Update comment

Fixed an issue that `start_callback` was not invoked for some LLM services

.github/workflows/coverage.yaml

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

.gitignore

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

CHANGELOG.md

@@ -5,10 +5,193 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## Unreleased
+
+### Added
+
+- Added `room_url` property to `DailyTransport`.
+
+- Added `addons` argument to `DeepgramSTTService`.
+
+- Added `exponential_backoff_time()` to `utils.network` module.
+
+### Changed
+
+- `DeepgramSTTService` now uses the new `nova-3` model by default. If you want
+  to use the previous model you can pass `LiveOptions(model="nova-2-general")`.
+  (see https://deepgram.com/learn/introducing-nova-3-speech-to-text-api)
+
+```python
+stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
+```
+
+### Fixed
+
+- Fixed an issue that `start_callback` was not invoked for some LLM services.
+
+- Fixed an issue that would cause `DeepgramSTTService` to stop working after an
+  error occurred (e.g. sudden network loss). If the network recovered we would
+  not reconnect.
+
+- Fixed a `STTMuteFilter` issue that would not mute user audio frames causing
+  transcriptions to be generated by the STT service.
+
+### Other
+
+- Added Gemini support to `examples/phone-chatbot`.
+
+## [0.0.57] - 2025-02-14
+
+### Added
+
+- Added new `AudioContextWordTTSService`. This is a TTS base class for TTS
+  services that handling multiple separate audio requests.
+
+- Added new frames `EmulateUserStartedSpeakingFrame` and
+  `EmulateUserStoppedSpeakingFrame` which can be used to emulated VAD behavior
+  without VAD being present or not being triggered.
+
+- Added a new `audio_in_stream_on_start` field to `TransportParams`.
+
+- Added a new method `start_audio_in_streaming` in the `BaseInputTransport`.
+
+  - This method should be used to start receiving the input audio in case the
+    field `audio_in_stream_on_start` is set to `false`.
+
+- Added support for the `RTVIProcessor` to handle buffered audio in `base64`
+  format, converting it into InputAudioRawFrame for transport.
+
+- Added support for the `RTVIProcessor` to trigger `start_audio_in_streaming`
+  only after the `client-ready` message.
+
+- Added new `MUTE_UNTIL_FIRST_BOT_COMPLETE` strategy to `STTMuteStrategy`. This
+  strategy starts muted and remains muted until the first bot speech completes,
+  ensuring the bot's first response cannot be interrupted. This complements the
+  existing `FIRST_SPEECH` strategy which only mutes during the first detected
+  bot speech.
+
+- Added support for Google Cloud Speech-to-Text V2 through `GoogleSTTService`.
+
+- Added `RimeTTSService`, a new `WordTTSService`. Updated the foundational
+  example `07q-interruptible-rime.py` to use `RimeTTSService`.
+
+- Added support for Groq's Whisper API through the new `GroqSTTService` and
+  OpenAI's Whisper API through the new `OpenAISTTService`. Introduced a new
+  base class `BaseWhisperSTTService` to handle common Whisper API
+  functionality.
+
+- Added `PerplexityLLMService` for Perplexity NIM API integration, with an
+  OpenAI-compatible interface. Also, added foundational example
+  `14n-function-calling-perplexity.py`.
+
+- Added `DailyTransport.update_remote_participants()`. This allows you to update
+  remote participant's settings, like their permissions or which of their
+  devices are enabled. Requires that the local participant have participant
+  admin permission.
+
+### Changed
+
+- We don't consider a colon `:` and end of sentence any more.
+
+- Updated `DailyTransport` to respect the `audio_in_stream_on_start` field,
+  ensuring it only starts receiving the audio input if it is enabled.
+
+- Updated `FastAPIWebsocketOutputTransport` to send `TransportMessageFrame` and
+  `TransportMessageUrgentFrame` to the serializer.
+
+- Updated `WebsocketServerOutputTransport` to send `TransportMessageFrame` and
+  `TransportMessageUrgentFrame` to the serializer.
+
+- Enhanced `STTMuteConfig` to validate strategy combinations, preventing
+  `MUTE_UNTIL_FIRST_BOT_COMPLETE` and `FIRST_SPEECH` from being used together
+  as they handle first bot speech differently.
+
+- Updated foundational example `07n-interruptible-google.py` to use all Google
+  services.
+
+- `RimeHttpTTSService` now uses the `mistv2` model by default.
+
+- Improved error handling in `AzureTTSService` to properly detect and log
+  synthesis cancellation errors.
+
+- Enhanced `WhisperSTTService` with full language support and improved model
+  documentation.
+
+- Updated foundation example `14f-function-calling-groq.py` to use
+  `GroqSTTService` for transcription.
+
+- Updated `GroqLLMService` to use `llama-3.3-70b-versatile` as the default
+  model.
+
+- `RTVIObserver` doesn't handle `LLMSearchResponseFrame` frames anymore. For
+  now, to handle those frames you need to create a `GoogleRTVIObserver`
+  instead.
+
+### Deprecated
+
+- `STTMuteFilter` constructor's `stt_service` parameter is now deprecated and
+  will be removed in a future version. The filter now manages mute state
+  internally instead of querying the STT service.
+
+- `RTVI.observer()` is now deprecated, instantiate an `RTVIObserver` directly
+  instead.
+
+- All RTVI frame processors (e.g. `RTVISpeakingProcessor`,
+  `RTVIBotLLMProcessor`) are now deprecated, instantiate an `RTVIObserver`
+  instead.
+
+### Fixed
+
+- Fixed a `FalImageGenService` issue that was causing the event loop to be
+  blocked while loading the downloadded image.
+
+- Fixed a `CartesiaTTSService` service issue that would cause audio overlapping
+  in some cases.
+
+- Fixed a websocket-based service issue (e.g. `CartesiaTTSService`) that was
+  preventing a reconnection after the server disconnected cleanly, which was
+  causing an inifite loop instead.
+
+- Fixed a `BaseOutputTransport` issue that was causing upstream frames to no be
+  pushed upstream.
+
+- Fixed multiple issue where user transcriptions where not being handled
+  properly. It was possible for short utterances to not trigger VAD which would
+  cause user transcriptions to be ignored. It was also possible for one or more
+  transcriptions to be generated after VAD in which case they would also be
+  ignored.
+
+- Fixed an issue that was causing `BotStoppedSpeakingFrame` to be generated too
+  late. This could then cause issues unblocking `STTMuteFilter` later than
+  desired.
+
+- Fixed an issue that was causing `AudioBufferProcessor` to not record
+  synchronized audio.
+
+- Fixed an `RTVI` issue that was causing `bot-tts-text` messages to be sent
+  before being processed by the output transport.
+
+- Fixed an issue[#1192] in 11labs where we are trying to reconnect/disconnect
+  the websocket connection even when the connection is already closed.
+
+- Fixed an issue where `has_regular_messages` condition was always true in
+  `GoogleLLMContext` due to `Part` having `function_call` & `function_response`
+  with `None` values.
+
+### Other
+
+- Added new `instant-voice` example. This example showcases how to enable
+  instant voice communication as soon as a user connects.
+
+- Added new `local-input-select-stt` example. This examples allows you to play
+  with local audio inputs by slecting them through a nice text interface.
+
 ## [0.0.56] - 2025-02-06
 
 ### Changed
 
+- Use `gemini-2.0-flash-001` as the default model for `GoogleLLMSerivce`.
+
 - Improved foundational examples 22b, 22c, and 22d to support function calling.
   With these base examples, `FunctionCallInProgressFrame` and
   `FunctionCallResultFrame` will no longer be blocked by the gates.
@@ -22,7 +205,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   logging setup.
 
 - Fixed a `SentryMetrics` issue that was preventing any metrics to be sent to
-  Sentry and also was preventing from metrics frames to be pushed to the pipeline.
+  Sentry and also was preventing from metrics frames to be pushed to the
+  pipeline.
 
 - Fixed an issue in `BaseOutputTransport` where incoming audio would not be
   resampled to the desired output sample rate.
@@ -33,10 +217,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   and should be set manually from the serializer constructor if a different
   value is needed.
 
-### Changed
-
-- Use `gemini-2.0-flash-001` as the default model for `GoogleLLMSerivce`.
-
 ### Other
 
 - Added a new `sentry-metrics` example.
@@ -119,7 +299,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - `AudioBufferProcessor.reset_audio_buffers()` has been removed, use
   `AudioBufferProcessor.start_recording()` and
-  ``AudioBufferProcessor.stop_recording()` instead.
+  `AudioBufferProcessor.stop_recording()` instead.
 
 ### Fixed
 
@@ -185,7 +365,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - Added `enable_recording` and `geo` parameters to `DailyRoomProperties`.
 
-- Added `RecordingsBucketConfig` to `DailyRoomProperties` to upload recordings to a custom AWS bucket.
+- Added `RecordingsBucketConfig` to `DailyRoomProperties` to upload recordings
+  to a custom AWS bucket.
 
 ### Changed
 

README.md

@@ -2,7 +2,7 @@
  <img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
 </div></h1>
 
-[![PyPI](https://img.shields.io/pypi/v/pipecat-ai)](https://pypi.org/project/pipecat-ai) ![Tests](https://github.com/pipecat-ai/pipecat/actions/workflows/tests.yaml/badge.svg) [![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.pipecat.ai) [![Discord](https://img.shields.io/discord/1239284677165056021)](https://discord.gg/pipecat) <a href="https://app.commanddash.io/agent/github_pipecat-ai_pipecat"><img src="https://img.shields.io/badge/AI-Code%20Agent-EB9FDA"></a>
+[![PyPI](https://img.shields.io/pypi/v/pipecat-ai)](https://pypi.org/project/pipecat-ai) ![Tests](https://github.com/pipecat-ai/pipecat/actions/workflows/tests.yaml/badge.svg) [![codecov](https://codecov.io/gh/pipecat-ai/pipecat/graph/badge.svg?token=LNVUIVO4Y9)](https://codecov.io/gh/pipecat-ai/pipecat) [![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.pipecat.ai) [![Discord](https://img.shields.io/discord/1239284677165056021)](https://discord.gg/pipecat)
 
 Pipecat is an open source Python framework for building voice and multimodal conversational agents. It handles the complex orchestration of AI services, network transport, audio processing, and multimodal interactions, letting you focus on creating engaging experiences.
 
@@ -55,17 +55,17 @@ pip install "pipecat-ai[option,...]"
 
 ### Available services
 
-| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | Install Command Example                 |
-| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                                                                                                                                                                                                                            | `pip install "pipecat-ai[deepgram]"`    |
-| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | `pip install "pipecat-ai[openai]"`      |
-| Text-to-Speech      | [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                              | `pip install "pipecat-ai[cartesia]"`    |
-| Speech-to-Speech    | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | `pip install "pipecat-ai[openai]"`      |
-| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `pip install "pipecat-ai[daily]"`       |
-| Video               | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | `pip install "pipecat-ai[tavus,simli]"` |
-| Vision & Image      | [Moondream](https://docs.pipecat.ai/server/services/vision/moondream), [fal](https://docs.pipecat.ai/server/services/image-generation/fal)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | `pip install "pipecat-ai[moondream]"`   |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[silero]"`      |
-| Analytics & Metrics | [Canonical AI](https://docs.pipecat.ai/server/services/analytics/canonical), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | `pip install "pipecat-ai[canonical]"`   |
+| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | Install Command Example                 |
+| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[deepgram]"`    |
+| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | `pip install "pipecat-ai[openai]"`      |
+| Text-to-Speech      | [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                                                                                                                                                                          | `pip install "pipecat-ai[cartesia]"`    |
+| Speech-to-Speech    | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | `pip install "pipecat-ai[google]"`      |
+| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      | `pip install "pipecat-ai[daily]"`       |
+| Video               | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[tavus,simli]"` |
+| Vision & Image      | [Moondream](https://docs.pipecat.ai/server/services/vision/moondream), [fal](https://docs.pipecat.ai/server/services/image-generation/fal)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[moondream]"`   |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `pip install "pipecat-ai[silero]"`      |
+| Analytics & Metrics | [Canonical AI](https://docs.pipecat.ai/server/services/analytics/canonical), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | `pip install "pipecat-ai[canonical]"`   |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 
@@ -149,36 +149,40 @@ Sign up [here](https://dashboard.daily.co/u/signup) and [create a room](https://
 
 ## Hacking on the framework itself
 
-_Note that you may need to set up a virtual environment before following the instructions below. For instance, you might need to run the following from the root of the repo:_
+_Note: You may need to set up a virtual environment before following these instructions. From the root of the repo:_
 
 ```shell
 python3 -m venv venv
 source venv/bin/activate
 ```
 
-From the root of this repo, run the following:
+Install the development dependencies:
 
 ```shell
 pip install -r dev-requirements.txt
 ```
 
-This will install the necessary development dependencies. Also, make sure you install the git pre-commit hooks:
+Install the git pre-commit hooks (these help ensure your code follows project rules):
 
 ```shell
 pre-commit install
 ```
 
-The hooks will just save you time when you submit a PR by making sure your code follows the project rules.
-
-To use the package locally (e.g. to run sample files), run:
+Install the `pipecat-ai` package locally in editable mode:
 
 ```shell
-pip install --editable ".[option,...]"
+pip install -e .
 ```
 
-The `--editable` option makes sure you don't have to run `pip install` again and you can just edit the project files locally.
+The `-e` or `--editable` option allows you to modify the code without reinstalling.
 
