirements-playht.txt  # PlayHT-specific dependencies
+├── build-docs.sh   # Local build script
+└── rtd-test.py     # ReadTheDocs test build script
+```
+
+## Notes
+
+- Documentation is auto-generated from Python docstrings
+- Service modules are automatically detected and included
+- The build process matches our ReadTheDocs configuration
+- Warnings are treated as errors (-W flag) to maintain consistency
+- The --keep-going flag ensures all errors are reported
+- Dependencies are split into multiple requirements files to handle version conflicts
+
+## Troubleshooting
+
+If you encounter missing service modules:
+
+1. Verify the service is installed with its extras: `pip install pipecat-ai[service-name]`
+2. Check the build logs for import errors
+3. Ensure the service module is properly initialized in the package
+4. Run `./rtd-test.py` to test in an isolated environment matching ReadTheDocs
+
+For dependency conflicts:
+
+1. Check the requirements files for version specifications
+2. Use `rtd-test.py` to verify dependency resolution
+3. Consider adding service-specific requirements files if needed
+
+For more information:
+
+- [ReadTheDocs Configuration](.readthedocs.yaml)
+- [Sphinx Documentation](https://www.sphinx-doc.org/)

docs/api/build-docs.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+# Clean previous build
+rm -rf _build
+
+# Build docs matching ReadTheDocs configuration
+sphinx-build -b html -d _build/doctrees . _build/html -W --keep-going
+
+# Open docs (MacOS)
+open _build/html/index.html

docs/api/conf.py

@@ -0,0 +1,252 @@
+import logging
+import sys
+from pathlib import Path
+
+# Configure logging
+logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
+logger = logging.getLogger("sphinx-build")
+
+# Add source directory to path
+docs_dir = Path(__file__).parent
+project_root = docs_dir.parent.parent
+sys.path.insert(0, str(project_root / "src"))
+
+# Project information
+project = "pipecat-ai"
+copyright = "2024, Daily"
+author = "Daily"
+
+# General configuration
+extensions = [
+    "sphinx.ext.autodoc",
+    "sphinx.ext.napoleon",
+    "sphinx.ext.viewcode",
+    "sphinx.ext.intersphinx",
+]
+
+# Napoleon settings
+napoleon_google_docstring = True
+napoleon_numpy_docstring = False
+napoleon_include_init_with_doc = True
+
+# AutoDoc settings
+autodoc_default_options = {
+    "members": True,
+    "member-order": "bysource",
+    "special-members": "__init__",
+    "undoc-members": True,
+    "exclude-members": "__weakref__",
+    "no-index": True,
+    "show-inheritance": True,
+}
+
+# Mock imports for optional dependencies
+autodoc_mock_imports = [
+    "riva",
+    "livekit",
+    "pyht",  # Base PlayHT package
+    "pyht.async_client",  # PlayHT specific imports
+    "pyht.client",
+    "pyht.protos",
+    "pyht.protos.api_pb2",
+    "pipecat_ai_playht",  # PlayHT wrapper
+    "anthropic",
+    "assemblyai",
+    "boto3",
+    "azure",
+    "cartesia",
+    "deepgram",
+    "elevenlabs",
+    "fal",
+    "gladia",
+    "google",
+    "krisp",
+    "langchain",
+    "lmnt",
+    "noisereduce",
+    "openai",
+    "openpipe",
+    "simli",
+    "soundfile",
+    # Existing mocks
+    "pipecat_ai_krisp",
+    "pyaudio",
+    "_tkinter",
+    "tkinter",
+    "daily",
+    "daily_python",
+    "pydantic.BaseModel",
+    "pydantic.Field",
+    "pydantic._internal._model_construction",
+    "pydantic._internal._fields",
+]
+
+# HTML output settings
+html_theme = "sphinx_rtd_theme"
+html_static_path = ["_static"]
+autodoc_typehints = "description"
+html_show_sphinx = False
+
+
+def verify_modules():
+    """Verify that required modules are available."""
+    required_modules = {
+        "services": [
+            "assemblyai",
+            "aws",
+            "cartesia",
+            "deepgram",
+            "google",
+            "lmnt",
+            "riva",
+            "simli",
+        ],
+        "serializers": ["livekit"],
+        "vad": ["silero", "vad_analyzer"],
+        "transports": {
+            "services": ["daily", "livekit"],
+            "local": ["audio", "tk"],
+            "network": ["fastapi_websocket", "websocket_server"],
+        },
+    }
+
+    missing = []
+    for category, modules in required_modules.items():
+        if isinstance(modules, dict):
+            # Handle nested structure
+            for subcategory, submodules in modules.items():
+                for module in submodules:
+                    try:
+                        __import__(f"pipecat.{category}.{subcategory}.{module}")
+                        logger.info(
+                            f"Successfully imported pipecat.{category}.{subcategory}.{module}"
+                        )
+                    except (ImportError, TypeError, NameError) as e:
+                        missing.append(f"pipecat.{category}.{subcategory}.{module}")
+                        logger.warning(
+                            f"Optional module not available: pipecat.{category}.{subcategory}.{module} - {str(e)}"
+                        )
+        else:
+            # Handle flat structure
+            for module in modules:
+                try:
+                    __import__(f"pipecat.{category}.{module}")
+                    logger.info(f"Successfully imported pipecat.{category}.{module}")
+                except (ImportError, TypeError, NameError) as e:
+                    missing.append(f"pipecat.{category}.{module}")
+                    logger.warning(
+                        f"Optional module not available: pipecat.{category}.{module} - {str(e)}"
+                    )
+
+    if missing:
+        logger.warning(f"Some optional modules are not available: {missing}")
+
+
+def clean_title(title: str) -> str:
+    """Automatically clean module titles."""
+    # Remove everything after space (like 'module', 'processor', etc.)
+    title = title.split(" ")[0]
+
+    # Get the last part of the dot-separated path
+    parts = title.split(".")
+    title = parts[-1]
+
+    # Special cases for service names and common acronyms
+    special_cases = {
+        "ai": "AI",
+        "aws": "AWS",
+        "api": "API",
+        "vad": "VAD",
+        "assemblyai": "AssemblyAI",
+        "deepgram": "Deepgram",
+        "elevenlabs": "ElevenLabs",
+        "openai": "OpenAI",
+        "openpipe": "OpenPipe",
+        "playht": "PlayHT",
+        "xtts": "XTTS",
+        "lmnt": "LMNT",
+    }
+
+    # Check if the entire title is a special case
+    if title.lower() in special_cases:
+        return special_cases[title.lower()]
+
+    # Otherwise, capitalize each word
+    words = title.split("_")
+    cleaned_words = []
+    for word in words:
+        if word.lower() in special_cases:
+            cleaned_words.append(special_cases[word.lower()])
+        else:
+            cleaned_words.append(word.capitalize())
+
+    return " ".join(cleaned_words)
+
+
+def setup(app):
+    """Generate API documentation during Sphinx build."""
+    from sphinx.ext.apidoc import main
+
+    docs_dir = Path(__file__).parent
+    project_root = docs_dir.parent.parent
+    output_dir = str(docs_dir / "api")
+    source_dir = str(project_root / "src" / "pipecat")
+
+    # Clean existing files
+    if Path(output_dir).exists():
+        import shutil
+
+        shutil.rmtree(output_dir)
+        logger.info(f"Cleaned existing documentation in {output_dir}")
+
+    logger.info(f"Generating API documentation...")
+    logger.info(f"Output directory: {output_dir}")
+    logger.info(f"Source directory: {source_dir}")
+
+    excludes = [
+        str(project_root / "src/pipecat/pipeline/to_be_updated"),
+        str(project_root / "src/pipecat/processors/gstreamer"),
+        str(project_root / "src/pipecat/services/to_be_updated"),
+        str(project_root / "src/pipecat/vad"),  # deprecated
+        "**/test_*.py",
+        "**/tests/*.py",
+    ]
+
+    try:
+        main(
+            [
+                "-f",  # Force overwriting
+                "-e",  # Don't generate empty files
+                "-M",  # Put module documentation before submodule documentation
+                "--no-toc",  # Don't create a table of contents file
+                "--separate",  # Put documentation for each module in its own page
+                "--module-first",  # Module documentation before submodule documentation
+                "--implicit-namespaces",  # Added: Handle implicit namespace packages
+                "-o",
+                output_dir,
+                source_dir,
+            ]
+            + excludes
+        )
+
+        logger.info("API documentation generated successfully!")
+
+        # Process generated RST files to update titles
+        for rst_file in Path(output_dir).glob("**/*.rst"):  # Changed to recursive glob
+            content = rst_file.read_text()
+            lines = content.split("\n")
+
+            # Find and clean up the title
+            if lines and "=" in lines[1]:  # Title is typically the first line
+                old_title = lines[0]
+                new_title = clean_title(old_title)
+                content = content.replace(old_title, new_title)
+                rst_file.write_text(content)
+                logger.info(f"Updated title: {old_title} -> {new_title}")
+
+    except Exception as e:
+        logger.error(f"Error generating API documentation: {e}", exc_info=True)
+
+
+# Run module verification
+verify_modules()