-If you want to use this package from another directory, you can run:
+To include optional dependencies, add them to the install command. For example:
+
+```shell
+pip install -e ".[daily,deepgram,cartesia,openai,silero]"     # Updated for the services you're using
+```
+
+If you want to use this package from another directory:
 
 ```shell
 pip install "path_to_this_repo[option,...]"

codecov.yml

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

dev-requirements.txt

@@ -1,11 +1,12 @@
 build~=1.2.2
+coverage~=7.6.12
 grpcio-tools~=1.67.1
 pip-tools~=7.4.1
 pre-commit~=4.0.1
-pyright~=1.1.392
+pyright~=1.1.393
 pytest~=8.3.4
 pytest-asyncio~=0.25.2
-ruff~=0.9.1
+ruff~=0.9.5
 setuptools~=70.0.0
 setuptools_scm~=8.1.0
 python-dotenv~=1.0.1

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

@@ -27,7 +27,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.services.cartesia import CartesiaHttpTTSService
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
@@ -91,7 +91,7 @@ async def main():
             ),
         )
 
-        tts = CartesiaHttpTTSService(
+        tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
         )

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

@@ -18,7 +18,7 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.openai import OpenAILLMService, OpenAITTSService
+from pipecat.services.openai import OpenAILLMService, OpenAISTTService, OpenAITTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -37,12 +37,22 @@ async def main():
             "Respond bot",
             DailyParams(
                 audio_out_enabled=True,
-                transcription_enabled=True,
+                audio_out_sample_rate=24000,
+                transcription_enabled=False,
                 vad_enabled=True,
                 vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
             ),
         )
 
+        # You can use the OpenAI compatible API like Groq.
+        # stt = OpenAISTTService(
+        #     base_url="https://api.groq.com/openai/v1",
+        #     api_key="gsk_***",
+        #     model="whisper-large-v3",
+        # )
+        stt = OpenAISTTService(api_key=os.getenv("OPENAI_API_KEY"), model="whisper-1")
+
         tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="alloy")
 
         llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
@@ -60,6 +70,7 @@ async def main():
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
+                stt,  # STT
                 context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS

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

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

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

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

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

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

examples/foundational/14-function-calling.py

@@ -29,14 +29,22 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")
 
 
-async def start_fetch_weather(function_name, llm, context):
+async def start_fetch_products(function_name, llm, context):
     """Push a frame to the LLM; this is handy when the LLM response might take a while."""
-    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
-    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+    await llm.push_frame(TTSSpeakFrame("I'll take a look!"))
+    logger.debug(f"Starting fetch_products_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 fetch_products_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+    logger.debug(f"args for fetch_products_from_api: {args}")
+    # In the real world you'd fetch the products from an API. We're hardcoding them here.
+    product = args["product"]
+    if product == "vacuums":
+        await result_callback({"vacuums": ["Dyson V11", "Roomba i7"]})
+    elif product == "tvs":
+        await result_callback({"tvs": ["Samsung 65 inch", "LG 55 inch"]})
+    else:
+        await result_callback({"error": "Unknown product"})
 
 
 async def main():
@@ -63,28 +71,24 @@ async def main():
         llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
         # 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)
+        llm.register_function(None, fetch_products_from_api, start_callback=start_fetch_products)
 
         tools = [
             ChatCompletionToolParam(
                 type="function",
                 function={
-                    "name": "get_current_weather",
-                    "description": "Get the current weather",
+                    "name": "get_products",
+                    "description": "Get the list of products available.",
                     "parameters": {
                         "type": "object",
                         "properties": {
-                            "location": {
+                            "product": {
                                 "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.",
-                            },
+                                "enum": ["vacuums", "tvs"],
+                                "description": "The type of product to show.",
+                            }
                         },
-                        "required": ["location", "format"],
+                        "required": ["product"],
                     },
                 },
             )
@@ -92,7 +96,7 @@ async def main():
         messages = [
             {
                 "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+                "content": "You are a helpful customer service agent named Hailey in a video call. Your goal is to sell vacuums or tvs. 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.",
             },
         ]
 

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

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

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

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

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

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

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

@@ -497,7 +497,7 @@ class UserAggregatorBuffer(LLMResponseAggregator):
         if isinstance(frame, UserStartedSpeakingFrame):
             self._transcription = ""
 
-    async def _push_aggregation(self):
+    async def push_aggregation(self):
         if self._aggregation:
             self._transcription = self._aggregation
             self._aggregation = ""

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

@@ -61,9 +61,11 @@ async def main():
         stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
         # Configure the mute processor with both strategies
         stt_mute_processor = STTMuteFilter(
-            stt_service=stt,
             config=STTMuteConfig(
-                strategies={STTMuteStrategy.FIRST_SPEECH, STTMuteStrategy.FUNCTION_CALL}
+                strategies={
+                    STTMuteStrategy.MUTE_UNTIL_FIRST_BOT_COMPLETE,
+                    STTMuteStrategy.FUNCTION_CALL,
+                }
             ),
         )
 

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

@@ -143,7 +143,14 @@ class InputTranscriptionContextFilter(FrameProcessor):
             return
 
         try:
-            message = frame.context.messages[-1]
+            # Make sure we're working with a GoogleLLMContext
+            context = GoogleLLMContext.upgrade_to_google(frame.context)
+            message = context.messages[-1]
+
+            if not isinstance(message, glm.Content):
+                logger.error(f"Expected glm.Content, got {type(message)}")
+                return
+
             last_part = message.parts[-1]
             if not (
                 message.role == "user"

examples/foundational/28c-transcription-processor-gemini.py

@@ -6,6 +6,7 @@
 
 import asyncio
 import os
+import sqlite3
 import sys
 from typing import List, Optional
 
@@ -44,22 +45,33 @@ class TranscriptHandler:
         output_file: Optional path to file where transcript is saved. If None, outputs to log only.
     """
 
-    def __init__(self, output_file: Optional[str] = None):
-        """Initialize handler with optional file output.
+    def __init__(self, output_file: Optional[str] = None, output_db: Optional[str] = None):
+        """Initialize handler with optional file or database output.
 
         Args:
             output_file: Path to output file. If None, outputs to log only.
         """
         self.messages: List[TranscriptionMessage] = []
         self.output_file: Optional[str] = output_file
+        self.output_db: Optional[str] = output_db
+
+        if self.output_db:
+            self.con = sqlite3.connect("example.db")
+            self.db = self.con.cursor()
+
+            table = self.db.execute("SELECT name FROM sqlite_master WHERE name='messages'")
+            if not (table.fetchone()):
+                self.db.execute(
+                    "CREATE TABLE messages(role TEXT, content TEXT, timestamp DATETIME DEFAULT CURRENT_TIMESTAMP )"
+                )
         logger.debug(
-            f"TranscriptHandler initialized {'with output_file=' + output_file if output_file else 'with log output only'}"
+            f"TranscriptHandler initialized; output file: {output_file}, output DB: {output_db}"
         )
 
     async def save_message(self, message: TranscriptionMessage):
         """Save a single transcript message.
 
-        Outputs the message to the log and optionally to a file.
+        Outputs the message to the log and optionally to a SQLite database or file.
 
         Args:
             message: The message to save
@@ -78,6 +90,14 @@ class TranscriptHandler:
             except Exception as e:
                 logger.error(f"Error saving transcript message to file: {e}")
 
+        # and/or to a SQLite database
+        if self.output_db:
+            self.db.execute(
+                "INSERT INTO messages VALUES (?, ?, ?)",
+                (message.role, message.content, message.timestamp),
+            )
+            self.con.commit()
+
     async def on_transcript_update(
         self, processor: TranscriptProcessor, frame: TranscriptionUpdateFrame
     ):
@@ -136,8 +156,11 @@ async def main():
 
         # Create transcript processor and handler
         transcript = TranscriptProcessor()
+        # Select a TranscriptHandler output method
+        # Uncomment out only one of the following lines:
         transcript_handler = TranscriptHandler()  # Output to log only
         # transcript_handler = TranscriptHandler(output_file="transcript.txt") # Output to file and log
+        # transcript_handler = TranscriptHandler(output_db="example.db")  # Output to SQLite DB and log
 
         pipeline = Pipeline(
             [

examples/foundational/32-gemini-grounding-metadata.py

@@ -89,6 +89,7 @@ async def main():
             api_key=os.getenv("GOOGLE_API_KEY"),
             system_instruction=system_instruction,
             tools=tools,
+            model="gemini-1.5-flash-002",
         )
 
         context = OpenAILLMContext(

examples/foundational/33-gemini-rag.py

@@ -0,0 +1,254 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+"""CrossFit Games 2025 Rulebook RAG Demo.
+
+This example demonstrates a Model-Assisted Generation (MAG) chatbot using Google's Gemini model.
+This example uses 2 Gemini models:
+- Gemini 2.0 Flash: This is the voice model that is used to generate the response.
+- Gemini 2.0 Flash Lite: This is the model that is used to answer questions about the CrossFit Games 2025 rulebook - information that isn't yet publicly
+indexed by Gemini (or any other LLM).
+
+How it works:
+- The voice model (Gemini 2.0 Flash) is configured to call a function whenever the user asks a question.
+- The function call is a tool call to the MAG model (Gemini 2.0 Flash Lite).
+- The MAG model generates a response based on the question. The MAG model has the entire contents of the CrossFit Games 2025 rulebook in it's context window.
+- The response is returned to the voice model (Gemini 2.0 Flash), which then generates the response to the user.
+
+Why this works:
+- Gemini 2.0 Flash is fast
+- Gemini 2.0 Flash Lite is faster
+- Gemini 2.0 Flash Lite has a large (1 million tokens) context window
+- IMPORTANT: The generated response from Gemini 2.0 Flash Lite is limited to 50 words or less and 64 tokens.
+You can see this in the RAG_PROMPT variable and the generation_config in the query_knowledge_base function.
+Long generations are slower and more expensive, in the world of Voice AI, we don't need long generations.
+
+Example questions to ask and compare to other RAG solutions:
+- What lenses are not allowed?
+- How many people can be on a team?
+- What do winning gyms get?
+- What happens if I skip a workout?
+- Can I switch my team members for the Games?
+- What happens if I start too early?
+
+Notes:
+- The RAG model is Gemini 2.0 Flash Lite.
+- The voice model is Gemini 2.0 Flash.
+- The RAG content is stored in the assets/rag-content.txt file.
+- The model for voice is Gemini 2.0 Flash, but can be easily switched to any other model.
+
+Customization options:
+- update assets/rag-content.txt with your own knowledge base
+- increase/decrease the RAG_MODEL's generation length
+- use a different voice model
+- play with the RAG_PROMPT
+- change the function calling logic
+"""
+
+import asyncio
+import json
+import os
+import sys
+import time
+
+import aiohttp
+import google.generativeai as genai
+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.services.cartesia import CartesiaTTSService
+from pipecat.services.google import GoogleLLMService
+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="INFO")
+
+video_participant_id = None
+
+
+def get_rag_content():
+    """Get the RAG content from the file."""
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+    rag_content_path = os.path.join(script_dir, "assets", "rag-content.txt")
+    with open(rag_content_path, "r") as f:
+        return f.read()
+
+
+RAG_MODEL = "gemini-2.0-flash-lite-preview-02-05"
+VOICE_MODEL = "gemini-2.0-flash"
+RAG_CONTENT = get_rag_content()
+RAG_PROMPT = f"""
+You are a helpful assistant designed to answer user questions based solely on the provided knowledge base.
+
+**Instructions:**
+
+1.  **Knowledge Base Only:** Answer questions *exclusively* using the information in the "Knowledge Base" section below. Do not use any outside information.
+2.  **Conversation History:** Use the "Conversation History" (ordered oldest to newest) to understand the context of the current question.
+3.  **Concise Response:**  Respond in 50 words or fewer.  The response will be spoken, so avoid symbols, abbreviations, or complex formatting. Use plain, natural language.
+4.  **Unknown Answer:** If the answer is not found within the "Knowledge Base," respond with "I don't know." Do not guess or make up an answer.
+5. Do not introduce your response. Just provide the answer.
+6. You must follow all instructions.
+
+**Input Format:**
+
+Each request will include:
+
+*   **Conversation History:**  (A list of previous user and assistant messages, if any)
+
+**Knowledge Base:**
+Here is the knowledge base you have access to:
+{RAG_CONTENT}
+"""
+genai.configure(api_key=os.environ["GOOGLE_API_KEY"])
+
+
+async def query_knowledge_base(