docs/api/index.rst

@@ -0,0 +1,77 @@
+Pipecat API Reference Docs
+==========================
+
+Welcome to Pipecat's API reference documentation!
+
+Pipecat is an open source framework for building voice and multimodal assistants.
+It provides a flexible pipeline architecture for connecting various AI services,
+audio processing, and transport layers.
+
+Quick Links
+-----------
+
+* `GitHub Repository <https://github.com/pipecat-ai/pipecat>`_
+* `Website <https://pipecat.ai>`_
+
+API Reference
+-------------
+
+Core Components
+~~~~~~~~~~~~~~~
+
+* :mod:`Frames <pipecat.frames>`
+* :mod:`Processors <pipecat.processors>`
+* :mod:`Pipeline <pipecat.pipeline>`
+
+Audio Processing
+~~~~~~~~~~~~~~~~
+
+* :mod:`Audio <pipecat.audio>`
+
+Services
+~~~~~~~~
+
+* :mod:`Services <pipecat.services>`
+
+Transport & Serialization
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+* :mod:`Transports <pipecat.transports>`
+   * :mod:`Local <pipecat.transports.local>`
+   * :mod:`Network <pipecat.transports.network>`
+   * :mod:`Services <pipecat.transports.services>`
+* :mod:`Serializers <pipecat.serializers>`
+
+Utilities
+~~~~~~~~~
+
+* :mod:`Clocks <pipecat.clocks>`
+* :mod:`Metrics <pipecat.metrics>`
+* :mod:`Sync <pipecat.sync>`
+* :mod:`Transcriptions <pipecat.transcriptions>`
+* :mod:`Utils <pipecat.utils>`
+
+.. toctree::
+   :maxdepth: 3
+   :caption: API Reference
+   :hidden:
+
+   Audio <api/pipecat.audio>
+   Clocks <api/pipecat.clocks>
+   Frames <api/pipecat.frames>
+   Metrics <api/pipecat.metrics>
+   Pipeline <api/pipecat.pipeline>
+   Processors <api/pipecat.processors>
+   Serializers <api/pipecat.serializers>
+   Services <api/pipecat.services>
+   Sync <api/pipecat.sync>
+   Transcriptions <api/pipecat.transcriptions>
+   Transports <api/pipecat.transports>
+   Utils <api/pipecat.utils>
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

docs/api/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/api/requirements.txt

@@ -0,0 +1,40 @@
+# Sphinx dependencies
+sphinx>=8.1.3
+sphinx-rtd-theme
+sphinx-markdown-builder
+sphinx-autodoc-typehints
+toml
+
+# Install all extras individually to ensure they're properly resolved
+pipecat-ai[anthropic]
+pipecat-ai[assemblyai]
+pipecat-ai[aws]
+pipecat-ai[azure]
+pipecat-ai[canonical]
+pipecat-ai[cartesia]
+pipecat-ai[daily]
+pipecat-ai[deepgram]
+pipecat-ai[elevenlabs]
+pipecat-ai[fal]
+pipecat-ai[fireworks]
+pipecat-ai[gladia]
+pipecat-ai[google]
+pipecat-ai[grok]
+pipecat-ai[groq]
+# pipecat-ai[krisp] # Mocked instead
+pipecat-ai[langchain]
+pipecat-ai[livekit]
+pipecat-ai[lmnt]
+pipecat-ai[local]
+pipecat-ai[moondream]
+pipecat-ai[nim]
+pipecat-ai[noisereduce]
+pipecat-ai[openai]
+# pipecat-ai[openpipe]
+# pipecat-ai[playht] # Mocked due to grpcio conflict with riva
+pipecat-ai[riva]
+pipecat-ai[silero]
+pipecat-ai[simli]
+pipecat-ai[soundfile]
+pipecat-ai[websocket]
+pipecat-ai[whisper]

docs/api/rtd-test.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+set -e
+
+# Configuration
+DOCS_DIR=$(pwd)
+PROJECT_ROOT=$(cd ../../ && pwd)
+TEST_DIR="/tmp/rtd-test-$(date +%Y%m%d_%H%M%S)"
+
+echo "Creating test directory: $TEST_DIR"
+mkdir -p "$TEST_DIR"
+cd "$TEST_DIR"
+
+# Create virtual environment
+python -m venv venv
+source venv/bin/activate
+
+echo "Installing build dependencies..."
+pip install --upgrade pip wheel setuptools
+
+echo "Installing documentation dependencies..."
+pip install -r "$DOCS_DIR/requirements.txt"
+
+echo "Building documentation..."
+cd "$DOCS_DIR"
+sphinx-build -b html . "_build/html"
+
+echo "Build complete. Check _build/html directory for output."
+
+# Print summary
+echo -e "\n=== Build Summary ==="
+echo "Documentation: $DOCS_DIR/_build/html"
+echo "Test environment: $TEST_DIR"
+echo -e "\nTo view the documentation:"
+echo "open $DOCS_DIR/_build/html/index.html"
+
+# Print installed packages for verification
+echo -e "\n=== Installed Packages ==="
+pip freeze | grep -E "sphinx|pipecat"

docs/frame.md

@@ -0,0 +1,110 @@
+# Understanding Different Frame Types in the Pipecat System
+
+In the Pipecat system, frames are used to represent different types of data and control signals that flow through the pipeline. Understanding these frame types is crucial for working with the system effectively. This tutorial will cover the main categories of frames and their specific uses.
+
+## 1. Base Frame Classes
+
+### Frame
+The `Frame` class is the base class for all frames. It includes:
+- `id`: A unique identifier
+- `name`: A descriptive name
+- `pts`: Presentation timestamp (optional)
+
+### DataFrame
+`DataFrame` is a subclass of `Frame` and serves as a base for most data-carrying frames.
+
+## 2. Audio Frames
+
+### AudioRawFrame
+Represents a chunk of audio with properties:
+- `audio`: Raw audio data
+- `sample_rate`: Audio sample rate
+- `num_channels`: Number of audio channels
+
+Subclasses include:
+- `InputAudioRawFrame`: For audio from input sources
+- `OutputAudioRawFrame`: For audio to be played by output devices
+- `TTSAudioRawFrame`: For audio generated by Text-to-Speech services
+
+## 3. Image Frames
+
+### ImageRawFrame
+Represents an image with properties:
+- `image`: Raw image data
+- `size`: Image dimensions
+- `format`: Image format (e.g., JPEG, PNG)
+
+Subclasses include:
+- `InputImageRawFrame`: For images from input sources
+- `OutputImageRawFrame`: For images to be displayed
+- `UserImageRawFrame`: For images associated with a specific user
+- `VisionImageRawFrame`: For images with associated text for description
+- `URLImageRawFrame`: For images with an associated URL
+
+### SpriteFrame
+Represents an animated sprite, containing a list of `ImageRawFrame` objects.
+
+## 4. Text and Transcription Frames
+
+### TextFrame
+Represents a chunk of text, used for various purposes in the pipeline.
+
+### TranscriptionFrame
+A specialized `TextFrame` for speech transcriptions, including:
+- `user_id`: ID of the speaking user
+- `timestamp`: When the transcription was generated
+- `language`: Detected language of the speech
+
+### InterimTranscriptionFrame
+Similar to `TranscriptionFrame`, but for interim (not final) transcriptions.
+
+## 5. LLM (Language Model) Frames
+
+### LLMMessagesFrame
+Contains a list of messages for an LLM service to process.
+
+### LLMMessagesAppendFrame and LLMMessagesUpdateFrame
+Used to modify the current context of LLM messages.
+
+### LLMSetToolsFrame
+Specifies tools (functions) available for the LLM to use.
+
+### LLMEnablePromptCachingFrame
+Controls prompt caching in certain LLMs.
+
+## 6. System and Control Frames
+
+### SystemFrame
+Base class for system-level frames.
+
+Important system frames include:
+- `StartFrame`: Initiates a pipeline
+- `CancelFrame`: Stops a pipeline immediately
+- `ErrorFrame`: Notifies of errors (with `FatalErrorFrame` for unrecoverable errors)
+- `EndTaskFrame` and `CancelTaskFrame`: Control pipeline tasks
+- `StartInterruptionFrame` and `StopInterruptionFrame`: Indicate user speech for interruptions
+
+### ControlFrame
+Base class for control-flow frames.
+
+Notable control frames:
+- `EndFrame`: Signals the end of a pipeline
+- `LLMFullResponseStartFrame` and `LLMFullResponseEndFrame`: Bracket LLM responses
+- `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame`: Indicate user speech activity
+- `BotStartedSpeakingFrame` and `BotStoppedSpeakingFrame`: Indicate bot speech activity
+- `TTSStartedFrame` and `TTSStoppedFrame`: Bracket Text-to-Speech responses
+
+## 7. Special Purpose Frames
+
+### MetricsFrame
+Contains performance metrics data.
+
+### FunctionCallInProgressFrame and FunctionCallResultFrame
+Used for handling LLM function (tool) calls.
+
+### ServiceUpdateSettingsFrame
+Base class for updating service settings, with specific subclasses for LLM, TTS, and STT services.
+
+## Conclusion
+
+Understanding these frame types is essential for working with the Pipecat system. Each frame type serves a specific purpose in the pipeline, whether it's carrying data (like audio or images), controlling the flow of the pipeline, or managing system-level operations. By using the appropriate frame types, you can effectively process and transmit various kinds of information through your pipeline.

dot-env.template

@@ -52,4 +52,32 @@ OPENPIPE_API_KEY=...
 # Tavus
 TAVUS_API_KEY=...
 TAVUS_REPLICA_ID=...
-TAVUS_PERSONA_ID=...
+TAVUS_PERSONA_ID=...
+
+# Simli
+SIMLI_API_KEY=...
+SIMLI_FACE_ID=...
+
+# Krisp
+KRISP_MODEL_PATH=...
+
+# DeepSeek
+DEEPSEEK_API_KEY=...
+
+# Groq
+GROQ_API_KEY=...
+
+# Grok
+GROK_API_KEY=...
+
+# Together.ai
+TOGETHER_API_KEY=...
+
+# Cerebras
+CEREBRAS_API_KEY=...
+
+# Fish Audio
+FISH_API_KEY=...
+
+# Assembly AI
+ASSEMBLYAI_API_KEY=...

examples/README.md

@@ -42,6 +42,7 @@ Next, follow the steps in the README for each demo.
 | [Dialin Chatbot](dialin-chatbot)             | A chatbot that connects to an incoming phone call from Daily or Twilio.                                                                    | Deepgram, ElevenLabs, OpenAI, Daily, Twilio                       |
 | [Twilio Chatbot](twilio-chatbot)             | A chatbot that connects to an incoming phone call from Twilio.                                                                             | Deepgram, ElevenLabs, OpenAI, Daily, Twilio                       |
 | [studypal](studypal)                         | A chatbot to have a conversation about any article on the web                                                                              |                                                                   |
+| [WebSocket Chatbot Server](websocket-server) | A real-time websocket server that handles audio streaming and bot interactions with speech-to-text and text-to-speech capabilities | `python-websockets`, `openai`, `deepgram`, `silero-tts`, `numpy` |
 
 > [!IMPORTANT]
 > These example projects use Daily as a WebRTC transport and can be joined using their hosted Prebuilt UI.

examples/canonical-metrics/bot.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -15,7 +15,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import EndFrame, LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -102,7 +102,6 @@ async def main():
             audio_buffer_processor=audio_buffer_processor,
             aiohttp_session=session,
             api_key=os.getenv("CANONICAL_API_KEY"),
-            api_url=os.getenv("CANONICAL_API_URL"),
             call_id=str(uuid.uuid4()),
             assistant="pipecat-chatbot",
             assistant_speaks_first=True,
@@ -125,7 +124,7 @@ async def main():
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         @transport.event_handler("on_participant_left")
         async def on_participant_left(transport, participant, reason):

examples/canonical-metrics/runner.py

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

examples/canonical-metrics/server.py

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

examples/chatbot-audio-recording/bot.py

@@ -1,22 +1,24 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
+import datetime
+import io
 import os
 import sys
-
-import aiohttp
-import datetime
 import wave
+
+import aiofiles
+import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import EndFrame, LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -32,15 +34,17 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")
 
 
-async def save_audio(audiobuffer):
-    if audiobuffer.has_audio():
-        merged_audio = audiobuffer.merge_audio_buffers()
+async def save_audio(audio: bytes, sample_rate: int, num_channels: int):
+    if len(audio) > 0:
         filename = f"conversation_recording{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}.wav"
-        with wave.open(filename, "wb") as wf:
-            wf.setnchannels(2)
-            wf.setsampwidth(2)
-            wf.setframerate(audiobuffer._sample_rate)
-            wf.writeframes(merged_audio)
+        with io.BytesIO() as buffer:
+            with wave.open(buffer, "wb") as wf:
+                wf.setsampwidth(2)
+                wf.setnchannels(num_channels)
+                wf.setframerate(sample_rate)
+                wf.writeframes(audio)
+            async with aiofiles.open(filename, "wb") as file:
+                await file.write(buffer.getvalue())
         print(f"Merged audio saved to {filename}")
     else:
         print("No audio data to save")
@@ -106,7 +110,9 @@ async def main():
         context = OpenAILLMContext(messages)
         context_aggregator = llm.create_context_aggregator(context)
 
-        audiobuffer = AudioBufferProcessor()
+        # Save audio every 10 seconds.
+        audiobuffer = AudioBufferProcessor(buffer_size=480000)
+
         pipeline = Pipeline(
             [
                 transport.input(),  # microphone
@@ -121,16 +127,19 @@ async def main():
 
         task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
+        @audiobuffer.event_handler("on_audio_data")
+        async def on_audio_data(buffer, audio, sample_rate, num_channels):
+            await save_audio(audio, sample_rate, num_channels)
+
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         @transport.event_handler("on_participant_left")
         async def on_participant_left(transport, participant, reason):
             print(f"Participant left: {participant}")
             await task.queue_frame(EndFrame())
-            await save_audio(audiobuffer)
 
         runner = PipelineRunner()
 

examples/chatbot-audio-recording/requirements.txt

@@ -1,3 +1,4 @@
+aiofiles
 python-dotenv
 fastapi[all]
 uvicorn

examples/chatbot-audio-recording/runner.py

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

examples/chatbot-audio-recording/server.py

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

examples/deployment/flyio-example/bot.py

@@ -1,22 +1,21 @@
+import argparse
 import asyncio
 import os
 import sys
-import argparse
+
+from dotenv import load_dotenv
+from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.frames.frames import LLMMessagesFrame, EndFrame
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.openai import OpenAILLMService
 from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -76,7 +75,7 @@ async def main(room_url: str, token: str):
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):
         await transport.capture_participant_transcription(participant["id"])
-        await task.queue_frames([LLMMessagesFrame(messages)])
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
     @transport.event_handler("on_participant_left")
     async def on_participant_left(transport, participant, reason):

examples/deployment/flyio-example/bot_runner.py

@@ -1,29 +1,27 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import argparse
-import subprocess
 import os
-
+import subprocess
 from contextlib import asynccontextmanager
 
-from fastapi import FastAPI, Request, HTTPException
+import aiohttp
+from dotenv import load_dotenv
+from fastapi import FastAPI, HTTPException, Request
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import JSONResponse
 
 from pipecat.transports.services.helpers.daily_rest import (
     DailyRESTHelper,
     DailyRoomObject,
-    DailyRoomProperties,
     DailyRoomParams,
+    DailyRoomProperties,
 )
 