+    function_name, tool_call_id, arguments, llm, context, result_callback
+):
+    """Query the knowledge base for the answer to the question."""
+    logger.info(f"Querying knowledge base for question: {arguments['question']}")
+    client = genai.GenerativeModel(
+        model_name=RAG_MODEL,
+        system_instruction=RAG_PROMPT,
+        generation_config=genai.types.GenerationConfig(
+            temperature=0.1,
+            max_output_tokens=64,
+        ),
+    )
+    # for our case, the first two messages are the instructions and the user message
+    # so we remove them.
+    conversation_turns = context.messages[2:]
+    # convert to standard messages
+    messages = []
+    for turn in conversation_turns:
+        messages.extend(context.to_standard_messages(turn))
+
+    def _is_tool_call(turn):
+        if turn.get("role", None) == "tool":
+            return True
+        if turn.get("tool_calls", None):
+            return True
+        return False
+
+    # filter out tool calls
+    messages = [turn for turn in messages if not _is_tool_call(turn)]
+    # use the last 3 turns as the conversation history/context
+    messages = messages[-3:]
+    messages_json = json.dumps(messages, ensure_ascii=False, indent=2)
+
+    logger.info(f"Conversation turns: {messages_json}")
+
+    start = time.perf_counter()
+    response = client.generate_content(
+        contents=[messages_json],
+    )
+    end = time.perf_counter()
+    logger.info(f"Time taken: {end - start:.2f} seconds")
+    logger.info(response.text)
+    await result_callback(response.text)
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Gemini RAG 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="f9836c6e-a0bd-460e-9d3c-f7299fa60f94",  # Southern Lady
+        )
+
+        llm = GoogleLLMService(
+            model=VOICE_MODEL,
+            api_key=os.getenv("GOOGLE_API_KEY"),
+        )
+        llm.register_function("query_knowledge_base", query_knowledge_base)
+        tools = [
+            {
+                "function_declarations": [
+                    {
+                        "name": "query_knowledge_base",
+                        "description": "Query the knowledge base for the answer to the question.",
+                        "parameters": {
+                            "type": "object",
+                            "properties": {
+                                "question": {
+                                    "type": "string",
+                                    "description": "The question to query the knowledge base with.",
+                                },
+                            },
+                        },
+                    },
+                ],
+            },
+        ]
+        system_prompt = """\
+You are a helpful assistant who converses with a user and answers questions.
+
+You have access to the tool, query_knowledge_base, that allows you to query the knowledge base for the answer to the user's question.
+
+Your response will be turned into speech so use only simple words and punctuation.
+"""
+        messages = [
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": "Greet the user."},
+        ]
+
+        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):
+            global video_participant_id
+            video_participant_id = participant["id"]
+            await transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_video(video_participant_id, framerate=0)
+            # 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/instant-voice/.gitignore

@@ -0,0 +1,7 @@
+venv
+.idea
+server/.env
+client/javascript/node_modules
+client/javascript/.vite
+bkp
+

examples/instant-voice/README.md

@@ -0,0 +1,55 @@
+# Instant Voice
+
+This demo showcases how to enable instant voice communication as soon as a user connects.
+By leveraging optimizations on both the server and client sides, users can start speaking immediately after pressing the connect button.
+
+## How It Works
+
+### Server-Side Improvements:
+- A **pool of Daily rooms** is managed to ensure quick connections.
+- When a user connects, an existing room from the pool is assigned.
+- A new room is created asynchronously to maintain the predefined pool size.
+
+### Client-Side Improvements:
+- Using the **DailyTransport** property `bufferLocalAudioUntilBotReady` set to enabled, users can start speaking immediately
+  upon receiving the `AUDIO_BUFFERING_STARTED` event (typically within ~1s).
+- This allows users to speak even before the bot is fully ready or the WebRTC connection is fully established.
+
+## Quick Start
+
+### 1. Start the Bot Server
+
+1. Navigate to the server directory:
+   ```bash
+   cd server
+   ```
+2. Create and activate a virtual environment:
+   ```bash
+   python3 -m venv venv
+   source venv/bin/activate  # On Windows: venv\Scripts\activate
+   ```
+3. Install dependencies:
+   ```bash
+   pip install -r requirements.txt
+   ```
+4. Copy the `.env.example` file to `.env` and configure it:
+    - Add your API keys.
+5. Start the server:
+   ```bash
+   python src/server.py
+   ```
+
+### 2. Connect Using the Client App
+
+For client-side setup, refer to the [JavaScript Guide](client/javascript/README.md).
+
+## Important Notes
+- The bot server **must** be running before using the client implementation.
+- Ensure your environment variables are correctly set up.
+
+## Requirements
+- **Python 3.10+**
+- **Node.js 16+** (for JavaScript/React client)
+- **Daily API key**
+- **Google API key**
+- **Modern web browser with WebRTC support**

examples/instant-voice/client/javascript/README.md

@@ -0,0 +1,27 @@
+# JavaScript Implementation
+
+Basic implementation using the [Pipecat JavaScript SDK](https://docs.pipecat.ai/client/js/introduction).
+
+## Setup
+
+1. Run the bot server. See the [server README](../../README).
+
+2. Navigate to the `client/javascript` directory:
+
+```bash
+cd client/javascript
+```
+
+3. Install dependencies:
+
+```bash
+npm install
+```
+
+4. Run the client app:
+
+```
+npm run dev
+```
+
+5. Visit http://localhost:5173 in your browser.

examples/instant-voice/client/javascript/index.html

@@ -0,0 +1,37 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>AI Chatbot</title>
+</head>
+
+<body>
+<div class="container">
+  <div class="status-bar">
+    <div class="status">
+      Buffering audio: <span id="buffering-status">No</span>
+    </div>
+    <div class="status">
+      Transport: <span id="connection-status">Disconnected</span>
+    </div>
+    <div class="controls">
+      <button id="connect-btn">Connect</button>
+      <button id="disconnect-btn" disabled>Disconnect</button>
+    </div>
+  </div>
+
+  <audio id="bot-audio" autoplay></audio>
+
+  <div class="debug-panel">
+    <h3>Debug Info</h3>
+    <div id="debug-log"></div>
+  </div>
+</div>
+
+<script type="module" src="/src/app.ts"></script>
+<link rel="stylesheet" href="/src/style.css">
+</body>
+
+</html>

examples/instant-voice/client/javascript/package.json

@@ -0,0 +1,24 @@
+{
+  "name": "client",
+  "version": "1.0.0",
+  "main": "index.js",
+  "scripts": {
+    "dev": "vite",
+    "build": "tsc && vite build",
+    "preview": "vite preview"
+  },
+  "keywords": [],
+  "author": "",
+  "license": "ISC",
+  "description": "",
+  "devDependencies": {
+    "@types/node": "^22.13.1",
+    "@vitejs/plugin-react-swc": "^3.7.2",
+    "typescript": "^5.7.3",
+    "vite": "^6.0.2"
+  },
+  "dependencies": {
+    "@pipecat-ai/client-js": "^0.3.2",
+    "@pipecat-ai/daily-transport": "^0.3.5"
+  }
+}

examples/instant-voice/client/javascript/src/app.ts

@@ -0,0 +1,268 @@
+/**
+ * Copyright (c) 2024–2025, Daily
+ *
+ * SPDX-License-Identifier: BSD 2-Clause License
+ */
+
+/**
+ * RTVI Client Implementation
+ *
+ * This client connects to an RTVI-compatible bot server using WebRTC (via Daily).
+ * It handles audio/video streaming and manages the connection lifecycle.
+ *
+ * Requirements:
+ * - A running RTVI bot server (defaults to http://localhost:7860)
+ * - The server must implement the /connect endpoint that returns Daily.co room credentials
+ * - Browser with WebRTC support
+ */
+
+import {
+  Participant,
+  RTVIClient,
+  RTVIClientOptions,
+  RTVIEvent,
+} from '@pipecat-ai/client-js';
+import { DailyTransport } from '@pipecat-ai/daily-transport';
+import SoundUtils from "./util/soundUtils";
+import { InstantVoiceHelper } from "./util/instantVoiceHelper";
+
+/**
+ * InstantVoiceClient handles the connection and media management for a real-time
+ * voice and video interaction with an AI bot.
+ */
+class InstantVoiceClient {
+
+  private declare rtviClient: RTVIClient;
+  private connectBtn: HTMLButtonElement | null = null;
+  private disconnectBtn: HTMLButtonElement | null = null;
+  private statusSpan: HTMLElement | null = null;
+  private bufferingAudioSpan: HTMLElement | null = null;
+  private debugLog: HTMLElement | null = null;
+  private botAudio: HTMLAudioElement;
+  private declare startTime: number;
+
+  constructor() {
+    this.botAudio = document.createElement('audio');
+    this.botAudio.autoplay = true;
+    document.body.appendChild(this.botAudio);
+    this.setupDOMElements();
+    this.setupEventListeners();
+    this.initializeRTVIClient();
+  }
+
+  /**
+   * Set up references to DOM elements and create necessary media elements
+   */
+  private setupDOMElements(): void {
+    this.connectBtn = document.getElementById('connect-btn') as HTMLButtonElement;
+    this.disconnectBtn = document.getElementById('disconnect-btn') as HTMLButtonElement;
+    this.statusSpan = document.getElementById('connection-status');
+    this.bufferingAudioSpan = document.getElementById('buffering-status');
+    this.debugLog = document.getElementById('debug-log');
+  }
+
+  /**
+   * Set up event listeners for connect/disconnect buttons
+   */
+  private setupEventListeners(): void {
+    this.connectBtn?.addEventListener('click', () => this.connect());
+    this.disconnectBtn?.addEventListener('click', () => this.disconnect());
+  }
+
+  private initializeRTVIClient(): void {
+    const transport = new DailyTransport({
+      bufferLocalAudioUntilBotReady: true
+    });
+    const RTVIConfig: RTVIClientOptions = {
+      transport,
+      params: {
+        // The baseURL and endpoint of your bot server that the client will connect to
+        baseUrl: 'http://localhost:7860',
+        endpoints: { connect: '/connect' },
+      },
+      enableMic: true,
+      enableCam: false,
+      callbacks: {
+        onConnected: () => {
+          this.updateStatus('Connected');
+          if (this.connectBtn) this.connectBtn.disabled = true;
+          if (this.disconnectBtn) this.disconnectBtn.disabled = false;
+        },
+        onDisconnected: () => {
+          this.updateStatus('Disconnected');
+          this.updateBufferingStatus('No');
+          if (this.connectBtn) this.connectBtn.disabled = false;
+          if (this.disconnectBtn) this.disconnectBtn.disabled = true;
+          this.log('Client disconnected');
+        },
+        onBotConnected: (participant: Participant)  => {
+          this.log(`onBotConnected, timeTaken: ${Date.now() - this.startTime}`);
+        },
+        onBotReady: (data) => {
+          this.log(`onBotReady, timeTaken: ${Date.now() - this.startTime}`);
+          this.log(`Bot ready: ${JSON.stringify(data)}`);
+          this.setupMediaTracks();
+        },
+        onUserTranscript: (data) => {
+          if (data.final) {
+            this.log(`User: ${data.text}`);
+          }
+        },
+        onBotTranscript: (data) => this.log(`Bot: ${data.text}`),
+        onMessageError: (error) => console.error('Message error:', error),
+        onError: (error) => console.error('Error:', error),
+      },
+    }
+
+    this.rtviClient = new RTVIClient(RTVIConfig);
+    this.rtviClient.registerHelper("transport", new InstantVoiceHelper({
+          callbacks: {
+            onAudioBufferingStarted: () => {
+              SoundUtils.beep()
+              this.updateBufferingStatus('Yes');
+              this.log(`onMicCaptureStarted, timeTaken: ${Date.now() - this.startTime}`);
+            },
+            onAudioBufferingStopped: () => {
+              this.updateBufferingStatus('No');
+              this.log(`onMicCaptureStopped, timeTaken: ${Date.now() - this.startTime}`);
+            }
+          }
+        }
+    ));
+    this.setupTrackListeners();
+  }
+
+  /**
+   * Add a timestamped message to the debug log
+   */
+  private log(message: string): void {
+    if (!this.debugLog) return;
+    const entry = document.createElement('div');
+    entry.textContent = `${new Date().toISOString()} - ${message}`;
+    if (message.startsWith('User: ')) {
+      entry.style.color = '#2196F3';
+    } else if (message.startsWith('Bot: ')) {
+      entry.style.color = '#4CAF50';
+    }
+    this.debugLog.appendChild(entry);
+    this.debugLog.scrollTop = this.debugLog.scrollHeight;
+    console.log(message);
+  }
+
+  /**
+   * Update the connection status display
+   */
+  private updateStatus(status: string): void {
+    if (this.statusSpan) {
+      this.statusSpan.textContent = status;
+    }
+    this.log(`Status: ${status}`);
+  }
+
+  /**
+   * Update the connection status display
+   */
+  private updateBufferingStatus(status: string): void {
+    if (this.bufferingAudioSpan) {
+      this.bufferingAudioSpan.textContent = status;
+    }
+    this.log(`BufferingStatus: ${status}`);
+  }
+
+  /**
+   * Check for available media tracks and set them up if present
+   * This is called when the bot is ready or when the transport state changes to ready
+   */
+  setupMediaTracks() {
+    if (!this.rtviClient) return;
+    const tracks = this.rtviClient.tracks();
+    if (tracks.bot?.audio) {
+      this.setupAudioTrack(tracks.bot.audio);
+    }
+  }
+
+  /**
+   * Set up listeners for track events (start/stop)
+   * This handles new tracks being added during the session
+   */
+  setupTrackListeners() {
+    if (!this.rtviClient) return;
+
+    // Listen for new tracks starting
+    this.rtviClient.on(RTVIEvent.TrackStarted, (track, participant) => {
+      // Only handle non-local (bot) tracks
+      if (!participant?.local && track.kind === 'audio') {
+        this.setupAudioTrack(track);
+      }
+    });
+
+    // Listen for tracks stopping
+    this.rtviClient.on(RTVIEvent.TrackStopped, (track, participant) => {
+      this.log(`Track stopped: ${track.kind} from ${participant?.name || 'unknown'}`);
+    });
+  }
+
+  /**
+   * Set up an audio track for playback
+   * Handles both initial setup and track updates
+   */
+  private setupAudioTrack(track: MediaStreamTrack): void {
+    this.log('Setting up audio track');
+    if (this.botAudio.srcObject && "getAudioTracks" in this.botAudio.srcObject) {
+      const oldTrack = this.botAudio.srcObject.getAudioTracks()[0];
+      if (oldTrack?.id === track.id) return;
+    }
+    this.botAudio.srcObject = new MediaStream([track]);
+  }
+
+  /**
+   * Initialize and connect to the bot
+   * This sets up the RTVI client, initializes devices, and establishes the connection
+   */
+  public async connect(): Promise<void> {
+    try {
+      this.startTime = Date.now();
+      this.log('Connecting to bot...');
+      await this.rtviClient.connect();
+    } catch (error) {
+      this.log(`Error connecting: ${(error as Error).message}`);