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 

examples/deployment/modal-example/.gitignore

@@ -0,0 +1,91 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+dist/
+*.egg-info/
+*.egg
+.installed.cfg
+.eggs/
+downloads/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+MANIFEST
+
+# Virtual Environments
+venv/
+env/
+.env
+.venv/
+ENV/
+env.bak/
+venv.bak/
+
+# IDE
+.idea/
+.vscode/
+.spyderproject
+.spyproject
+.ropeproject
+
+# Testing and Coverage
+.coverage
+.coverage.*
+htmlcov/
+.pytest_cache/
+.tox/
+.nox/
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+cover/
+
+# Logs and Databases
+*.log
+*.db
+db.sqlite3
+db.sqlite3-journal
+pip-log.txt
+
+# System Files
+.DS_Store
+Thumbs.db
+desktop.ini
+*.swp
+*.swo
+*.bak
+*.tmp
+*~
+
+# Build and Documentation
+docs/_build/
+.pybuilder/
+target/
+instance/
+.webassets-cache
+.pdm.toml
+.pdm-python
+.pdm-build/
+__pypackages__/
+
+# Other
+*.mo
+*.pot
+*.sage.py
+.mypy_cache/
+.dmypy.json
+dmypy.json
+.pyre/
+.pytype/
+cython_debug/
+.ipynb_checkpoints

examples/deployment/modal-example/README.md

@@ -0,0 +1,37 @@
+# Deploying Pipecat to Modal.com
+
+Barebones deployment example for [modal.com](https://www.modal.com)
+
+1. Install dependencies
+
+```bash
+python -m venv venv
+source venv/bin/active # or OS equivalent
+pip install -r requirements.txt
+```
+
+2. Setup .env
+
+```bash
+cp env.example .env
+```
+
+Alternatively, you can configure your Modal app to use [secrets](https://modal.com/docs/guide/secrets)
+
+3. Test the app locally
+
+```bash
+modal serve app.py
+```
+
+4. Deploy to production
+
+```bash
+modal deploy app.py
+```
+
+## Configuration options
+
+This app sets some sensible defaults for reducing cold starts, such as `minkeep_warm=1`, which will keep at least 1 warm instance ready for your bot function.
+
+It has been configured to only allow a concurrency of 1 (`max_inputs=1`) as each user will require their own running function.

examples/deployment/modal-example/app.py

@@ -0,0 +1,74 @@
+import os
+
+import aiohttp
+import modal
+from bot import _voice_bot_process
+from fastapi import HTTPException
+from fastapi.responses import JSONResponse
+from loguru import logger
+
+MAX_SESSION_TIME = 15 * 60  # 15 minutes
+
+app = modal.App("pipecat-modal")
+
+
+image = modal.Image.debian_slim(python_version="3.12").pip_install_from_requirements(
+    "requirements.txt"
+)
+
+
+@app.function(
+    image=image,
+    cpu=1.0,
+    secrets=[modal.Secret.from_dotenv()],
+    keep_warm=1,
+    enable_memory_snapshot=True,
+    max_inputs=1,  # Do not reuse instances across requests
+    retries=0,
+)
+def launch_bot_process(room_url: str, token: str):
+    _voice_bot_process(room_url, token)
+
+
+@app.function(
+    image=image,
+    secrets=[modal.Secret.from_dotenv()],
+)
+@modal.web_endpoint(method="POST")
+async def start():
+    from pipecat.transports.services.helpers.daily_rest import (
+        DailyRESTHelper,
+        DailyRoomParams,
+    )
+
+    logger.info("Request received")
+
+    async with aiohttp.ClientSession() as session:
+        daily_rest_helper = DailyRESTHelper(
+            daily_api_key=os.getenv("DAILY_API_KEY", ""),
+            daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
+            aiohttp_session=session,
+        )
+
+        # Create new Daily room
+        room = await daily_rest_helper.create_room(DailyRoomParams())
+        if not room.url:
+            raise HTTPException(
+                status_code=500,
+                detail="Unable to create room",
+            )
+        logger.info(f"Created room: {room.url}")
+
+        # Create bot token for room
+        token = await daily_rest_helper.get_token(room.url, MAX_SESSION_TIME)
+        if not token:
+            raise HTTPException(status_code=500, detail=f"Failed to get token for room: {room.url}")
+
+        logger.info(f"Bot token created: {token}")
+
+        # Spawn a new bot process
+        launch_bot_process.spawn(room_url=room.url, token=token)
+
+        # Return room URL to the user to join
+        # Note: in production, you would want to return a token to the user
+        return JSONResponse(content={"room_url": room.url, token: token})

examples/deployment/modal-example/bot.py

@@ -0,0 +1,90 @@
+import asyncio
+import os
+import sys
+
+from dotenv import load_dotenv
+from loguru import logger
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main(room_url: str, token: str):
+    from pipecat.audio.vad.silero import SileroVADAnalyzer
+    from pipecat.frames.frames import EndFrame
+    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.cartesia import CartesiaTTSService
+    from pipecat.services.openai import OpenAILLMService
+    from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+    transport = DailyTransport(
+        room_url,
+        token,
+        "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"
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = 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,
+        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"])
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_participant_left")
+    async def on_participant_left(transport, participant, reason):
+        await task.queue_frame(EndFrame())
+
+    runner = PipelineRunner()
+
+    await runner.run(task)
+
+
+def _voice_bot_process(room_url: str, token: str):
+    asyncio.run(main(room_url, token))

examples/deployment/modal-example/env.example

@@ -0,0 +1,3 @@
+DAILY_API_KEY=
+OPENAI_API_KEY=
+CARTESIA_API_KEY=

examples/deployment/modal-example/requirements.txt

@@ -0,0 +1,5 @@
+python-dotenv==1.0.1
+modal==0.71.3
+pipecat-ai[daily,silero,cartesia,openai]==0.0.52
+fastapi==0.115.6
+aiohttp==3.11.11

examples/dialin-chatbot/bot_daily.py

@@ -1,21 +1,20 @@
+import argparse
 import asyncio
 import os
 import sys
-import argparse
+
+from dotenv import load_dotenv
+from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.frames.frames import LLMMessagesFrame, EndFrame
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport, DailyDialinSettings
-
-from loguru import logger
-
-from dotenv import load_dotenv
+from pipecat.transports.services.daily import DailyDialinSettings, DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -82,7 +81,7 @@ async def main(room_url: str, token: str, callId: str, callDomain: str):
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):
         await transport.capture_participant_transcription(participant["id"])
-        await task.queue_frames([LLMMessagesFrame(messages)])
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
     @transport.event_handler("on_participant_left")
     async def on_participant_left(transport, participant, reason):

examples/dialin-chatbot/bot_runner.py

@@ -7,14 +7,14 @@ provisioning a room and starting a Pipecat bot in response.
 Refer to README for more information.
 """
 
-import aiohttp
-import os
 import argparse
+import os
 import subprocess
-
 from contextlib import asynccontextmanager
 
-from fastapi import FastAPI, Request, HTTPException
+import aiohttp
+from dotenv import load_dotenv
+from fastapi import FastAPI, HTTPException, Request
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import JSONResponse, PlainTextResponse
 from twilio.twiml.voice_response import VoiceResponse
@@ -22,13 +22,11 @@ from twilio.twiml.voice_response import VoiceResponse
 from pipecat.transports.services.helpers.daily_rest import (
     DailyRESTHelper,
     DailyRoomObject,
+    DailyRoomParams,
     DailyRoomProperties,
     DailyRoomSipParams,
-    DailyRoomParams,
 )
 
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 

examples/dialin-chatbot/bot_twilio.py

@@ -1,24 +1,22 @@
+import argparse
 import asyncio
 import os
 import sys
-import argparse
+
+from dotenv import load_dotenv
+from loguru import logger
+from twilio.rest import Client
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.frames.frames import LLMMessagesFrame, EndFrame
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from twilio.rest import Client
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -85,7 +83,7 @@ async def main(room_url: str, token: str, callId: str, sipUri: str):
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):
         await transport.capture_participant_transcription(participant["id"])
-        await task.queue_frames([LLMMessagesFrame(messages)])
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
     @transport.event_handler("on_participant_left")
     async def on_participant_left(transport, participant, reason):

examples/foundational/01-say-one-thing.py

@@ -1,26 +1,24 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
-from pipecat.frames.frames import EndFrame, TextFrame
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.task import PipelineTask
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.services.cartesia import CartesiaHttpTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
 from runner import configure
 