+      this.updateStatus('Error');
+      this.updateBufferingStatus('No');
+
+      // Clean up if there's an error
+      if (this.rtviClient) {
+        try {
+          await this.rtviClient.disconnect();
+        } catch (disconnectError) {
+          this.log(`Error during disconnect: ${disconnectError}`);
+        }
+      }
+    }
+  }
+
+  /**
+   * Disconnect from the bot and clean up media resources
+   */
+  public async disconnect(): Promise<void> {
+    try {
+      await this.rtviClient.disconnect();
+      if (this.botAudio.srcObject && "getAudioTracks" in this.botAudio.srcObject) {
+        this.botAudio.srcObject.getAudioTracks().forEach((track) => track.stop());
+        this.botAudio.srcObject = null;
+      }
+    } catch (error) {
+      this.log(`Error disconnecting: ${(error as Error).message}`);
+    }
+  }
+}
+
+declare global {
+  interface Window {
+    InstantVoiceClient: typeof InstantVoiceClient;
+  }
+}
+
+window.addEventListener('DOMContentLoaded', () => {
+  window.InstantVoiceClient = InstantVoiceClient;
+  new InstantVoiceClient();
+});

examples/instant-voice/client/javascript/src/style.css

@@ -0,0 +1,98 @@
+body {
+    margin: 0;
+    padding: 20px;
+    font-family: Arial, sans-serif;
+    background-color: #f0f0f0;
+}
+
+.container {
+    max-width: 1200px;
+    margin: 0 auto;
+}
+
+.status-bar {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    padding: 10px;
+    background-color: #fff;
+    border-radius: 8px;
+    margin-bottom: 20px;
+}
+
+.controls button {
+    padding: 8px 16px;
+    margin-left: 10px;
+    border: none;
+    border-radius: 4px;
+    cursor: pointer;
+}
+
+#connect-btn {
+    background-color: #4caf50;
+    color: white;
+}
+
+#disconnect-btn {
+    background-color: #f44336;
+    color: white;
+}
+
+button:disabled {
+    opacity: 0.5;
+    cursor: not-allowed;
+}
+
+.main-content {
+    background-color: #fff;
+    border-radius: 8px;
+    padding: 20px;
+    margin-bottom: 20px;
+}
+
+.bot-container {
+    display: flex;
+    flex-direction: column;
+    align-items: center;
+}
+
+#bot-video-container {
+    width: 640px;
+    height: 360px;
+    background-color: #e0e0e0;
+    border-radius: 8px;
+    margin: 20px auto;
+    overflow: hidden;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+}
+
+#bot-video-container video {
+    width: 100%;
+    height: 100%;
+    object-fit: cover;
+}
+
+.debug-panel {
+    background-color: #fff;
+    border-radius: 8px;
+    padding: 20px;
+}
+
+.debug-panel h3 {
+    margin: 0 0 10px 0;
+    font-size: 16px;
+    font-weight: bold;
+}
+
+#debug-log {
+    height: 500px;
+    overflow-y: auto;
+    background-color: #f8f8f8;
+    padding: 10px;
+    border-radius: 4px;
+    font-family: monospace;
+    font-size: 12px;
+    line-height: 1.4;
+}

examples/instant-voice/client/javascript/src/util/instantVoiceHelper.ts

@@ -0,0 +1,39 @@
+import {RTVIClientHelper, RTVIClientHelperOptions, RTVIMessage} from "@pipecat-ai/client-js";
+import {DailyRTVIMessageType} from '@pipecat-ai/daily-transport';
+
+export type InstantVoiceHelperCallbacks = Partial<{
+    onAudioBufferingStarted: () => void;
+    onAudioBufferingStopped: () => void;
+}>;
+
+// --- Interface and class
+export interface InstantVoiceHelperOptions extends RTVIClientHelperOptions {
+    callbacks?: InstantVoiceHelperCallbacks;
+}
+export class InstantVoiceHelper extends RTVIClientHelper {
+
+    protected declare _options: InstantVoiceHelperOptions;
+
+    constructor(options: InstantVoiceHelperOptions) {
+        super(options);
+    }
+
+    handleMessage(rtviMessage: RTVIMessage): void {
+        switch (rtviMessage.type) {
+            case DailyRTVIMessageType.AUDIO_BUFFERING_STARTED:
+                if (this._options.callbacks?.onAudioBufferingStarted) {
+                    this._options.callbacks?.onAudioBufferingStarted()
+                }
+                break;
+            case DailyRTVIMessageType.AUDIO_BUFFERING_STOPPED:
+                if (this._options.callbacks?.onAudioBufferingStopped) {
+                    this._options.callbacks?.onAudioBufferingStopped()
+                }
+                break;
+        }
+    }
+
+    getMessageTypes(): string[] {
+        return [DailyRTVIMessageType.AUDIO_BUFFERING_STARTED, DailyRTVIMessageType.AUDIO_BUFFERING_STOPPED];
+    }
+}

examples/instant-voice/client/javascript/src/util/soundUtils.ts

@@ -0,0 +1,8 @@
+class SoundUtils {
+    static beep() {
+        const snd = new Audio("data:audio/wav;base64,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");
+        void snd.play();
+    }
+}
+
+export default SoundUtils;

examples/instant-voice/client/javascript/tsconfig.json

@@ -0,0 +1,111 @@
+{
+  "compilerOptions": {
+    /* Visit https://aka.ms/tsconfig to read more about this file */
+
+    /* Projects */
+    // "incremental": true,                              /* Save .tsbuildinfo files to allow for incremental compilation of projects. */
+    // "composite": true,                                /* Enable constraints that allow a TypeScript project to be used with project references. */
+    // "tsBuildInfoFile": "./.tsbuildinfo",              /* Specify the path to .tsbuildinfo incremental compilation file. */
+    // "disableSourceOfProjectReferenceRedirect": true,  /* Disable preferring source files instead of declaration files when referencing composite projects. */
+    // "disableSolutionSearching": true,                 /* Opt a project out of multi-project reference checking when editing. */
+    // "disableReferencedProjectLoad": true,             /* Reduce the number of projects loaded automatically by TypeScript. */
+
+    /* Language and Environment */
+    "target": "es2016",                                  /* Set the JavaScript language version for emitted JavaScript and include compatible library declarations. */
+    // "lib": [],                                        /* Specify a set of bundled library declaration files that describe the target runtime environment. */
+    // "jsx": "preserve",                                /* Specify what JSX code is generated. */
+    // "experimentalDecorators": true,                   /* Enable experimental support for legacy experimental decorators. */
+    // "emitDecoratorMetadata": true,                    /* Emit design-type metadata for decorated declarations in source files. */
+    // "jsxFactory": "",                                 /* Specify the JSX factory function used when targeting React JSX emit, e.g. 'React.createElement' or 'h'. */
+    // "jsxFragmentFactory": "",                         /* Specify the JSX Fragment reference used for fragments when targeting React JSX emit e.g. 'React.Fragment' or 'Fragment'. */
+    // "jsxImportSource": "",                            /* Specify module specifier used to import the JSX factory functions when using 'jsx: react-jsx*'. */
+    // "reactNamespace": "",                             /* Specify the object invoked for 'createElement'. This only applies when targeting 'react' JSX emit. */
+    // "noLib": true,                                    /* Disable including any library files, including the default lib.d.ts. */
+    // "useDefineForClassFields": true,                  /* Emit ECMAScript-standard-compliant class fields. */
+    // "moduleDetection": "auto",                        /* Control what method is used to detect module-format JS files. */
+
+    /* Modules */
+    "module": "commonjs",                                /* Specify what module code is generated. */
+    // "rootDir": "./",                                  /* Specify the root folder within your source files. */
+    // "moduleResolution": "node10",                     /* Specify how TypeScript looks up a file from a given module specifier. */
+    // "baseUrl": "./",                                  /* Specify the base directory to resolve non-relative module names. */
+    // "paths": {},                                      /* Specify a set of entries that re-map imports to additional lookup locations. */
+    // "rootDirs": [],                                   /* Allow multiple folders to be treated as one when resolving modules. */
+    // "typeRoots": [],                                  /* Specify multiple folders that act like './node_modules/@types'. */
+    // "types": [],                                      /* Specify type package names to be included without being referenced in a source file. */
+    // "allowUmdGlobalAccess": true,                     /* Allow accessing UMD globals from modules. */
+    // "moduleSuffixes": [],                             /* List of file name suffixes to search when resolving a module. */
+    // "allowImportingTsExtensions": true,               /* Allow imports to include TypeScript file extensions. Requires '--moduleResolution bundler' and either '--noEmit' or '--emitDeclarationOnly' to be set. */
+    // "rewriteRelativeImportExtensions": true,          /* Rewrite '.ts', '.tsx', '.mts', and '.cts' file extensions in relative import paths to their JavaScript equivalent in output files. */
+    // "resolvePackageJsonExports": true,                /* Use the package.json 'exports' field when resolving package imports. */
+    // "resolvePackageJsonImports": true,                /* Use the package.json 'imports' field when resolving imports. */
+    // "customConditions": [],                           /* Conditions to set in addition to the resolver-specific defaults when resolving imports. */
+    // "noUncheckedSideEffectImports": true,             /* Check side effect imports. */
+    // "resolveJsonModule": true,                        /* Enable importing .json files. */
+    // "allowArbitraryExtensions": true,                 /* Enable importing files with any extension, provided a declaration file is present. */
+    // "noResolve": true,                                /* Disallow 'import's, 'require's or '<reference>'s from expanding the number of files TypeScript should add to a project. */
+
+    /* JavaScript Support */
+    // "allowJs": true,                                  /* Allow JavaScript files to be a part of your program. Use the 'checkJS' option to get errors from these files. */
+    // "checkJs": true,                                  /* Enable error reporting in type-checked JavaScript files. */
+    // "maxNodeModuleJsDepth": 1,                        /* Specify the maximum folder depth used for checking JavaScript files from 'node_modules'. Only applicable with 'allowJs'. */
+
+    /* Emit */
+    // "declaration": true,                              /* Generate .d.ts files from TypeScript and JavaScript files in your project. */
+    // "declarationMap": true,                           /* Create sourcemaps for d.ts files. */
+    // "emitDeclarationOnly": true,                      /* Only output d.ts files and not JavaScript files. */
+    // "sourceMap": true,                                /* Create source map files for emitted JavaScript files. */
+    // "inlineSourceMap": true,                          /* Include sourcemap files inside the emitted JavaScript. */
+    // "noEmit": true,                                   /* Disable emitting files from a compilation. */
+    // "outFile": "./",                                  /* Specify a file that bundles all outputs into one JavaScript file. If 'declaration' is true, also designates a file that bundles all .d.ts output. */
+    // "outDir": "./",                                   /* Specify an output folder for all emitted files. */
+    // "removeComments": true,                           /* Disable emitting comments. */
+    // "importHelpers": true,                            /* Allow importing helper functions from tslib once per project, instead of including them per-file. */
+    // "downlevelIteration": true,                       /* Emit more compliant, but verbose and less performant JavaScript for iteration. */
+    // "sourceRoot": "",                                 /* Specify the root path for debuggers to find the reference source code. */
+    // "mapRoot": "",                                    /* Specify the location where debugger should locate map files instead of generated locations. */
+    // "inlineSources": true,                            /* Include source code in the sourcemaps inside the emitted JavaScript. */
+    // "emitBOM": true,                                  /* Emit a UTF-8 Byte Order Mark (BOM) in the beginning of output files. */
+    // "newLine": "crlf",                                /* Set the newline character for emitting files. */
+    // "stripInternal": true,                            /* Disable emitting declarations that have '@internal' in their JSDoc comments. */
+    // "noEmitHelpers": true,                            /* Disable generating custom helper functions like '__extends' in compiled output. */
+    // "noEmitOnError": true,                            /* Disable emitting files if any type checking errors are reported. */
+    // "preserveConstEnums": true,                       /* Disable erasing 'const enum' declarations in generated code. */
+    // "declarationDir": "./",                           /* Specify the output directory for generated declaration files. */
+
+    /* Interop Constraints */
+    // "isolatedModules": true,                          /* Ensure that each file can be safely transpiled without relying on other imports. */
+    // "verbatimModuleSyntax": true,                     /* Do not transform or elide any imports or exports not marked as type-only, ensuring they are written in the output file's format based on the 'module' setting. */
+    // "isolatedDeclarations": true,                     /* Require sufficient annotation on exports so other tools can trivially generate declaration files. */
+    // "allowSyntheticDefaultImports": true,             /* Allow 'import x from y' when a module doesn't have a default export. */
+    "esModuleInterop": true,                             /* Emit additional JavaScript to ease support for importing CommonJS modules. This enables 'allowSyntheticDefaultImports' for type compatibility. */
+    // "preserveSymlinks": true,                         /* Disable resolving symlinks to their realpath. This correlates to the same flag in node. */
+    "forceConsistentCasingInFileNames": true,            /* Ensure that casing is correct in imports. */
+
+    /* Type Checking */
+    "strict": true,                                      /* Enable all strict type-checking options. */
+    // "noImplicitAny": true,                            /* Enable error reporting for expressions and declarations with an implied 'any' type. */
+    // "strictNullChecks": true,                         /* When type checking, take into account 'null' and 'undefined'. */
+    // "strictFunctionTypes": true,                      /* When assigning functions, check to ensure parameters and the return values are subtype-compatible. */
+    // "strictBindCallApply": true,                      /* Check that the arguments for 'bind', 'call', and 'apply' methods match the original function. */
+    // "strictPropertyInitialization": true,             /* Check for class properties that are declared but not set in the constructor. */
+    // "strictBuiltinIteratorReturn": true,              /* Built-in iterators are instantiated with a 'TReturn' type of 'undefined' instead of 'any'. */
+    // "noImplicitThis": true,                           /* Enable error reporting when 'this' is given the type 'any'. */
+    // "useUnknownInCatchVariables": true,               /* Default catch clause variables as 'unknown' instead of 'any'. */
+    // "alwaysStrict": true,                             /* Ensure 'use strict' is always emitted. */
+    // "noUnusedLocals": true,                           /* Enable error reporting when local variables aren't read. */
+    // "noUnusedParameters": true,                       /* Raise an error when a function parameter isn't read. */
+    // "exactOptionalPropertyTypes": true,               /* Interpret optional property types as written, rather than adding 'undefined'. */
+    // "noImplicitReturns": true,                        /* Enable error reporting for codepaths that do not explicitly return in a function. */
+    // "noFallthroughCasesInSwitch": true,               /* Enable error reporting for fallthrough cases in switch statements. */
+    // "noUncheckedIndexedAccess": true,                 /* Add 'undefined' to a type when accessed using an index. */
+    // "noImplicitOverride": true,                       /* Ensure overriding members in derived classes are marked with an override modifier. */
+    // "noPropertyAccessFromIndexSignature": true,       /* Enforces using indexed accessors for keys declared using an indexed type. */
+    // "allowUnusedLabels": true,                        /* Disable error reporting for unused labels. */
+    // "allowUnreachableCode": true,                     /* Disable error reporting for unreachable code. */
+
+    /* Completeness */
+    // "skipDefaultLibCheck": true,                      /* Skip type checking .d.ts files that are included with TypeScript. */
+    "skipLibCheck": true                                 /* Skip type checking all .d.ts files. */
+  }
+}

examples/instant-voice/client/javascript/vite.config.js

@@ -0,0 +1,15 @@
+import { defineConfig } from 'vite';
+import react from '@vitejs/plugin-react-swc';
+
+export default defineConfig({
+    plugins: [react()],
+    server: {
+        proxy: {
+            // Proxy /api requests to the backend server
+            '/connect': {
+                target: 'http://0.0.0.0:7860', // Replace with your backend URL
+                changeOrigin: true,
+            },
+        },
+    },
+});

examples/instant-voice/client/javascript/yarn.lock

@@ -0,0 +1,339 @@
+# THIS IS AN AUTOGENERATED FILE. DO NOT EDIT THIS FILE DIRECTLY.
+# yarn lockfile v1
+
+
+"@babel/runtime@^7.12.5":
+  version "7.26.0"
+  resolved "https://registry.npmjs.org/@babel/runtime/-/runtime-7.26.0.tgz"
+  integrity sha512-FDSOghenHTiToteC/QRlv2q3DhPZ/oOXTBoirfWNx1Cx3TMVcGWQtMMmQcSvb/JjpNeGzx8Pq/b4fKEJuWm1sw==
+  dependencies:
+    regenerator-runtime "^0.14.0"
+
+"@daily-co/daily-js@^0.73.0":
+  version "0.73.0"
+  resolved "https://registry.npmjs.org/@daily-co/daily-js/-/daily-js-0.73.0.tgz"
+  integrity sha512-Wz8c60hgmkx8fcEeDAi4L4J0rbafiihWKyXFyhYoFYPsw2OdChHpA4RYwIB+1enRws5IK+/HdmzFDYLQsB4A6w==
+  dependencies:
+    "@babel/runtime" "^7.12.5"
+    "@sentry/browser" "^8.33.1"
+    bowser "^2.8.1"
+    dequal "^2.0.3"
+    events "^3.1.0"
+
+"@esbuild/darwin-arm64@0.24.0":
+  version "0.24.0"
+  resolved "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.24.0.tgz"
+  integrity sha512-CKyDpRbK1hXwv79soeTJNHb5EiG6ct3efd/FTPdzOWdbZZfGhpbcqIpiD0+vwmpu0wTIL97ZRPZu8vUt46nBSw==
+
+"@pipecat-ai/client-js@^0.3.2", "@pipecat-ai/client-js@~0.3.2":
+  version "0.3.2"
+  resolved "https://registry.npmjs.org/@pipecat-ai/client-js/-/client-js-0.3.2.tgz"
+  integrity sha512-psunOVrJjPka2SWlq53vxVWCA0Vt8pSXsXtn8pOLC0YTKFsUx+b7Z6quYUJcDZjCe1aAg9cKETek3Xal3Co8Tg==
+  dependencies:
+    "@types/events" "^3.0.3"
+    clone-deep "^4.0.1"
+    events "^3.3.0"
+    typed-emitter "^2.1.0"
+    uuid "^10.0.0"
+
+"@pipecat-ai/daily-transport@^0.3.5":
+  version "0.3.5"
+  resolved "https://registry.npmjs.org/@pipecat-ai/daily-transport/-/daily-transport-0.3.5.tgz"
+  integrity sha512-nJ0TvWPCqXPmU81U8cXOqk5mUEEvEuI06Mis+N0jN8KZUrNy1pP08iWbs07ObmIXdnQcoL+kQmHOerT4q/bF0w==
+  dependencies:
+    "@daily-co/daily-js" "^0.73.0"
+
+"@rollup/rollup-darwin-arm64@4.28.0":
+  version "4.28.0"
+  resolved "https://registry.npmjs.org/@rollup/rollup-darwin-arm64/-/rollup-darwin-arm64-4.28.0.tgz"
+  integrity sha512-lmKx9yHsppblnLQZOGxdO66gT77bvdBtr/0P+TPOseowE7D9AJoBw8ZDULRasXRWf1Z86/gcOdpBrV6VDUY36Q==
+
+"@sentry-internal/browser-utils@8.49.0":
+  version "8.49.0"
+  resolved "https://registry.npmjs.org/@sentry-internal/browser-utils/-/browser-utils-8.49.0.tgz"
+  integrity sha512-XkPHHdFqsN7EPaB+QGUOEmpFqXiqP67t2rRZ1HG1UwJoe0PhJEKNy7b4+WRwmT7ODSt+PvFk1gNBlJBpThwH7Q==
+  dependencies:
+    "@sentry/core" "8.49.0"
+
+"@sentry-internal/feedback@8.49.0":
+  version "8.49.0"
+  resolved "https://registry.npmjs.org/@sentry-internal/feedback/-/feedback-8.49.0.tgz"
+  integrity sha512-v/wf7WvPxEvZUB7xrCnecI3fhevVo84hw8WlxgZIz6mLUHXEIX8xYWc9H8Yet/KKJ2uEB8GQ8aDsY6S1hVEIUA==
+  dependencies:
+    "@sentry/core" "8.49.0"
+
+"@sentry-internal/replay-canvas@8.49.0":
+  version "8.49.0"
+  resolved "https://registry.npmjs.org/@sentry-internal/replay-canvas/-/replay-canvas-8.49.0.tgz"
+  integrity sha512-/yXxI7f+Wu24FIYoRE7A0AidNxORuhAyPzb5ey1wFqMXP72nG8dXhOpcl0w+bi554FkqkLjdeUDhSOBWYZXH9g==
+  dependencies:
+    "@sentry-internal/replay" "8.49.0"
+    "@sentry/core" "8.49.0"
+
+"@sentry-internal/replay@8.49.0":
+  version "8.49.0"
+  resolved "https://registry.npmjs.org/@sentry-internal/replay/-/replay-8.49.0.tgz"
+  integrity sha512-BDiiCBxskkktTd6FNplBc9V8l14R4T/AwRIZj2itX4xnuHewTTDjVbeyvGol4roA4r+V0Mzoi31hLEGI6yFQ5Q==
+  dependencies:
+    "@sentry-internal/browser-utils" "8.49.0"
+    "@sentry/core" "8.49.0"
+
+"@sentry/browser@^8.33.1":
+  version "8.49.0"
+  resolved "https://registry.npmjs.org/@sentry/browser/-/browser-8.49.0.tgz"
+  integrity sha512-dS4Sw2h8EixHeXOIR++XEVMTen6xCGcIQ/XhJbsjqvddXeIijW0WkxSeTfPkfs0dsqFHSisWmlmo0xhHbXvEsQ==
+  dependencies:
+    "@sentry-internal/browser-utils" "8.49.0"
+    "@sentry-internal/feedback" "8.49.0"
+    "@sentry-internal/replay" "8.49.0"
+    "@sentry-internal/replay-canvas" "8.49.0"
+    "@sentry/core" "8.49.0"
+
+"@sentry/core@8.49.0":
+  version "8.49.0"
+  resolved "https://registry.npmjs.org/@sentry/core/-/core-8.49.0.tgz"
+  integrity sha512-/OAm6LdHhh8TvfDAucWfSJV7M03IOHrJm5LVjrrKr4gwQ1HKd4CDbARsBbPwHIzSRAle0IgG3sbJxEvv52JUIw==
+
+"@swc/core-darwin-arm64@1.10.14":
+  version "1.10.14"
+  resolved "https://registry.npmjs.org/@swc/core-darwin-arm64/-/core-darwin-arm64-1.10.14.tgz"
+  integrity sha512-Dh4VyrhDDb05tdRmqJ/MucOPMTnrB4pRJol18HVyLlqu1HOT5EzonUniNTCdQbUXjgdv5UVJSTE1lYTzrp+myA==
+
+"@swc/core@^1.7.26":
+  version "1.10.14"
+  resolved "https://registry.npmjs.org/@swc/core/-/core-1.10.14.tgz"
+  integrity sha512-WSrnE6JRnH20ZYjOOgSS4aOaPv9gxlkI2KRkN24kagbZnPZMnN8bZZyzw1rrLvwgpuRGv17Uz+hflosbR+SP6w==
+  dependencies:
+    "@swc/counter" "^0.1.3"
+    "@swc/types" "^0.1.17"
+  optionalDependencies:
+    "@swc/core-darwin-arm64" "1.10.14"
+    "@swc/core-darwin-x64" "1.10.14"
+    "@swc/core-linux-arm-gnueabihf" "1.10.14"
+    "@swc/core-linux-arm64-gnu" "1.10.14"
+    "@swc/core-linux-arm64-musl" "1.10.14"
+    "@swc/core-linux-x64-gnu" "1.10.14"
+    "@swc/core-linux-x64-musl" "1.10.14"
+    "@swc/core-win32-arm64-msvc" "1.10.14"
+    "@swc/core-win32-ia32-msvc" "1.10.14"
+    "@swc/core-win32-x64-msvc" "1.10.14"
+
+"@swc/counter@^0.1.3":
+  version "0.1.3"
+  resolved "https://registry.npmjs.org/@swc/counter/-/counter-0.1.3.tgz"
+  integrity sha512-e2BR4lsJkkRlKZ/qCHPw9ZaSxc0MVUd7gtbtaB7aMvHeJVYe8sOB8DBZkP2DtISHGSku9sCK6T6cnY0CtXrOCQ==
+
+"@swc/types@^0.1.17":
+  version "0.1.17"
+  resolved "https://registry.npmjs.org/@swc/types/-/types-0.1.17.tgz"
+  integrity sha512-V5gRru+aD8YVyCOMAjMpWR1Ui577DD5KSJsHP8RAxopAH22jFz6GZd/qxqjO6MJHQhcsjvjOFXyDhyLQUnMveQ==
+  dependencies:
+    "@swc/counter" "^0.1.3"
+
+"@types/estree@1.0.6":
+  version "1.0.6"
+  resolved "https://registry.npmjs.org/@types/estree/-/estree-1.0.6.tgz"
+  integrity sha512-AYnb1nQyY49te+VRAVgmzfcgjYS91mY5P0TKUDCLEM+gNnA+3T6rWITXRLYCpahpqSQbN5cE+gHpnPyXjHWxcw==
+
+"@types/events@^3.0.3":
+  version "3.0.3"
+  resolved "https://registry.npmjs.org/@types/events/-/events-3.0.3.tgz"
+  integrity sha512-trOc4AAUThEz9hapPtSd7wf5tiQKvTtu5b371UxXdTuqzIh0ArcRspRP0i0Viu+LXstIQ1z96t1nsPxT9ol01g==
+
+"@types/node@^18.0.0 || ^20.0.0 || >=22.0.0", "@types/node@^22.13.1":
+  version "22.13.1"
+  resolved "https://registry.npmjs.org/@types/node/-/node-22.13.1.tgz"
+  integrity sha512-jK8uzQlrvXqEU91UxiK5J7pKHyzgnI1Qnl0QDHIgVGuolJhRb9EEl28Cj9b3rGR8B2lhFCtvIm5os8lFnO/1Ew==
+  dependencies:
+    undici-types "~6.20.0"
+
+"@vitejs/plugin-react-swc@^3.7.2":
+  version "3.7.2"
+  resolved "https://registry.npmjs.org/@vitejs/plugin-react-swc/-/plugin-react-swc-3.7.2.tgz"
+  integrity sha512-y0byko2b2tSVVf5Gpng1eEhX1OvPC7x8yns1Fx8jDzlJp4LS6CMkCPfLw47cjyoMrshQDoQw4qcgjsU9VvlCew==
+  dependencies:
+    "@swc/core" "^1.7.26"
+
+bowser@^2.8.1:
+  version "2.11.0"
+  resolved "https://registry.npmjs.org/bowser/-/bowser-2.11.0.tgz"
+  integrity sha512-AlcaJBi/pqqJBIQ8U9Mcpc9i8Aqxn88Skv5d+xBX006BY5u8N3mGLHa5Lgppa7L/HfwgwLgZ6NYs+Ag6uUmJRA==
+
+clone-deep@^4.0.1:
+  version "4.0.1"
+  resolved "https://registry.npmjs.org/clone-deep/-/clone-deep-4.0.1.tgz"
+  integrity sha512-neHB9xuzh/wk0dIHweyAXv2aPGZIVk3pLMe+/RNzINf17fe0OG96QroktYAUm7SM1PBnzTabaLboqqxDyMU+SQ==
+  dependencies:
+    is-plain-object "^2.0.4"
+    kind-of "^6.0.2"
+    shallow-clone "^3.0.0"
+
+dequal@^2.0.3:
+  version "2.0.3"
+  resolved "https://registry.npmjs.org/dequal/-/dequal-2.0.3.tgz"
+  integrity sha512-0je+qPKHEMohvfRTCEo3CrPG6cAzAYgmzKyxRiYSSDkS6eGJdyVJm7WaYA5ECaAD9wLB2T4EEeymA5aFVcYXCA==
+
+esbuild@^0.24.0:
+  version "0.24.0"
+  resolved "https://registry.npmjs.org/esbuild/-/esbuild-0.24.0.tgz"
+  integrity sha512-FuLPevChGDshgSicjisSooU0cemp/sGXR841D5LHMB7mTVOmsEHcAxaH3irL53+8YDIeVNQEySh4DaYU/iuPqQ==
+  optionalDependencies:
+    "@esbuild/aix-ppc64" "0.24.0"
+    "@esbuild/android-arm" "0.24.0"
+    "@esbuild/android-arm64" "0.24.0"
+    "@esbuild/android-x64" "0.24.0"
+    "@esbuild/darwin-arm64" "0.24.0"
+    "@esbuild/darwin-x64" "0.24.0"
+    "@esbuild/freebsd-arm64" "0.24.0"
+    "@esbuild/freebsd-x64" "0.24.0"
+    "@esbuild/linux-arm" "0.24.0"
+    "@esbuild/linux-arm64" "0.24.0"
+    "@esbuild/linux-ia32" "0.24.0"
+    "@esbuild/linux-loong64" "0.24.0"
+    "@esbuild/linux-mips64el" "0.24.0"
+    "@esbuild/linux-ppc64" "0.24.0"
+    "@esbuild/linux-riscv64" "0.24.0"
+    "@esbuild/linux-s390x" "0.24.0"
+    "@esbuild/linux-x64" "0.24.0"
+    "@esbuild/netbsd-x64" "0.24.0"
+    "@esbuild/openbsd-arm64" "0.24.0"
+    "@esbuild/openbsd-x64" "0.24.0"
+    "@esbuild/sunos-x64" "0.24.0"
+    "@esbuild/win32-arm64" "0.24.0"
+    "@esbuild/win32-ia32" "0.24.0"
+    "@esbuild/win32-x64" "0.24.0"
+
+events@^3.1.0, events@^3.3.0:
+  version "3.3.0"
+  resolved "https://registry.npmjs.org/events/-/events-3.3.0.tgz"
+  integrity sha512-mQw+2fkQbALzQ7V0MY0IqdnXNOeTtP4r0lN9z7AAawCXgqea7bDii20AYrIBrFd/Hx0M2Ocz6S111CaFkUcb0Q==
+
+fsevents@~2.3.2, fsevents@~2.3.3:
+  version "2.3.3"
+  resolved "https://registry.npmjs.org/fsevents/-/fsevents-2.3.3.tgz"
+  integrity sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==
+
+is-plain-object@^2.0.4:
+  version "2.0.4"
+  resolved "https://registry.npmjs.org/is-plain-object/-/is-plain-object-2.0.4.tgz"
+  integrity sha512-h5PpgXkWitc38BBMYawTYMWJHFZJVnBquFE57xFpjB8pJFiF6gZ+bU+WyI/yqXiFR5mdLsgYNaPe8uao6Uv9Og==
+  dependencies:
+    isobject "^3.0.1"
+
+isobject@^3.0.1:
+  version "3.0.1"
+  resolved "https://registry.npmjs.org/isobject/-/isobject-3.0.1.tgz"
+  integrity sha512-WhB9zCku7EGTj/HQQRz5aUQEUeoQZH2bWcltRErOpymJ4boYE6wL9Tbr23krRPSZ+C5zqNSrSw+Cc7sZZ4b7vg==
+
+kind-of@^6.0.2:
+  version "6.0.3"
+  resolved "https://registry.npmjs.org/kind-of/-/kind-of-6.0.3.tgz"
+  integrity sha512-dcS1ul+9tmeD95T+x28/ehLgd9mENa3LsvDTtzm3vyBEO7RPptvAD+t44WVXaUjTBRcrpFeFlC8WCruUR456hw==
+
+nanoid@^3.3.7:
+  version "3.3.8"
+  resolved "https://registry.npmjs.org/nanoid/-/nanoid-3.3.8.tgz"
+  integrity sha512-WNLf5Sd8oZxOm+TzppcYk8gVOgP+l58xNy58D0nbUnOxOWRWvlcCV4kUF7ltmI6PsrLl/BgKEyS4mqsGChFN0w==
+
+picocolors@^1.1.1:
+  version "1.1.1"
+  resolved "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz"
+  integrity sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA==
+
+postcss@^8.4.49:
+  version "8.4.49"
+  resolved "https://registry.npmjs.org/postcss/-/postcss-8.4.49.tgz"
+  integrity sha512-OCVPnIObs4N29kxTjzLfUryOkvZEq+pf8jTF0lg8E7uETuWHA+v7j3c/xJmiqpX450191LlmZfUKkXxkTry7nA==
+  dependencies:
+    nanoid "^3.3.7"
+    picocolors "^1.1.1"
+    source-map-js "^1.2.1"
+
+regenerator-runtime@^0.14.0:
+  version "0.14.1"
+  resolved "https://registry.npmjs.org/regenerator-runtime/-/regenerator-runtime-0.14.1.tgz"
+  integrity sha512-dYnhHh0nJoMfnkZs6GmmhFknAGRrLznOu5nc9ML+EJxGvrx6H7teuevqVqCuPcPK//3eDrrjQhehXVx9cnkGdw==
+
+rollup@^4.23.0:
+  version "4.28.0"
+  resolved "https://registry.npmjs.org/rollup/-/rollup-4.28.0.tgz"
+  integrity sha512-G9GOrmgWHBma4YfCcX8PjH0qhXSdH8B4HDE2o4/jaxj93S4DPCIDoLcXz99eWMji4hB29UFCEd7B2gwGJDR9cQ==
+  dependencies:
+    "@types/estree" "1.0.6"
+  optionalDependencies:
+    "@rollup/rollup-android-arm-eabi" "4.28.0"
+    "@rollup/rollup-android-arm64" "4.28.0"
+    "@rollup/rollup-darwin-arm64" "4.28.0"
+    "@rollup/rollup-darwin-x64" "4.28.0"
+    "@rollup/rollup-freebsd-arm64" "4.28.0"
+    "@rollup/rollup-freebsd-x64" "4.28.0"
+    "@rollup/rollup-linux-arm-gnueabihf" "4.28.0"
+    "@rollup/rollup-linux-arm-musleabihf" "4.28.0"
+    "@rollup/rollup-linux-arm64-gnu" "4.28.0"
+    "@rollup/rollup-linux-arm64-musl" "4.28.0"
+    "@rollup/rollup-linux-powerpc64le-gnu" "4.28.0"
+    "@rollup/rollup-linux-riscv64-gnu" "4.28.0"
+    "@rollup/rollup-linux-s390x-gnu" "4.28.0"
+    "@rollup/rollup-linux-x64-gnu" "4.28.0"
+    "@rollup/rollup-linux-x64-musl" "4.28.0"
+    "@rollup/rollup-win32-arm64-msvc" "4.28.0"
+    "@rollup/rollup-win32-ia32-msvc" "4.28.0"
+    "@rollup/rollup-win32-x64-msvc" "4.28.0"
+    fsevents "~2.3.2"
+
+rxjs@*:
+  version "7.8.1"
+  resolved "https://registry.npmjs.org/rxjs/-/rxjs-7.8.1.tgz"
+  integrity sha512-AA3TVj+0A2iuIoQkWEK/tqFjBq2j+6PO6Y0zJcvzLAFhEFIO3HL0vls9hWLncZbAAbK0mar7oZ4V079I/qPMxg==
+  dependencies:
+    tslib "^2.1.0"
+
+shallow-clone@^3.0.0:
+  version "3.0.1"
+  resolved "https://registry.npmjs.org/shallow-clone/-/shallow-clone-3.0.1.tgz"
+  integrity sha512-/6KqX+GVUdqPuPPd2LxDDxzX6CAbjJehAAOKlNpqqUpAqPM6HeL8f+o3a+JsyGjn2lv0WY8UsTgUJjU9Ok55NA==
+  dependencies:
+    kind-of "^6.0.2"
+
+source-map-js@^1.2.1:
+  version "1.2.1"
+  resolved "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.1.tgz"
+  integrity sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==
+
+tslib@^2.1.0:
+  version "2.8.1"
+  resolved "https://registry.npmjs.org/tslib/-/tslib-2.8.1.tgz"
+  integrity sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w==
+
+typed-emitter@^2.1.0:
+  version "2.1.0"
+  resolved "https://registry.npmjs.org/typed-emitter/-/typed-emitter-2.1.0.tgz"