-from loguru import logger
-
-from dotenv import load_dotenv
+from pipecat.frames.frames import EndFrame, TTSSpeakFrame
+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.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -36,7 +34,7 @@ async def main():
             room_url, None, "Say One Thing", DailyParams(audio_out_enabled=True)
         )
 
-        tts = CartesiaHttpTTSService(
+        tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
         )
@@ -50,12 +48,9 @@ async def main():
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             participant_name = participant.get("info", {}).get("userName", "")
-            await task.queue_frame(TextFrame(f"Hello there, {participant_name}!"))
-
-        # Register an event handler to exit the application when the user leaves.
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.queue_frame(EndFrame())
+            await task.queue_frames(
+                [TTSSpeakFrame(f"Hello there, {participant_name}!"), EndFrame()]
+            )
 
         await runner.run(task)
 

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

@@ -1,15 +1,17 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
-from pipecat.frames.frames import TextFrame
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.frames.frames import EndFrame, TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
@@ -17,10 +19,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.local.audio import LocalAudioTransport
 
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -28,25 +26,24 @@ logger.add(sys.stderr, level="DEBUG")
 
 
 async def main():
-    async with aiohttp.ClientSession() as session:
-        transport = LocalAudioTransport(TransportParams(audio_out_enabled=True))
+    transport = LocalAudioTransport(TransportParams(audio_out_enabled=True))
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+    )
 
-        pipeline = Pipeline([tts, transport.output()])
+    pipeline = Pipeline([tts, transport.output()])
 
-        task = PipelineTask(pipeline)
+    task = PipelineTask(pipeline)
 
-        async def say_something():
-            await asyncio.sleep(1)
-            await task.queue_frame(TextFrame("Hello there!"))
+    async def say_something():
+        await asyncio.sleep(1)
+        await task.queue_frames([TTSSpeakFrame("Hello there, how is it going!"), EndFrame()])
 
-        runner = PipelineRunner()
+    runner = PipelineRunner()
 
-        await asyncio.gather(runner.run(task), say_something())
+    await asyncio.gather(runner.run(task), say_something())
 
 
 if __name__ == "__main__":

examples/foundational/01b-livekit-audio.py

@@ -4,6 +4,9 @@ import os
 import sys
 
 import aiohttp
+from dotenv import load_dotenv
+from livekit import api
+from loguru import logger
 
 from pipecat.frames.frames import TextFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -12,12 +15,6 @@ from pipecat.pipeline.task import PipelineTask
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.livekit import LiveKitParams, LiveKitTransport
 
-from livekit import api
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/01c-fastpitch.py

@@ -0,0 +1,54 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.frames.frames import EndFrame, TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.riva import FastPitchTTSService
+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, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url, None, "Say One Thing", DailyParams(audio_out_enabled=True)
+        )
+
+        tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+
+        runner = PipelineRunner()
+
+        task = PipelineTask(Pipeline([tts, transport.output()]))
+
+        # Register an event handler so we can play the audio when the
+        # participant joins.
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            participant_name = participant.get("info", {}).get("userName", "")
+            await task.queue_frames([TTSSpeakFrame(f"Aloha, {participant_name}!"), EndFrame()])
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/02-llm-say-one-thing.py

@@ -1,28 +1,26 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import EndFrame, LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
-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
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -37,7 +35,7 @@ async def main():
             room_url, None, "Say One Thing From an LLM", DailyParams(audio_out_enabled=True)
         )
 
-        tts = CartesiaHttpTTSService(
+        tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
         )
@@ -57,11 +55,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            await task.queue_frame(LLMMessagesFrame(messages))
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.queue_frame(EndFrame())
+            await task.queue_frames([LLMMessagesFrame(messages), EndFrame()])
 
         await runner.run(task)
 

examples/foundational/03-still-frame.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import EndFrame, TextFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -16,12 +20,6 @@ from pipecat.pipeline.task import PipelineTask
 from pipecat.services.fal import FalImageGenService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,16 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
-
 import tkinter as tk
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
 from pipecat.frames.frames import TextFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -19,10 +21,6 @@ from pipecat.services.fal import FalImageGenService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.local.tk import TkLocalTransport
 
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/04-utterance-and-speech.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -8,27 +8,24 @@
 # This example broken on latest pipecat and needs updating.
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 
-from pipecat.pipeline.merge_pipeline import SequentialMergePipeline
-from pipecat.pipeline.pipeline import Pipeline
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
 
 from pipecat.frames.frames import EndPipeFrame, LLMMessagesFrame, TextFrame
+from pipecat.pipeline.merge_pipeline import SequentialMergePipeline
+from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.task import PipelineTask
 from pipecat.services.azure import AzureLLMService, AzureTTSService
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.transport_services import TransportServiceOutput
 from pipecat.services.transports.daily_transport import DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,18 +1,21 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
-
 from dataclasses import dataclass
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import (
-    AppFrame,
+    DataFrame,
     Frame,
     LLMFullResponseStartFrame,
     LLMMessagesFrame,
@@ -22,19 +25,13 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
 from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.aggregators.sentence import SentenceAggregator
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaHttpTTSService
-from pipecat.services.openai import OpenAILLMService
 from pipecat.services.fal import FalImageGenService
+from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -42,7 +39,7 @@ logger.add(sys.stderr, level="DEBUG")
 
 
 @dataclass
-class MonthFrame(AppFrame):
+class MonthFrame(DataFrame):
     month: str
 
     def __str__(self):

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

@@ -1,23 +1,25 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
-
 import tkinter as tk
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
 from pipecat.frames.frames import (
     Frame,
+    LLMMessagesFrame,
     OutputAudioRawFrame,
+    TextFrame,
     TTSAudioRawFrame,
     URLImageRawFrame,
-    LLMMessagesFrame,
-    TextFrame,
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -26,15 +28,11 @@ from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.sentence import SentenceAggregator
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaHttpTTSService
-from pipecat.services.openai import OpenAILLMService
 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 loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import Frame, LLMMessagesFrame, MetricsFrame
+from pipecat.frames.frames import EndFrame, Frame, MetricsFrame
 from pipecat.metrics.metrics import (
     LLMUsageMetricsData,
     ProcessingMetricsData,
@@ -113,7 +113,11 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,18 +1,21 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
 from PIL import Image
+from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import Frame, OutputImageRawFrame, SystemFrame, TextFrame
+from pipecat.frames.frames import EndFrame, Frame, OutputImageRawFrame, SystemFrame, TextFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
@@ -20,14 +23,7 @@ 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.openai import OpenAILLMService
-from pipecat.transports.services.daily import DailyTransport
-
-from pipecat.transports.services.daily import DailyParams
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -130,6 +126,10 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             await task.queue_frames([TextFrame(f"Hi there {participant_name}!")])
 
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
         runner = PipelineRunner()
 
         await runner.run(task)

examples/foundational/07-interruptible-vad.py

@@ -1,30 +1,28 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
-from pipecat.frames.frames import LLMMessagesFrame
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.audio.vad.silero import SileroVAD
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.audio.vad.silero import SileroVAD
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -92,7 +90,11 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

examples/foundational/07-interruptible.py

@@ -1,16 +1,20 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -19,12 +23,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -90,7 +88,11 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -78,13 +78,25 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -9,9 +9,17 @@ import os
 import sys
 
 import aiohttp
+from dotenv import load_dotenv
+from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_community.chat_message_histories import ChatMessageHistory
+from langchain_core.chat_history import BaseChatMessageHistory
+from langchain_core.runnables.history import RunnableWithMessageHistory
+from langchain_openai import ChatOpenAI
+from loguru import logger
+from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame, LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -23,18 +31,6 @@ from pipecat.processors.frameworks.langchain import LangchainProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
-from langchain_community.chat_message_histories import ChatMessageHistory
-from langchain_core.chat_history import BaseChatMessageHistory
-from langchain_core.runnables.history import RunnableWithMessageHistory
-from langchain_openai import ChatOpenAI
-
-from loguru import logger
-
-from runner import configure
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 
@@ -105,7 +101,15 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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):
@@ -118,6 +122,10 @@ async def main():
             messages = [({"content": "Please briefly introduce yourself to the user."})]
             await task.queue_frames([LLMMessagesFrame(messages)])
 
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
         runner = PipelineRunner()
 
         await runner.run(task)

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

@@ -0,0 +1,117 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from deepgram import LiveOptions
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.frames.frames import (
+    BotInterruptionFrame,
+    EndFrame,
+    StopInterruptionFrame,
+    UserStartedSpeakingFrame,
+    UserStoppedSpeakingFrame,
+)
+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, DeepgramTTSService
+from pipecat.services.openai import OpenAILLMService
+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, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Respond bot",
+            DailyParams(
+                audio_in_enabled=True,
+                audio_out_enabled=True,
+            ),
+        )
+
+        stt = DeepgramSTTService(
+            api_key=os.getenv("DEEPGRAM_API_KEY"),
+            live_options=LiveOptions(vad_events=True, utterance_end_ms="1000"),
+        )
+
+        tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
+
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @stt.event_handler("on_speech_started")
+        async def on_speech_started(stt, *args, **kwargs):
+            await task.queue_frames([BotInterruptionFrame(), UserStartedSpeakingFrame()])
+
+        @stt.event_handler("on_utterance_end")
+        async def on_utterance_end(stt, *args, **kwargs):
+            await task.queue_frames([StopInterruptionFrame(), UserStoppedSpeakingFrame()])
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -31,11 +31,11 @@ logger.add(sys.stderr, level="DEBUG")
 
 async def main():
     async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+        (room_url, _) = await configure(session)
 
         transport = DailyTransport(
             room_url,
-            token,
+            None,
             "Respond bot",
             DailyParams(
                 audio_out_enabled=True,
@@ -73,13 +73,25 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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):
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,14 +11,14 @@ import sys
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 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.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
@@ -88,7 +88,11 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -0,0 +1,105 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
+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.openai import OpenAILLMService
+from pipecat.services.playht import PlayHTHttpTTSService
+from pipecat.transcriptions.language import Language
+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 = PlayHTHttpTTSService(
+            user_id=os.getenv("PLAYHT_USER_ID"),
+            api_key=os.getenv("PLAYHT_API_KEY"),
+            voice_url="s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json",
+        )
+
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            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.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -49,7 +49,7 @@ async def main():
         tts = PlayHTTTSService(
             user_id=os.getenv("PLAYHT_USER_ID"),
             api_key=os.getenv("PLAYHT_API_KEY"),
-            voice_url="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/manifest.json",
+            voice_url="s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json",
             params=PlayHTTTSService.InputParams(language=Language.EN),
         )
 
@@ -91,7 +91,11 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,16 +1,20 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -18,13 +22,6 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.azure import AzureLLMService, AzureSTTService, AzureTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -85,14 +82,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,14 +11,14 @@ import sys
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 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.openai import OpenAILLMService, OpenAITTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
@@ -70,14 +70,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,16 +1,21 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
+import time
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -19,13 +24,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openpipe import OpenPipeLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-import time
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -82,14 +80,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,16 +1,20 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -19,12 +23,6 @@ from pipecat.services.openai import OpenAILLMService
 from pipecat.services.xtts import XTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -50,7 +48,6 @@ async def main():
         tts = XTTSService(
             aiohttp_session=session,
             voice_id="Claribel Dervla",
-            language="en",
             base_url="http://localhost:8000",
         )
 
@@ -77,14 +74,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import EndFrame, LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -79,14 +79,22 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         # Register an event handler to exit the application when the user leaves.
         @transport.event_handler("on_participant_left")

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

@@ -1,16 +1,20 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -19,12 +23,6 @@ from pipecat.services.lmnt import LmntTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -73,14 +71,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -90,7 +90,10 @@ async def main():
         task = PipelineTask(
             pipeline,
             PipelineParams(
-                allow_interruptions=True, enable_metrics=True, enable_usage_metrics=True
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
             ),
         )
 
@@ -98,7 +101,11 @@ async def main():
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,12 +14,12 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 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.aws import AWSTTSService
+from pipecat.services.aws import PollyTTSService
 from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
@@ -32,11 +32,11 @@ logger.add(sys.stderr, level="DEBUG")
 
 async def main():
     async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+        (room_url, _) = await configure(session)
 
         transport = DailyTransport(
             room_url,
-            token,
+            None,
             "Respond bot",
             DailyParams(
                 audio_out_enabled=True,
@@ -48,12 +48,12 @@ async def main():
 
         stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = AWSTTSService(
+        tts = PollyTTSService(
             api_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
             aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
             region=os.getenv("AWS_REGION"),
             voice_id="Amy",
-            params=AWSTTSService.InputParams(engine="neural", language="en-GB", rate="1.05"),
+            params=PollyTTSService.InputParams(engine="neural", language="en-GB", rate="1.05"),
         )
 
         llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
@@ -80,14 +80,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,6 +22,7 @@ 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.transcriptions.language import Language
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -32,11 +33,11 @@ logger.add(sys.stderr, level="DEBUG")
 
 async def main():
     async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+        (room_url, _) = await configure(session)
 