+  integrity sha512-g/KzbYKbH5C2vPkaXGu8DJlHrGKHLsM25Zg9WuC9pMGfuvT+X25tZQWo5fK1BjBm8+UrVE9LDCvaY0CQk+fXDA==
+  optionalDependencies:
+    rxjs "*"
+
+typescript@^5.7.3:
+  version "5.7.3"
+  resolved "https://registry.npmjs.org/typescript/-/typescript-5.7.3.tgz"
+  integrity sha512-84MVSjMEHP+FQRPy3pX9sTVV/INIex71s9TL2Gm5FG/WG1SqXeKyZ0k7/blY/4FdOzI12CBy1vGc4og/eus0fw==
+
+undici-types@~6.20.0:
+  version "6.20.0"
+  resolved "https://registry.npmjs.org/undici-types/-/undici-types-6.20.0.tgz"
+  integrity sha512-Ny6QZ2Nju20vw1SRHe3d9jVu6gJ+4e3+MMpqu7pqE5HT6WsTSlce++GQmK5UXS8mzV8DSYHrQH+Xrf2jVcuKNg==
+
+uuid@^10.0.0:
+  version "10.0.0"
+  resolved "https://registry.npmjs.org/uuid/-/uuid-10.0.0.tgz"
+  integrity sha512-8XkAphELsDnEGrDxUOHB3RGvXz6TeuYSGEZBOjtTtPm2lwhGBjLgOzLHB63IUWfBpNucQjND6d3AOudO+H3RWQ==
+
+"vite@^4 || ^5 || ^6", vite@^6.0.2:
+  version "6.0.2"
+  resolved "https://registry.npmjs.org/vite/-/vite-6.0.2.tgz"
+  integrity sha512-XdQ+VsY2tJpBsKGs0wf3U/+azx8BBpYRHFAyKm5VeEZNOJZRB63q7Sc8Iup3k0TrN3KO6QgyzFf+opSbfY1y0g==
+  dependencies:
+    esbuild "^0.24.0"
+    postcss "^8.4.49"
+    rollup "^4.23.0"
+  optionalDependencies:
+    fsevents "~2.3.3"

examples/instant-voice/server/env.example

@@ -0,0 +1,3 @@
+DAILY_API_KEY=
+GOOGLE_API_KEY=
+DAILY_SAMPLE_ROOM_URL=https://yourdomain.daily.co/yourroom # (for joining the bot to the same room repeatedly for local dev)

examples/instant-voice/server/pyproject.toml

@@ -0,0 +1,11 @@
+[tool.ruff]
+exclude = [".git", "*_pb2.py"]
+line-length = 100
+
+[tool.ruff.lint]
+select = [
+    "I", # Import rules
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"

examples/instant-voice/server/requirements.txt

@@ -0,0 +1,4 @@
+python-dotenv
+fastapi[all]
+uvicorn
+pipecat-ai[openai,silero,websocket,google,daily]

examples/instant-voice/server/src/server.py

@@ -0,0 +1,200 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+import asyncio
+import os
+from contextlib import asynccontextmanager
+from typing import Any, Dict, List
+
+import aiohttp
+import uvicorn
+from dotenv import load_dotenv
+from fastapi import FastAPI, HTTPException, Request
+from fastapi.middleware.cors import CORSMiddleware
+from pipecat.transports.services.helpers.daily_rest import DailyRESTHelper, DailyRoomParams
+
+# Load environment variables
+load_dotenv(override=True)
+
+NUMBER_OF_ROOMS = 1
+
+
+class RoomPool:
+    """Manages a pool of pre-created rooms for quick allocation."""
+
+    def __init__(self, daily_rest_helper: DailyRESTHelper):
+        self.daily_rest_helper = daily_rest_helper
+        self.pool: List[Dict[str, str]] = []
+        self.lock = asyncio.Lock()
+
+    async def fill_pool(self, count: int):
+        """Fills the pool with `count` new rooms."""
+        for _ in range(count):
+            await self.add_room()
+
+    async def add_room(self):
+        """Creates a new room and adds it to the pool."""
+        try:
+            room = await self.daily_rest_helper.create_room(DailyRoomParams())
+            if not room.url:
+                raise HTTPException(status_code=500, detail="Failed to create room")
+
+            user_token = await self.daily_rest_helper.get_token(room.url)
+            if not user_token:
+                raise HTTPException(status_code=500, detail="Failed to get user token")
+
+            bot_token = await self.daily_rest_helper.get_token(room.url)
+            if not bot_token:
+                raise HTTPException(status_code=500, detail="Failed to get bot token")
+
+            async with self.lock:
+                self.pool.append(
+                    {"room_url": room.url, "user_token": user_token, "bot_token": bot_token}
+                )
+
+        except Exception as e:
+            print(f"Error adding room to pool: {e}")
+
+    async def get_room(self) -> Dict[str, str]:
+        """Retrieves a room from the pool and requests a new one to maintain the size."""
+        async with self.lock:
+            if not self.pool:
+                raise HTTPException(status_code=503, detail="No available rooms")
+
+            room = self.pool.pop(0)  # Get first available room
+
+        # Start a background task to replenish the pool
+        asyncio.create_task(self.add_room())
+
+        return room
+
+    async def delete_room(self, room_url: str):
+        """Deletes a room when it is not needed anymore"""
+        await self.daily_rest_helper.delete_room_by_url(room_url)
+
+    async def cleanup(self):
+        for rooms in self.pool:
+            room_url = rooms["room_url"]
+            await self.delete_room(room_url)
+
+
+class BotManager:
+    """Manages bot subprocesses asynchronously."""
+
+    def __init__(self):
+        self.bot_procs: Dict[int, asyncio.subprocess.Process] = {}
+        self.room_mappings: Dict[int, str] = {}  # Maps process ID to room URL
+
+    async def start_bot(self, room_url: str, token: str) -> int:
+        bot_file = "single_bot"
+        command = f"python3 -m {bot_file} -u {room_url} -t {token}"
+
+        try:
+            proc = await asyncio.create_subprocess_shell(
+                command,
+                cwd=os.path.dirname(os.path.abspath(__file__)),
+            )
+            if proc.pid is None:
+                raise HTTPException(status_code=500, detail="Failed to get subprocess PID")
+
+            self.bot_procs[proc.pid] = proc
+            self.room_mappings[proc.pid] = room_url
+            # Monitor the process and delete the room when it exits
+            asyncio.create_task(self._monitor_process(proc.pid))
+
+            return proc.pid
+        except Exception as e:
+            raise HTTPException(status_code=500, detail=f"Failed to start subprocess: {e}")
+
+    async def _monitor_process(self, pid: int):
+        """Monitors a bot process and deletes the associated room when it exits."""
+        proc = self.bot_procs.get(pid)
+        if proc:
+            await proc.wait()  # Wait for the process to exit
+            room_url = self.room_mappings.pop(pid, None)
+
+            if room_url:
+                await room_pool.delete_room(room_url)
+                print(f"Deleted room: {room_url}")
+
+            del self.bot_procs[pid]
+
+    async def cleanup(self):
+        """Terminates all running bot processes and deletes associated rooms."""
+        for pid, proc in list(self.bot_procs.items()):
+            try:
+                proc.terminate()
+                await asyncio.wait_for(proc.wait(), timeout=5)
+
+                room_url = self.room_mappings.pop(pid, None)
+                if room_url:
+                    await room_pool.delete_room(room_url)  # Delete room when process terminates
+                    print(f"Deleted room: {room_url}")
+
+            except asyncio.TimeoutError:
+                print(f"Process {pid} did not terminate in time.")
+            except Exception as e:
+                print(f"Error terminating process {pid}: {e}")
+
+        # Clear remaining mappings
+        self.bot_procs.clear()
+        self.room_mappings.clear()
+
+
+# Global instances
+bot_manager = BotManager()
+room_pool: RoomPool  # Will be initialized in lifespan
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    """Handles FastAPI startup and shutdown."""
+    global room_pool
+    aiohttp_session = aiohttp.ClientSession()
+    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=aiohttp_session,
+    )
+
+    room_pool = RoomPool(daily_rest_helper)
+    await room_pool.fill_pool(NUMBER_OF_ROOMS)  # Fill pool on startup
+
+    yield  # Run app
+
+    await bot_manager.cleanup()
+    await room_pool.cleanup()
+    await aiohttp_session.close()
+
+
+# Initialize FastAPI app with lifespan manager
+app = FastAPI(lifespan=lifespan)
+
+# Configure CORS to allow requests from any origin
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.post("/connect")
+async def bot_connect(request: Request) -> Dict[Any, Any]:
+    try:
+        room = await room_pool.get_room()
+        await bot_manager.start_bot(room["room_url"], room["bot_token"])
+    except HTTPException as e:
+        return {"error": str(e)}
+
+    return {
+        "room_url": room["room_url"],
+        "token": room["user_token"],
+    }
+
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)

examples/instant-voice/server/src/single_bot.py

@@ -0,0 +1,120 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+import argparse
+import asyncio
+import os
+import sys
+
+from dotenv import load_dotenv
+from loguru import logger
+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.processors.frameworks.rtvi import RTVIConfig, RTVIProcessor
+from pipecat.services.gemini_multimodal_live import GeminiMultimodalLiveLLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+SYSTEM_INSTRUCTION = f"""
+"You are Gemini Chatbot, a friendly, helpful robot.
+
+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. Keep your responses brief. One or two sentences at most.
+"""
+
+
+def extract_arguments():
+    parser = argparse.ArgumentParser(description="Instant Voice Example")
+    parser.add_argument(
+        "-u", "--url", type=str, required=True, help="URL of the Daily room to join"
+    )
+    parser.add_argument(
+        "-t", "--token", type=str, required=False, help="Token of the Daily room to join"
+    )
+    args, unknown = parser.parse_known_args()
+    url = args.url or os.getenv("DAILY_SAMPLE_ROOM_URL")
+    token = args.token
+    return url, token
+
+
+async def main():
+    room_url, token = extract_arguments()
+    print(f"room_url: {room_url}")
+
+    daily_transport = DailyTransport(
+        room_url,
+        token,
+        "Instant voice Chatbot",
+        DailyParams(
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
+
+    llm = GeminiMultimodalLiveLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
+        transcribe_user_audio=True,
+        transcribe_model_audio=True,
+        system_instruction=SYSTEM_INSTRUCTION,
+    )
+
+    context = OpenAILLMContext()
+    context_aggregator = llm.create_context_aggregator(context)
+
+    # RTVI events for Pipecat client UI
+    rtvi = RTVIProcessor(config=RTVIConfig(config=[]), transport=daily_transport)
+
+    pipeline = Pipeline(
+        [
+            daily_transport.input(),
+            context_aggregator.user(),
+            rtvi,
+            llm,  # LLM
+            daily_transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            observers=[rtvi.observer()],
+        ),
+    )
+
+    @rtvi.event_handler("on_client_ready")
+    async def on_client_ready(rtvi):
+        await rtvi.set_bot_ready()
+
+    @daily_transport.event_handler("on_first_participant_joined")
+    async def on_first_participant_joined(transport, participant):
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @daily_transport.event_handler("on_participant_left")
+    async def on_participant_left(transport, participant, reason):
+        print(f"Participant left: {participant}")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/local-input-select-stt/README.md

@@ -0,0 +1,88 @@
+
+# Pipecat Audio Transcription Example 🚀🎙️
+
+Welcome to the **Pipecat Audio Transcription Example**! 
+
+This project showcases how to integrate the awesome [pipecat](https://github.com/pipecat-ai/pipecat) library with a neat textual interface (powered by [Textual](https://github.com/Textualize/textual)) to select audio devices, perform real-time speech-to-text (STT) transcription using [Whisper](https://github.com/openai/whisper).
+
+> **Note:** Although the script allows you to select both input and output audio devices, this example only utilizes the audio **input** for transcription.
+
+---
+
+## 🎉 Features
+
+- **Interactive Audio Device Selection:**  
+  Choose your preferred audio input device using a cool, textual UI.
+  
+- **State-of-the-Art Transcription:**  
+  Leverage Whisper's large model (running on CUDA) for high-quality, real-time STT.
+  
+- **Live Transcription Logging:**  
+  Watch your spoken words transform into text on your console instantly.
+  
+- **Easy Setup:**  
+  Everything you need is in the [`requirements.txt`](./requirements.txt).
+
+---
+
+## 🎥 Demo
+
+Get a quick glimpse of the app in action!  
+*(Don't worry – I'll be adding a GIF demo here soon!)*
+
+![Demo GIF](demo.gif)
+
+---
+
+## 🔧 Installation
+
+
+Install Dependencies:
+
+```bash
+pip install -r requirements.txt
+```
+
+
+---
+
+## 🚀 Usage
+
+Run the main script:
+
+```bash
+python bot.py
+```
+
+When the app launches, you'll see a textual interface that lets you select your audio input device. Once selected, the app will begin capturing audio, transcribing it using Whisper.
+
+---
+
+## ⚙️ How It Works
+
+
+1. **LocalAudioTransport:**  
+   Captures audio from your chosen input device.
+   
+2. **WhisperSTTService:**  
+   Processes the audio stream using Whisper's large model for speech-to-text conversion.
+   
+3. **TranscriptionLogger:**  
+   Logs the transcribed text to the console as soon as it's processed.
+
+
+---
+
+## 📦 Dependencies
+
+The project relies on:
+
+- [pipecat](https://github.com/yourusername/pipecat) – For building the audio processing pipeline.
+- [Textual](https://github.com/Textualize/textual) – For the interactive terminal UI.
+- [Whisper](https://github.com/openai/whisper) – For state-of-the-art STT transcription.
+
+---
+
+## Example improvements:
+
+I plan to improve this example with local LLM calls and audio output.

examples/local-input-select-stt/bot.py

@@ -0,0 +1,65 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import sys
+from typing import Tuple
+
+from dotenv import load_dotenv
+from loguru import logger
+from select_audio_device import AudioDevice, run_device_selector
+
+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.whisper import Model, WhisperSTTService
+from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class TranscriptionLogger(FrameProcessor):
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, TranscriptionFrame):
+            print(f"Transcription: {frame.text}")
+
+
+async def main(input_device: int, output_device: int):
+    transport = LocalAudioTransport(
+        LocalAudioTransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=False,
+            input_device_index=input_device,
+            output_device_index=output_device,
+        )
+    )
+
+    stt = WhisperSTTService(device="cuda", model=Model.LARGE, no_speech_prob=0.3)
+
+    tl = TranscriptionLogger()
+
+    pipeline = Pipeline([transport.input(), stt, tl])
+
+    task = PipelineTask(pipeline)
+
+    runner = PipelineRunner(handle_sigint=False if sys.platform == "win32" else True)
+
+    await asyncio.gather(runner.run(task))
+
+
+if __name__ == "__main__":
+    res: Tuple[AudioDevice, AudioDevice, int] = asyncio.run(
+        run_device_selector()  # runs the textual app that allows to select input device
+    )
+
+    asyncio.run(main(res[0].index, res[1].index))

examples/local-input-select-stt/requirements.txt

@@ -0,0 +1,8 @@
+--extra-index-url https://download.pytorch.org/whl/cu124
+torch==2.5.0+cu124
+torchvision 
+torchaudio
+pipecat[whisper, openai]
+textual==1.0.0
+pydantic-settings==2.7.1
+pyaudio==0.2.14

examples/local-input-select-stt/select_audio_device.py

@@ -0,0 +1,247 @@
+from typing import List, Optional, Tuple
+
+import pyaudio
+from pydantic import BaseModel, ConfigDict, Field