         transport = DailyTransport(
             room_url,
-            token,
+            None,
             "Respond bot",
             DailyParams(
                 audio_out_enabled=True,
@@ -50,8 +51,8 @@ async def main():
         stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
         tts = GoogleTTSService(
-            voice_id="en-US-Neural2-J",
-            params=GoogleTTSService.InputParams(language="en-US", rate="1.05"),
+            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")
@@ -78,14 +79,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -79,14 +79,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            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.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -0,0 +1,104 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.filters.krisp_filter import KrispFilter
+from pipecat.frames.frames import EndFrame
+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, DeepgramTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+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,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+                audio_in_filter=KrispFilter(),
+            ),
+        )
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
+
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            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):
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,104 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
+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.openai import OpenAILLMService
+from pipecat.services.rime import RimeHttpTTSService
+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 = RimeHttpTTSService(
+            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")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            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.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,96 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
+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.nim import NimLLMService
+from pipecat.services.riva import FastPitchTTSService, ParakeetSTTService
+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, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            ),
+        )
+
+        stt = ParakeetSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
+
+        llm = NimLLMService(
+            api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct"
+        )
+
+        tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,282 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+from dataclasses import dataclass
+
+import aiohttp
+import google.ai.generativelanguage as glm
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import (
+    EndFrame,
+    Frame,
+    InputAudioRawFrame,
+    LLMFullResponseEndFrame,
+    LLMFullResponseStartFrame,
+    StartInterruptionFrame,
+    TextFrame,
+    TranscriptionFrame,
+    UserStartedSpeakingFrame,
+    UserStoppedSpeakingFrame,
+)
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.frame_processor import FrameProcessor
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.google import GoogleLLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+marker = "|----|"
+system_message = f"""
+You are a helpful LLM in a WebRTC call. Your goals are to be helpful and brief in your responses.
+
+You are expert at transcribing audio to text. You will receive a mixture of audio and text input. When
+asked to transcribe what the user said, output an exact, word-for-word transcription.
+
+Your output will be converted to audio so don't include special characters in your answers.
+
+Each time you answer, you should respond in three parts.
+
+1. Transcribe exactly what the user said.
+2. Output the separator field '{marker}'.
+3. Respond to the user's input in a helpful, creative way using only simple text and punctuation.
+
+Example:
+
+User: How many ounces are in a pound?
+
+You: How many ounces are in a pound?
+{marker}
+There are 16 ounces in a pound.
+"""
+
+
+@dataclass
+class MagicDemoTranscriptionFrame(Frame):
+    text: str
+
+
+class UserAudioCollector(FrameProcessor):
+    def __init__(self, context, user_context_aggregator):
+        super().__init__()
+        self._context = context
+        self._user_context_aggregator = user_context_aggregator
+        self._audio_frames = []
+        self._start_secs = 0.2  # this should match VAD start_secs (hardcoding for now)
+        self._user_speaking = False
+
+    async def process_frame(self, frame, direction):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, TranscriptionFrame):
+            # We could gracefully handle both audio input and text/transcription input ...
+            # but let's leave that as an exercise to the reader. :-)
+            return
+        if isinstance(frame, UserStartedSpeakingFrame):
+            self._user_speaking = True
+        elif isinstance(frame, UserStoppedSpeakingFrame):
+            self._user_speaking = False
+            self._context.add_audio_frames_message(audio_frames=self._audio_frames)
+            await self._user_context_aggregator.push_frame(
+                self._user_context_aggregator.get_context_frame()
+            )
+        elif isinstance(frame, InputAudioRawFrame):
+            if self._user_speaking:
+                self._audio_frames.append(frame)
+            else:
+                # Append the audio frame to our buffer. Treat the buffer as a ring buffer, dropping the oldest
+                # frames as necessary. Assume all audio frames have the same duration.
+                self._audio_frames.append(frame)
+                frame_duration = len(frame.audio) / 16 * frame.num_channels / frame.sample_rate
+                buffer_duration = frame_duration * len(self._audio_frames)
+                while buffer_duration > self._start_secs:
+                    self._audio_frames.pop(0)
+                    buffer_duration -= frame_duration
+
+        await self.push_frame(frame, direction)
+
+
+class TranscriptExtractor(FrameProcessor):
+    def __init__(self, context):
+        super().__init__()
+        self._context = context
+        self._accumulator = ""
+        self._processing_llm_response = False
+        self._accumulating_transcript = False
+
+    def reset(self):
+        self._accumulator = ""
+        self._processing_llm_response = False
+        self._accumulating_transcript = False
+
+    async def process_frame(self, frame, direction):
+        await super().process_frame(frame, direction)
+        if isinstance(frame, LLMFullResponseStartFrame):
+            self._processing_llm_response = True
+            self._accumulating_transcript = True
+        elif isinstance(frame, TextFrame) and self._processing_llm_response:
+            if self._accumulating_transcript:
+                text = frame.text
+                split_index = text.find(marker)
+                if split_index < 0:
+                    self._accumulator += frame.text
+                    # do not push this frame
+                    return
+                else:
+                    self._accumulating_transcript = False
+                    self._accumulator += text[:split_index]
+                    frame.text = text[split_index + len(marker) :]
+            await self.push_frame(frame)
+            return
+        elif isinstance(frame, LLMFullResponseEndFrame):
+            await self.push_frame(MagicDemoTranscriptionFrame(text=self._accumulator.strip()))
+            self.reset()
+
+        await self.push_frame(frame, direction)
+
+
+class TanscriptionContextFixup(FrameProcessor):
+    def __init__(self, context):
+        super().__init__()
+        self._context = context
+        self._transcript = "THIS IS A TRANSCRIPT"
+
+    def swap_user_audio(self):
+        if not self._transcript:
+            return
+        message = self._context.messages[-2]
+        last_part = message.parts[-1]
+        if (
+            message.role == "user"
+            and last_part.inline_data
+            and last_part.inline_data.mime_type == "audio/wav"
+        ):
+            self._context.messages[-2] = glm.Content(
+                role="user", parts=[glm.Part(text=self._transcript)]
+            )
+
+    def add_transcript_back_to_inference_output(self):
+        if not self._transcript:
+            return
+        message = self._context.messages[-1]
+        last_part = message.parts[-1]
+        if message.role == "model" and last_part.text:
+            self._context.messages[-1].parts[-1].text += f"\n\n{marker}\n{self._transcript}\n"
+
+    async def process_frame(self, frame, direction):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, MagicDemoTranscriptionFrame):
+            self._transcript = frame.text
+        elif isinstance(frame, LLMFullResponseEndFrame) or isinstance(
+            frame, StartInterruptionFrame
+        ):
+            self.swap_user_audio()
+            self.add_transcript_back_to_inference_output()
+            self._transcript = ""
+
+        await self.push_frame(frame, direction)
+
+
+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,
+                # No transcription at all. just audio input to Gemini!
+                # transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            ),
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = GoogleLLMService(
+            model="gemini-1.5-flash-latest",
+            # model="gemini-exp-1114",
+            api_key=os.getenv("GOOGLE_API_KEY"),
+        )
+
+        messages = [
+            {
+                "role": "system",
+                "content": system_message,
+            },
+            {
+                "role": "user",
+                "content": "Start by saying hello.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+        audio_collector = UserAudioCollector(context, context_aggregator.user())
+        pull_transcript_out_of_llm_output = TranscriptExtractor(context)
+        fixup_context_messages = TanscriptionContextFixup(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                audio_collector,
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                pull_transcript_out_of_llm_output,
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+                fixup_context_messages,
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=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()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,103 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
+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.fish import FishAudioTTSService
+from pipecat.services.openai import OpenAILLMService
+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 = FishAudioTTSService(
+            api_key=os.getenv("FISH_API_KEY"),
+            model="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
+        )
+
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            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.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/08-bots-arguing.py

@@ -1,20 +1,19 @@
-from typing import Tuple
-import aiohttp
 import asyncio
 import logging
 import os
-from pipecat.processors.aggregators import SentenceAggregator
-from pipecat.pipeline.pipeline import Pipeline
+from typing import Tuple
 
-from pipecat.transports.services.daily import DailyTransport
+import aiohttp
+from dotenv import load_dotenv
+from runner import configure
+
+from pipecat.frames.frames import AudioFrame, EndFrame, ImageFrame, LLMMessagesFrame, TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.processors.aggregators import SentenceAggregator
 from pipecat.services.azure import AzureLLMService, AzureTTSService
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.fal import FalImageGenService
-from pipecat.frames.frames import AudioFrame, EndFrame, ImageFrame, LLMMessagesFrame, TextFrame
-
-from runner import configure
-
-from dotenv import load_dotenv
+from pipecat.transports.services.daily import DailyTransport
 
 load_dotenv(override=True)
 

examples/foundational/09-mirror.py

@@ -1,13 +1,17 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import (
     Frame,
     InputAudioRawFrame,
@@ -19,13 +23,7 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.transports.services.daily import DailyTransport, DailyParams
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 

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

@@ -1,15 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import sys
-
 import tkinter as tk
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import (
     Frame,
     InputAudioRawFrame,
@@ -25,12 +28,6 @@ from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.local.tk import TkLocalTransport
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/10-wake-phrase.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -19,12 +23,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/11-sound-effects.py

@@ -1,38 +1,38 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 import wave
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import (
     Frame,
     LLMFullResponseEndFrame,
-    LLMMessagesFrame,
     OutputAudioRawFrame,
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.aggregators.openai_llm_context import (
+    OpenAILLMContext,
+    OpenAILLMContextFrame,
+)
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.logger import FrameLogger
-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
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -72,7 +72,7 @@ class InboundSoundEffectWrapper(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         await super().process_frame(frame, direction)
 
-        if isinstance(frame, LLMMessagesFrame):
+        if isinstance(frame, OpenAILLMContextFrame):
             await self.push_frame(sounds["ding2.wav"])
             # In case anything else downstream needs it
             await self.push_frame(frame, direction)
@@ -98,7 +98,7 @@ async def main():
 
         llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
 
-        tts = CartesiaHttpTTSService(
+        tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
         )

examples/foundational/12-describe-video.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,12 +25,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.moondream import MoondreamService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/12a-describe-video-gemini-flash.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,12 +25,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.google import GoogleLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/12b-describe-video-gpt-4o.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,12 +25,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/12c-describe-video-anthropic.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -17,16 +21,10 @@ from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.user_response import UserResponseAggregator
 from pipecat.processors.aggregators.vision_image_frame import VisionImageFrameAggregator
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.anthropic import AnthropicLLMService
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/13-whisper-transcription.py

@@ -1,13 +1,17 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -16,12 +20,6 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.whisper import WhisperSTTService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -7,6 +7,9 @@
 import asyncio
 import sys
 
+from dotenv import load_dotenv
+from loguru import logger
+
 from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -16,10 +19,6 @@ from pipecat.services.whisper import WhisperSTTService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.local.audio import LocalAudioTransport
 
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/13b-deepgram-transcription.py

@@ -1,28 +1,26 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.services.deepgram import DeepgramSTTService, LiveOptions, Language
+from pipecat.services.deepgram import DeepgramSTTService, Language, LiveOptions
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/13c-gladia-transcription.py

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

examples/foundational/13d-assemblyai-transcription.py

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

examples/foundational/14-function-calling.py

@@ -1,14 +1,19 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 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.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -17,14 +22,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMContext, OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from openai.types.chat import ChatCompletionToolParam
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,29 +1,27 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 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.cartesia import CartesiaTTSService
 from pipecat.services.anthropic import AnthropicLLMService
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,29 +1,27 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 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.cartesia import CartesiaTTSService
 from pipecat.services.anthropic import AnthropicLLMService
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -67,7 +65,8 @@ async def main():
 
         llm = AnthropicLLMService(
             api_key=os.getenv("ANTHROPIC_API_KEY"),
-            model="claude-3-5-sonnet-20240620",
+            # model="claude-3-5-sonnet-20240620",
+            model="claude-3-5-sonnet-latest",
             enable_prompt_caching_beta=True,
         )
         llm.register_function("get_weather", get_weather)

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

@@ -1,14 +1,19 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 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.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -18,14 +23,6 @@ from pipecat.services.openai import OpenAILLMContext
 from pipecat.services.together import TogetherLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from openai.types.chat import ChatCompletionToolParam
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -125,7 +122,7 @@ async def main():
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
-            # await tts.say("Hi! Ask me about the weather in San Francisco.")
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         runner = PipelineRunner()
 

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

@@ -1,14 +1,19 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 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.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -17,14 +22,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMContext, OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from openai.types.chat import ChatCompletionToolParam
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -18,12 +22,6 @@ from pipecat.services.google import GoogleLLMService
 from pipecat.services.openai import OpenAILLMContext
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -64,7 +62,11 @@ async def main():
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
         )
 
-        llm = GoogleLLMService(model="gemini-1.5-flash-latest", api_key=os.getenv("GOOGLE_API_KEY"))
+        llm = GoogleLLMService(
+            model="gemini-1.5-flash-latest",
+            # model="gemini-exp-1114",
+            api_key=os.getenv("GOOGLE_API_KEY"),
+        )
         llm.register_function("get_weather", get_weather)
         llm.register_function("get_image", get_image)
 
@@ -151,7 +153,6 @@ indicate you should use the get_image tool are:
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
             ),
         )
 

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

@@ -0,0 +1,139 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+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.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.openai import OpenAILLMContext
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def start_fetch_weather(function_name, llm, context):
+    # note: we can't push a frame to the LLM here. the bot
+    # can interrupt itself and/or cause audio overlapping glitches.
+    # possible question for Aleix and Chad about what the right way
+    # to trigger speech is, now, with the new queues/async/sync refactors.
+    # await llm.push_frame(TextFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+    await result_callback({"conditions": "nice", "temperature": "75"})
+
+
+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 = GroqLLMService(
+            api_key=os.getenv("GROQ_API_KEY"), model="llama3-groq-70b-8192-tool-use-preview"
+        )
+        # 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)
+
+        tools = [
+            ChatCompletionToolParam(
+                type="function",
+                function={
+                    "name": "get_current_weather",
+                    "description": "Get the current weather",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "location": {
+                                "type": "string",
+                                "description": "The city and state, e.g. San Francisco, CA",
+                            },
+                            "unit": {
+                                "type": "string",
+                                "enum": ["celsius", "fahrenheit"],
+                                "description": "The temperature unit to use. Infer this from the users location.",
+                            },
+                        },
+                        "required": ["location"],
+                    },
+                },
+            )
+        ]
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=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/14g-function-calling-grok.py

@@ -0,0 +1,137 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+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.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.grok import GrokLLMService
+from pipecat.services.openai import OpenAILLMContext
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def start_fetch_weather(function_name, llm, context):
+    # note: we can't push a frame to the LLM here. the bot
+    # can interrupt itself and/or cause audio overlapping glitches.
+    # possible question for Aleix and Chad about what the right way
+    # to trigger speech is, now, with the new queues/async/sync refactors.
+    # await llm.push_frame(TextFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+    await result_callback({"conditions": "nice", "temperature": "75"})
+
+
+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 = GrokLLMService(api_key=os.getenv("GROK_API_KEY"))
+        # 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)
+
+        tools = [
+            ChatCompletionToolParam(
+                type="function",
+                function={
+                    "name": "get_current_weather",
+                    "description": "Get the current weather",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "location": {
+                                "type": "string",
+                                "description": "The city and state, e.g. San Francisco, CA",
+                            },
+                            "format": {
+                                "type": "string",
+                                "enum": ["celsius", "fahrenheit"],
+                                "description": "The temperature unit to use. Infer this from the users location.",
+                            },
+                        },
+                        "required": ["location", "format"],
+                    },
+                },
+            )
+        ]
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=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/14h-function-calling-azure.py

@@ -0,0 +1,141 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+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.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.services.azure import AzureLLMService
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMContext
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def start_fetch_weather(function_name, llm, context):
+    # note: we can't push a frame to the LLM here. the bot
+    # can interrupt itself and/or cause audio overlapping glitches.
+    # possible question for Aleix and Chad about what the right way
+    # to trigger speech is, now, with the new queues/async/sync refactors.
+    # await llm.push_frame(TextFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+    await result_callback({"conditions": "nice", "temperature": "75"})
+
+
+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 = AzureLLMService(
+            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+            model=os.getenv("AZURE_CHATGPT_MODEL"),
+        )
+        # 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)
+
+        tools = [
+            ChatCompletionToolParam(
+                type="function",
+                function={
+                    "name": "get_current_weather",
+                    "description": "Get the current weather",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "location": {
+                                "type": "string",
+                                "description": "The city and state, e.g. San Francisco, CA",
+                            },
+                            "format": {
+                                "type": "string",
+                                "enum": ["celsius", "fahrenheit"],
+                                "description": "The temperature unit to use. Infer this from the users location.",
+                            },
+                        },
+                        "required": ["location", "format"],
+                    },
+                },
+            )
+        ]
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=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/14i-function-calling-fireworks.py

@@ -0,0 +1,140 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+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.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.fireworks import FireworksLLMService
+from pipecat.services.openai import OpenAILLMContext
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def start_fetch_weather(function_name, llm, context):
+    # note: we can't push a frame to the LLM here. the bot
+    # can interrupt itself and/or cause audio overlapping glitches.
+    # possible question for Aleix and Chad about what the right way
+    # to trigger speech is, now, with the new queues/async/sync refactors.
+    # await llm.push_frame(TextFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+    await result_callback({"conditions": "nice", "temperature": "75"})
+
+
+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 = FireworksLLMService(
+            api_key=os.getenv("FIREWORKS_API_KEY"),
+            model="accounts/fireworks/models/firefunction-v2",
+        )
+        # 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)
+
+        tools = [
+            ChatCompletionToolParam(
+                type="function",
+                function={
+                    "name": "get_current_weather",
+                    "description": "Get the current weather",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "location": {
+                                "type": "string",
+                                "description": "The city and state, e.g. San Francisco, CA",
+                            },
+                            "format": {
+                                "type": "string",
+                                "enum": ["celsius", "fahrenheit"],
+                                "description": "The temperature unit to use. Infer this from the users location.",
+                            },
+                        },
+                        "required": ["location", "format"],
+                    },
+                },
+            )
+        ]
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=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/14j-function-calling-nim.py

@@ -0,0 +1,140 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+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.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.nim import NimLLMService
+from pipecat.services.openai import OpenAILLMContext
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def start_fetch_weather(function_name, llm, context):
+    # note: we can't push a frame to the LLM here. the bot
+    # can interrupt itself and/or cause audio overlapping glitches.
+    # possible question for Aleix and Chad about what the right way
+    # to trigger speech is, now, with the new queues/async/sync refactors.
+    # await llm.push_frame(TextFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+    await result_callback({"conditions": "nice", "temperature": "75"})
+
+
+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
+            # text_filter=MarkdownTextFilter(),
+        )
+
+        llm = NimLLMService(
+            api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.3-70b-instruct"
+        )
+        # 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)
+
+        tools = [
+            ChatCompletionToolParam(
+                type="function",
+                function={
+                    "name": "get_current_weather",
+                    "description": "Returns the current weather at a location, if one is specified, and defaults to the user's location.",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "location": {
+                                "type": "string",
+                                "description": "The location to find the weather of, or if not provided, it's the default location.",
+                            },
+                            "format": {
+                                "type": "string",
+                                "enum": ["celsius", "fahrenheit"],
+                                "description": "Whether to use SI or USCS units (celsius or fahrenheit).",
+                            },
+                        },
+                        "required": ["location", "format"],
+                    },
+                },
+            )
+        ]
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=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())