+from pydantic_settings import BaseSettings
+from textual.app import App, ComposeResult
+from textual.containers import Container
+from textual.widgets import Footer, Header, Label, ListItem, ListView, Select
+from textual.widgets.option_list import Option
+
+# ─── DATA MODELS ───────────────────────────────────────────────────────────────
+
+
+class HostApi(BaseModel):
+    index: int
+    struct_version: int = Field(..., alias="structVersion")
+    type: int
+    name: str
+    device_count: int = Field(..., alias="deviceCount")
+    default_input_device: int = Field(..., alias="defaultInputDevice")
+    default_output_device: int = Field(..., alias="defaultOutputDevice")
+
+
+class AudioDevice(BaseModel):
+    model_config = ConfigDict(populate_by_name=True)
+    index: int
+    struct_version: int = Field(..., alias="structVersion")
+    name: str
+    host_api: int = Field(..., alias="hostApi")
+    max_input_channels: int = Field(..., alias="maxInputChannels")
+    max_output_channels: int = Field(..., alias="maxOutputChannels")
+    default_low_input_latency: float = Field(..., alias="defaultLowInputLatency")
+    default_low_output_latency: float = Field(..., alias="defaultLowOutputLatency")
+    default_high_input_latency: float = Field(..., alias="defaultHighInputLatency")
+    default_high_output_latency: float = Field(..., alias="defaultHighOutputLatency")
+    default_sample_rate: float = Field(..., alias="defaultSampleRate")
+
+
+# ─── SETTINGS MODEL ───────────────────────────────────────────────────────────
+
+
+class AudioSettings(BaseSettings):  # to save settings to a file
+    host_api: Optional[int] = None
+    input_device: Optional[AudioDevice] = None
+    output_device: Optional[AudioDevice] = None
+
+    class Config:
+        env_file = "settings.env"  # or adjust as needed
+
+    def save_to_json(self, filepath: str) -> None:
+        with open(filepath, "w") as f:
+            f.write(self.model_dump_json(indent=2))
+
+
+# ─── TEXTUAL APP ──────────────────────────────────────────────────────────────
+
+
+class AudioDeviceSelectorApp(App):
+    CSS = """
+    Screen {
+        align: center middle;
+    }
+    #container {
+        width: 80%;
+        border: round green;
+        padding: 1 2;
+    }
+    """
+
+    def __init__(
+        self,
+        default_host_api: Optional[int] = None,
+        default_input_device: Optional[AudioDevice] = None,
+        default_output_device: Optional[AudioDevice] = None,
+        **kwargs,
+    ) -> None:
+        super().__init__(**kwargs)
+        # Save defaults passed from settings.
+        self.default_host_api: Optional[int] = default_host_api
+        self.default_input_device: Optional[AudioDevice] = default_input_device
+        self.default_output_device: Optional[AudioDevice] = default_output_device
+
+        self.pyaudio_instance = pyaudio.PyAudio()
+
+        # Static datastructures: host APIs and devices as well‐typed models.
+        self.host_apis: List[HostApi] = []
+        self.current_host_api: Optional[int] = None
+
+        self.all_input_devices: List[AudioDevice] = []
+        self.all_output_devices: List[AudioDevice] = []
+        self.input_devices: List[AudioDevice] = []
+        self.output_devices: List[AudioDevice] = []
+
+        # Stage management: first select input, then output.
+        self.stage: str = "input"
+        self.selected_input_device: Optional[AudioDevice] = None
+        self.selected_output_device: Optional[AudioDevice] = None
+        host_api_count: int = self.pyaudio_instance.get_host_api_count()
+        for i in range(host_api_count):
+            raw_api = self.pyaudio_instance.get_host_api_info_by_index(i)
+            # Inject the index (if not already present)
+            raw_api["index"] = i
+            try:
+                api = HostApi.parse_obj(raw_api)
+                self.host_apis.append(api)
+            except Exception as e:
+                # Skip APIs that don't conform.
+                continue
+
+    def compose(self) -> ComposeResult:
+        options: List[Tuple[str, Option]] = [
+            (
+                api.name,
+                Option(
+                    prompt=str(api.name) if api.name else f"Host API {api.index}",
+                    id=str(api.index),
+                ),
+            )
+            for api in self.host_apis
+        ]
+
+        yield Header()
+
+        yield Footer()
+        with Container(id="container"):
+            yield Label("Select Host API:", id="host-api-label")
+            # Create the Select widget with no options initially.
+            self.host_api_select: Select[HostApi] = Select(options=options, id="host-api-select")
+            yield self.host_api_select
+            self.prompt = Label("Select Input Audio Device:", id="prompt")
+            yield self.prompt
+            self.list_view = ListView(id="device-list")
+            yield self.list_view
+
+    def on_mount(self) -> None:
+        # Populate host APIs from PyAudio.
+
+        # Build the dropdown options.
+
+        self.host_api_select.refresh()  # Force a redraw
+
+        # Determine the default host API.
+        if self.default_host_api is not None:
+            self.current_host_api = self.default_host_api
+        else:
+            default_api_info = self.pyaudio_instance.get_default_host_api_info()
+            self.current_host_api = default_api_info["index"]
+
+        # Delay setting the dropdown's value until the widget is fully initialized.
+        self.set_timer(
+            0,
+            lambda: setattr(self.host_api_select, "value", str(self.current_host_api)),
+        )
+
+        # Load all devices and parse them into AudioDevice objects.
+        device_count: int = self.pyaudio_instance.get_device_count()
+        for i in range(device_count):
+            raw_device = self.pyaudio_instance.get_device_info_by_index(i)
+            raw_device["index"] = i
+            try:
+                device = AudioDevice.parse_obj(raw_device)
+            except Exception as e:
+                # Skip devices missing required fields.
+                continue
+            if device.max_input_channels > 0:
+                self.all_input_devices.append(device)
+            if device.max_output_channels > 0:
+                self.all_output_devices.append(device)
+
+        self.filter_devices()
+        self.populate_list(self.input_devices)
+        if self.default_input_device:
+            self._select_default_in_list(self.default_input_device)
+
+    def filter_devices(self) -> None:
+        """Filter devices based on the selected host API."""
+        self.input_devices = [
+            d for d in self.all_input_devices if d.host_api == self.current_host_api
+        ]
+        self.output_devices = [
+            d for d in self.all_output_devices if d.host_api == self.current_host_api
+        ]
+
+    def populate_list(self, devices: List[AudioDevice]) -> None:
+        """Populate the ListView with a list of AudioDevice objects."""
+        self.list_view.clear()
+        for dev in devices:
+            item_text: str = f"{dev.name} (Index: {dev.index})"
+            item = ListItem(Label(item_text))
+            # Attach the AudioDevice instance to the widget.
+            item.device_info = dev  # type: ignore
+            self.list_view.append(item)
+
+    def _select_default_in_list(self, default_device: AudioDevice) -> None:
+        """Pre-select the default device if present in the current list."""
+        for idx, item in enumerate(self.list_view.children):
+            if hasattr(item, "device_info") and item.device_info.index == default_device.index:
+                self.list_view.index = idx
+                break
+
+    async def on_select_changed(self, event: Select.Changed) -> None:
+        """Handle changes in the host API dropdown."""
+        if event.select.id == "host-api-select":
+            self.current_host_api = int(event.value.id)
+            self.filter_devices()
+            if self.stage == "input":
+                self.populate_list(self.input_devices)
+                if self.default_input_device:
+                    self._select_default_in_list(self.default_input_device)
+            elif self.stage == "output":
+                self.populate_list(self.output_devices)
+                if self.default_output_device:
+                    self._select_default_in_list(self.default_output_device)
+
+    async def on_list_view_selected(self, message: ListView.Selected) -> None:
+        """Record device selection and switch stages."""
+        selected_item = message.item
+        device_info: AudioDevice = selected_item.device_info  # type: ignore
+        if self.stage == "input":
+            self.selected_input_device = device_info
+            self.stage = "output"
+            self.prompt.update("Select Output Audio Device:")
+            self.populate_list(self.output_devices)
+            if self.default_output_device:
+                self._select_default_in_list(self.default_output_device)
+        elif self.stage == "output":
+            self.selected_output_device = device_info
+            await self.action_quit()
+
+
+# ─── HELPER FUNCTIONS ─────────────────────────────────────────────────────────
+
+
+async def run_device_selector(
+    default_host_api: Optional[int] = None,
+    default_input_device: Optional[AudioDevice] = None,
+    default_output_device: Optional[AudioDevice] = None,
+) -> Tuple[AudioDevice, AudioDevice, int]:
+    app = AudioDeviceSelectorApp(
+        default_host_api=default_host_api,
+        default_input_device=default_input_device,
+        default_output_device=default_output_device,
+    )
+    await app.run_async()
+
+    # The current_host_api is guaranteed to be set.
+    return app.selected_input_device, app.selected_output_device, app.current_host_api  # type: ignore

examples/news-chatbot/client/javascript/package-lock.json

@@ -13,7 +13,7 @@
         "@pipecat-ai/daily-transport": "^0.3.4"
       },
       "devDependencies": {
-        "vite": "^6.0.2"
+        "vite": "^6.0.9"
       }
     },
     "node_modules/@babel/runtime": {
@@ -45,14 +45,13 @@
       }
     },
     "node_modules/@esbuild/aix-ppc64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.24.0.tgz",
-      "integrity": "sha512-WtKdFM7ls47zkKHFVzMz8opM7LkcsIp9amDUBIAWirg70RM71WRSjdILPsY5Uv1D42ZpUfaPILDlfactHgsRkw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.24.2.tgz",
+      "integrity": "sha512-thpVCb/rhxE/BnMLQ7GReQLLN8q9qbHmI55F4489/ByVg2aQaQ6kbcLb6FHkocZzQhxc4gx0sCk0tJkKBFzDhA==",
       "cpu": [
         "ppc64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "aix"
@@ -62,14 +61,13 @@
       }
     },
     "node_modules/@esbuild/android-arm": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.24.0.tgz",
-      "integrity": "sha512-arAtTPo76fJ/ICkXWetLCc9EwEHKaeya4vMrReVlEIUCAUncH7M4bhMQ+M9Vf+FFOZJdTNMXNBrWwW+OXWpSew==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.24.2.tgz",
+      "integrity": "sha512-tmwl4hJkCfNHwFB3nBa8z1Uy3ypZpxqxfTQOcHX+xRByyYgunVbZ9MzUUfb0RxaHIMnbHagwAxuTL+tnNM+1/Q==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
@@ -79,14 +77,13 @@
       }
     },
     "node_modules/@esbuild/android-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.24.0.tgz",
-      "integrity": "sha512-Vsm497xFM7tTIPYK9bNTYJyF/lsP590Qc1WxJdlB6ljCbdZKU9SY8i7+Iin4kyhV/KV5J2rOKsBQbB77Ab7L/w==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.24.2.tgz",
+      "integrity": "sha512-cNLgeqCqV8WxfcTIOeL4OAtSmL8JjcN6m09XIgro1Wi7cF4t/THaWEa7eL5CMoMBdjoHOTh/vwTO/o2TRXIyzg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
@@ -96,14 +93,13 @@
       }
     },
     "node_modules/@esbuild/android-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.24.0.tgz",
-      "integrity": "sha512-t8GrvnFkiIY7pa7mMgJd7p8p8qqYIz1NYiAoKc75Zyv73L3DZW++oYMSHPRarcotTKuSs6m3hTOa5CKHaS02TQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.24.2.tgz",
+      "integrity": "sha512-B6Q0YQDqMx9D7rvIcsXfmJfvUYLoP722bgfBlO5cGvNVb5V/+Y7nhBE3mHV9OpxBf4eAS2S68KZztiPaWq4XYw==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
@@ -113,14 +109,13 @@
       }
     },
     "node_modules/@esbuild/darwin-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.24.0.tgz",
-      "integrity": "sha512-CKyDpRbK1hXwv79soeTJNHb5EiG6ct3efd/FTPdzOWdbZZfGhpbcqIpiD0+vwmpu0wTIL97ZRPZu8vUt46nBSw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.24.2.tgz",
+      "integrity": "sha512-kj3AnYWc+CekmZnS5IPu9D+HWtUI49hbnyqk0FLEJDbzCIQt7hg7ucF1SQAilhtYpIujfaHr6O0UHlzzSPdOeA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
@@ -130,14 +125,13 @@
       }
     },
     "node_modules/@esbuild/darwin-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.24.0.tgz",
-      "integrity": "sha512-rgtz6flkVkh58od4PwTRqxbKH9cOjaXCMZgWD905JOzjFKW+7EiUObfd/Kav+A6Gyud6WZk9w+xu6QLytdi2OA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.24.2.tgz",
+      "integrity": "sha512-WeSrmwwHaPkNR5H3yYfowhZcbriGqooyu3zI/3GGpF8AyUdsrrP0X6KumITGA9WOyiJavnGZUwPGvxvwfWPHIA==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
@@ -147,14 +141,13 @@
       }
     },
     "node_modules/@esbuild/freebsd-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.24.0.tgz",
-      "integrity": "sha512-6Mtdq5nHggwfDNLAHkPlyLBpE5L6hwsuXZX8XNmHno9JuL2+bg2BX5tRkwjyfn6sKbxZTq68suOjgWqCicvPXA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.24.2.tgz",
+      "integrity": "sha512-UN8HXjtJ0k/Mj6a9+5u6+2eZ2ERD7Edt1Q9IZiB5UZAIdPnVKDoG7mdTVGhHJIeEml60JteamR3qhsr1r8gXvg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
@@ -164,14 +157,13 @@
       }
     },
     "node_modules/@esbuild/freebsd-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.24.0.tgz",
-      "integrity": "sha512-D3H+xh3/zphoX8ck4S2RxKR6gHlHDXXzOf6f/9dbFt/NRBDIE33+cVa49Kil4WUjxMGW0ZIYBYtaGCa2+OsQwQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.24.2.tgz",
+      "integrity": "sha512-TvW7wE/89PYW+IevEJXZ5sF6gJRDY/14hyIGFXdIucxCsbRmLUcjseQu1SyTko+2idmCw94TgyaEZi9HUSOe3Q==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
@@ -181,14 +173,13 @@
       }
     },
     "node_modules/@esbuild/linux-arm": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.24.0.tgz",
-      "integrity": "sha512-gJKIi2IjRo5G6Glxb8d3DzYXlxdEj2NlkixPsqePSZMhLudqPhtZ4BUrpIuTjJYXxvF9njql+vRjB2oaC9XpBw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.24.2.tgz",
+      "integrity": "sha512-n0WRM/gWIdU29J57hJyUdIsk0WarGd6To0s+Y+LwvlC55wt+GT/OgkwoXCXvIue1i1sSNWblHEig00GBWiJgfA==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -198,14 +189,13 @@
       }
     },
     "node_modules/@esbuild/linux-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.24.0.tgz",
-      "integrity": "sha512-TDijPXTOeE3eaMkRYpcy3LarIg13dS9wWHRdwYRnzlwlA370rNdZqbcp0WTyyV/k2zSxfko52+C7jU5F9Tfj1g==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.24.2.tgz",
+      "integrity": "sha512-7HnAD6074BW43YvvUmE/35Id9/NB7BeX5EoNkK9obndmZBUk8xmJJeU7DwmUeN7tkysslb2eSl6CTrYz6oEMQg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -215,14 +205,13 @@
       }
     },
     "node_modules/@esbuild/linux-ia32": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.24.0.tgz",
-      "integrity": "sha512-K40ip1LAcA0byL05TbCQ4yJ4swvnbzHscRmUilrmP9Am7//0UjPreh4lpYzvThT2Quw66MhjG//20mrufm40mA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.24.2.tgz",
+      "integrity": "sha512-sfv0tGPQhcZOgTKO3oBE9xpHuUqguHvSo4jl+wjnKwFpapx+vUDcawbwPNuBIAYdRAvIDBfZVvXprIj3HA+Ugw==",
       "cpu": [
         "ia32"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -232,14 +221,13 @@
       }
     },
     "node_modules/@esbuild/linux-loong64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.24.0.tgz",
-      "integrity": "sha512-0mswrYP/9ai+CU0BzBfPMZ8RVm3RGAN/lmOMgW4aFUSOQBjA31UP8Mr6DDhWSuMwj7jaWOT0p0WoZ6jeHhrD7g==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.24.2.tgz",
+      "integrity": "sha512-CN9AZr8kEndGooS35ntToZLTQLHEjtVB5n7dl8ZcTZMonJ7CCfStrYhrzF97eAecqVbVJ7APOEe18RPI4KLhwQ==",
       "cpu": [
         "loong64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -249,14 +237,13 @@
       }
     },
     "node_modules/@esbuild/linux-mips64el": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.24.0.tgz",
-      "integrity": "sha512-hIKvXm0/3w/5+RDtCJeXqMZGkI2s4oMUGj3/jM0QzhgIASWrGO5/RlzAzm5nNh/awHE0A19h/CvHQe6FaBNrRA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.24.2.tgz",
+      "integrity": "sha512-iMkk7qr/wl3exJATwkISxI7kTcmHKE+BlymIAbHO8xanq/TjHaaVThFF6ipWzPHryoFsesNQJPE/3wFJw4+huw==",
       "cpu": [
         "mips64el"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -266,14 +253,13 @@
       }
     },
     "node_modules/@esbuild/linux-ppc64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.24.0.tgz",
-      "integrity": "sha512-HcZh5BNq0aC52UoocJxaKORfFODWXZxtBaaZNuN3PUX3MoDsChsZqopzi5UupRhPHSEHotoiptqikjN/B77mYQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.24.2.tgz",
+      "integrity": "sha512-shsVrgCZ57Vr2L8mm39kO5PPIb+843FStGt7sGGoqiiWYconSxwTiuswC1VJZLCjNiMLAMh34jg4VSEQb+iEbw==",
       "cpu": [
         "ppc64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -283,14 +269,13 @@
       }
     },
     "node_modules/@esbuild/linux-riscv64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.24.0.tgz",
-      "integrity": "sha512-bEh7dMn/h3QxeR2KTy1DUszQjUrIHPZKyO6aN1X4BCnhfYhuQqedHaa5MxSQA/06j3GpiIlFGSsy1c7Gf9padw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.24.2.tgz",
+      "integrity": "sha512-4eSFWnU9Hhd68fW16GD0TINewo1L6dRrB+oLNNbYyMUAeOD2yCK5KXGK1GH4qD/kT+bTEXjsyTCiJGHPZ3eM9Q==",
       "cpu": [
         "riscv64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -300,14 +285,13 @@
       }
     },
     "node_modules/@esbuild/linux-s390x": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.24.0.tgz",
-      "integrity": "sha512-ZcQ6+qRkw1UcZGPyrCiHHkmBaj9SiCD8Oqd556HldP+QlpUIe2Wgn3ehQGVoPOvZvtHm8HPx+bH20c9pvbkX3g==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.24.2.tgz",
+      "integrity": "sha512-S0Bh0A53b0YHL2XEXC20bHLuGMOhFDO6GN4b3YjRLK//Ep3ql3erpNcPlEFed93hsQAjAQDNsvcK+hV90FubSw==",
       "cpu": [
         "s390x"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -317,14 +301,13 @@
       }
     },
     "node_modules/@esbuild/linux-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.24.0.tgz",
-      "integrity": "sha512-vbutsFqQ+foy3wSSbmjBXXIJ6PL3scghJoM8zCL142cGaZKAdCZHyf+Bpu/MmX9zT9Q0zFBVKb36Ma5Fzfa8xA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.24.2.tgz",
+      "integrity": "sha512-8Qi4nQcCTbLnK9WoMjdC9NiTG6/E38RNICU6sUNqK0QFxCYgoARqVqxdFmWkdonVsvGqWhmm7MO0jyTqLqwj0Q==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -333,15 +316,30 @@
         "node": ">=18"
       }
     },
+    "node_modules/@esbuild/netbsd-arm64": {
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.24.2.tgz",
+      "integrity": "sha512-wuLK/VztRRpMt9zyHSazyCVdCXlpHkKm34WUyinD2lzK07FAHTq0KQvZZlXikNWkDGoT6x3TD51jKQ7gMVpopw==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "optional": true,
+      "os": [
+        "netbsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
     "node_modules/@esbuild/netbsd-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.24.0.tgz",
-      "integrity": "sha512-hjQ0R/ulkO8fCYFsG0FZoH+pWgTTDreqpqY7UnQntnaKv95uP5iW3+dChxnx7C3trQQU40S+OgWhUVwCjVFLvg==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.24.2.tgz",
+      "integrity": "sha512-VefFaQUc4FMmJuAxmIHgUmfNiLXY438XrL4GDNV1Y1H/RW3qow68xTwjZKfj/+Plp9NANmzbH5R40Meudu8mmw==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "netbsd"
@@ -351,14 +349,13 @@
       }
     },
     "node_modules/@esbuild/openbsd-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.24.0.tgz",
-      "integrity": "sha512-MD9uzzkPQbYehwcN583yx3Tu5M8EIoTD+tUgKF982WYL9Pf5rKy9ltgD0eUgs8pvKnmizxjXZyLt0z6DC3rRXg==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.24.2.tgz",
+      "integrity": "sha512-YQbi46SBct6iKnszhSvdluqDmxCJA+Pu280Av9WICNwQmMxV7nLRHZfjQzwbPs3jeWnuAhE9Jy0NrnJ12Oz+0A==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "openbsd"
@@ -368,14 +365,13 @@
       }
     },
     "node_modules/@esbuild/openbsd-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.24.0.tgz",
-      "integrity": "sha512-4ir0aY1NGUhIC1hdoCzr1+5b43mw99uNwVzhIq1OY3QcEwPDO3B7WNXBzaKY5Nsf1+N11i1eOfFcq+D/gOS15Q==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.24.2.tgz",
+      "integrity": "sha512-+iDS6zpNM6EnJyWv0bMGLWSWeXGN/HTaF/LXHXHwejGsVi+ooqDfMCCTerNFxEkM3wYVcExkeGXNqshc9iMaOA==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "openbsd"
@@ -385,14 +381,13 @@
       }
     },
     "node_modules/@esbuild/sunos-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.24.0.tgz",
-      "integrity": "sha512-jVzdzsbM5xrotH+W5f1s+JtUy1UWgjU0Cf4wMvffTB8m6wP5/kx0KiaLHlbJO+dMgtxKV8RQ/JvtlFcdZ1zCPA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.24.2.tgz",
+      "integrity": "sha512-hTdsW27jcktEvpwNHJU4ZwWFGkz2zRJUz8pvddmXPtXDzVKTTINmlmga3ZzwcuMpUvLw7JkLy9QLKyGpD2Yxig==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "sunos"
@@ -402,14 +397,13 @@
       }
     },
     "node_modules/@esbuild/win32-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.24.0.tgz",
-      "integrity": "sha512-iKc8GAslzRpBytO2/aN3d2yb2z8XTVfNV0PjGlCxKo5SgWmNXx82I/Q3aG1tFfS+A2igVCY97TJ8tnYwpUWLCA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.24.2.tgz",
+      "integrity": "sha512-LihEQ2BBKVFLOC9ZItT9iFprsE9tqjDjnbulhHoFxYQtQfai7qfluVODIYxt1PgdoyQkz23+01rzwNwYfutxUQ==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -419,14 +413,13 @@
       }
     },
     "node_modules/@esbuild/win32-ia32": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.24.0.tgz",
-      "integrity": "sha512-vQW36KZolfIudCcTnaTpmLQ24Ha1RjygBo39/aLkM2kmjkWmZGEJ5Gn9l5/7tzXA42QGIoWbICfg6KLLkIw6yw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.24.2.tgz",
+      "integrity": "sha512-q+iGUwfs8tncmFC9pcnD5IvRHAzmbwQ3GPS5/ceCyHdjXubwQWI12MKWSNSMYLJMq23/IUCvJMS76PDqXe1fxA==",
       "cpu": [
         "ia32"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -436,14 +429,13 @@
       }
     },
     "node_modules/@esbuild/win32-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.24.0.tgz",
-      "integrity": "sha512-7IAFPrjSQIJrGsK6flwg7NFmwBoSTyF3rl7If0hNUFQU4ilTsEPL6GuMuU9BfIWVVGuRnuIidkSMC+c0Otu8IA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.24.2.tgz",
+      "integrity": "sha512-7VTgWzgMGvup6aSqDPLiW5zHaxYJGTO4OokMjIlrCtf+VpEL+cXKtCvg723iguPYI5oaUNdS+/V7OU2gvXVWEg==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -478,252 +470,247 @@
       }
     },
     "node_modules/@rollup/rollup-android-arm-eabi": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm-eabi/-/rollup-android-arm-eabi-4.28.0.tgz",
-      "integrity": "sha512-wLJuPLT6grGZsy34g4N1yRfYeouklTgPhH1gWXCYspenKYD0s3cR99ZevOGw5BexMNywkbV3UkjADisozBmpPQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm-eabi/-/rollup-android-arm-eabi-4.34.6.tgz",
+      "integrity": "sha512-+GcCXtOQoWuC7hhX1P00LqjjIiS/iOouHXhMdiDSnq/1DGTox4SpUvO52Xm+div6+106r+TcvOeo/cxvyEyTgg==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
       ]
     },
     "node_modules/@rollup/rollup-android-arm64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm64/-/rollup-android-arm64-4.28.0.tgz",
-      "integrity": "sha512-eiNkznlo0dLmVG/6wf+Ifi/v78G4d4QxRhuUl+s8EWZpDewgk7PX3ZyECUXU0Zq/Ca+8nU8cQpNC4Xgn2gFNDA==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm64/-/rollup-android-arm64-4.34.6.tgz",
+      "integrity": "sha512-E8+2qCIjciYUnCa1AiVF1BkRgqIGW9KzJeesQqVfyRITGQN+dFuoivO0hnro1DjT74wXLRZ7QF8MIbz+luGaJA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
       ]
     },
     "node_modules/@rollup/rollup-darwin-arm64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-arm64/-/rollup-darwin-arm64-4.28.0.tgz",
-      "integrity": "sha512-lmKx9yHsppblnLQZOGxdO66gT77bvdBtr/0P+TPOseowE7D9AJoBw8ZDULRasXRWf1Z86/gcOdpBrV6VDUY36Q==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-arm64/-/rollup-darwin-arm64-4.34.6.tgz",
+      "integrity": "sha512-z9Ib+OzqN3DZEjX7PDQMHEhtF+t6Mi2z/ueChQPLS/qUMKY7Ybn5A2ggFoKRNRh1q1T03YTQfBTQCJZiepESAg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
       ]
     },
     "node_modules/@rollup/rollup-darwin-x64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-x64/-/rollup-darwin-x64-4.28.0.tgz",
-      "integrity": "sha512-8hxgfReVs7k9Js1uAIhS6zq3I+wKQETInnWQtgzt8JfGx51R1N6DRVy3F4o0lQwumbErRz52YqwjfvuwRxGv1w==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-x64/-/rollup-darwin-x64-4.34.6.tgz",
+      "integrity": "sha512-PShKVY4u0FDAR7jskyFIYVyHEPCPnIQY8s5OcXkdU8mz3Y7eXDJPdyM/ZWjkYdR2m0izD9HHWA8sGcXn+Qrsyg==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
       ]
     },
     "node_modules/@rollup/rollup-freebsd-arm64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-arm64/-/rollup-freebsd-arm64-4.28.0.tgz",
-      "integrity": "sha512-lA1zZB3bFx5oxu9fYud4+g1mt+lYXCoch0M0V/xhqLoGatbzVse0wlSQ1UYOWKpuSu3gyN4qEc0Dxf/DII1bhQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-arm64/-/rollup-freebsd-arm64-4.34.6.tgz",
+      "integrity": "sha512-YSwyOqlDAdKqs0iKuqvRHLN4SrD2TiswfoLfvYXseKbL47ht1grQpq46MSiQAx6rQEN8o8URtpXARCpqabqxGQ==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
       ]
     },
     "node_modules/@rollup/rollup-freebsd-x64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-x64/-/rollup-freebsd-x64-4.28.0.tgz",
-      "integrity": "sha512-aI2plavbUDjCQB/sRbeUZWX9qp12GfYkYSJOrdYTL/C5D53bsE2/nBPuoiJKoWp5SN78v2Vr8ZPnB+/VbQ2pFA==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-x64/-/rollup-freebsd-x64-4.34.6.tgz",
+      "integrity": "sha512-HEP4CgPAY1RxXwwL5sPFv6BBM3tVeLnshF03HMhJYCNc6kvSqBgTMmsEjb72RkZBAWIqiPUyF1JpEBv5XT9wKQ==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm-gnueabihf": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-gnueabihf/-/rollup-linux-arm-gnueabihf-4.28.0.tgz",
-      "integrity": "sha512-WXveUPKtfqtaNvpf0iOb0M6xC64GzUX/OowbqfiCSXTdi/jLlOmH0Ba94/OkiY2yTGTwteo4/dsHRfh5bDCZ+w==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-gnueabihf/-/rollup-linux-arm-gnueabihf-4.34.6.tgz",
+      "integrity": "sha512-88fSzjC5xeH9S2Vg3rPgXJULkHcLYMkh8faix8DX4h4TIAL65ekwuQMA/g2CXq8W+NJC43V6fUpYZNjaX3+IIg==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm-musleabihf": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-musleabihf/-/rollup-linux-arm-musleabihf-4.28.0.tgz",
-      "integrity": "sha512-yLc3O2NtOQR67lI79zsSc7lk31xjwcaocvdD1twL64PK1yNaIqCeWI9L5B4MFPAVGEVjH5k1oWSGuYX1Wutxpg==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-musleabihf/-/rollup-linux-arm-musleabihf-4.34.6.tgz",
+      "integrity": "sha512-wM4ztnutBqYFyvNeR7Av+reWI/enK9tDOTKNF+6Kk2Q96k9bwhDDOlnCUNRPvromlVXo04riSliMBs/Z7RteEg==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm64-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-gnu/-/rollup-linux-arm64-gnu-4.28.0.tgz",
-      "integrity": "sha512-+P9G9hjEpHucHRXqesY+3X9hD2wh0iNnJXX/QhS/J5vTdG6VhNYMxJ2rJkQOxRUd17u5mbMLHM7yWGZdAASfcg==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-gnu/-/rollup-linux-arm64-gnu-4.34.6.tgz",
+      "integrity": "sha512-9RyprECbRa9zEjXLtvvshhw4CMrRa3K+0wcp3KME0zmBe1ILmvcVHnypZ/aIDXpRyfhSYSuN4EPdCCj5Du8FIA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm64-musl": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-musl/-/rollup-linux-arm64-musl-4.28.0.tgz",
-      "integrity": "sha512-1xsm2rCKSTpKzi5/ypT5wfc+4bOGa/9yI/eaOLW0oMs7qpC542APWhl4A37AENGZ6St6GBMWhCCMM6tXgTIplw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-musl/-/rollup-linux-arm64-musl-4.34.6.tgz",
+      "integrity": "sha512-qTmklhCTyaJSB05S+iSovfo++EwnIEZxHkzv5dep4qoszUMX5Ca4WM4zAVUMbfdviLgCSQOu5oU8YoGk1s6M9Q==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@rollup/rollup-linux-loongarch64-gnu": {
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-loongarch64-gnu/-/rollup-linux-loongarch64-gnu-4.34.6.tgz",
+      "integrity": "sha512-4Qmkaps9yqmpjY5pvpkfOerYgKNUGzQpFxV6rnS7c/JfYbDSU0y6WpbbredB5cCpLFGJEqYX40WUmxMkwhWCjw==",
+      "cpu": [
+        "loong64"
+      ],
+      "dev": true,
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-powerpc64le-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-powerpc64le-gnu/-/rollup-linux-powerpc64le-gnu-4.28.0.tgz",
-      "integrity": "sha512-zgWxMq8neVQeXL+ouSf6S7DoNeo6EPgi1eeqHXVKQxqPy1B2NvTbaOUWPn/7CfMKL7xvhV0/+fq/Z/J69g1WAQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-powerpc64le-gnu/-/rollup-linux-powerpc64le-gnu-4.34.6.tgz",
+      "integrity": "sha512-Zsrtux3PuaxuBTX/zHdLaFmcofWGzaWW1scwLU3ZbW/X+hSsFbz9wDIp6XvnT7pzYRl9MezWqEqKy7ssmDEnuQ==",
       "cpu": [
         "ppc64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-riscv64-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-gnu/-/rollup-linux-riscv64-gnu-4.28.0.tgz",
-      "integrity": "sha512-VEdVYacLniRxbRJLNtzwGt5vwS0ycYshofI7cWAfj7Vg5asqj+pt+Q6x4n+AONSZW/kVm+5nklde0qs2EUwU2g==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-gnu/-/rollup-linux-riscv64-gnu-4.34.6.tgz",
+      "integrity": "sha512-aK+Zp+CRM55iPrlyKiU3/zyhgzWBxLVrw2mwiQSYJRobCURb781+XstzvA8Gkjg/hbdQFuDw44aUOxVQFycrAg==",
       "cpu": [
         "riscv64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-s390x-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-s390x-gnu/-/rollup-linux-s390x-gnu-4.28.0.tgz",
-      "integrity": "sha512-LQlP5t2hcDJh8HV8RELD9/xlYtEzJkm/aWGsauvdO2ulfl3QYRjqrKW+mGAIWP5kdNCBheqqqYIGElSRCaXfpw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-s390x-gnu/-/rollup-linux-s390x-gnu-4.34.6.tgz",
+      "integrity": "sha512-WoKLVrY9ogmaYPXwTH326+ErlCIgMmsoRSx6bO+l68YgJnlOXhygDYSZe/qbUJCSiCiZAQ+tKm88NcWuUXqOzw==",
       "cpu": [
         "s390x"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-x64-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.28.0.tgz",
-      "integrity": "sha512-Nl4KIzteVEKE9BdAvYoTkW19pa7LR/RBrT6F1dJCV/3pbjwDcaOq+edkP0LXuJ9kflW/xOK414X78r+K84+msw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.34.6.tgz",
+      "integrity": "sha512-Sht4aFvmA4ToHd2vFzwMFaQCiYm2lDFho5rPcvPBT5pCdC+GwHG6CMch4GQfmWTQ1SwRKS0dhDYb54khSrjDWw==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-x64-musl": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-musl/-/rollup-linux-x64-musl-4.28.0.tgz",
-      "integrity": "sha512-eKpJr4vBDOi4goT75MvW+0dXcNUqisK4jvibY9vDdlgLx+yekxSm55StsHbxUsRxSTt3JEQvlr3cGDkzcSP8bw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-musl/-/rollup-linux-x64-musl-4.34.6.tgz",
+      "integrity": "sha512-zmmpOQh8vXc2QITsnCiODCDGXFC8LMi64+/oPpPx5qz3pqv0s6x46ps4xoycfUiVZps5PFn1gksZzo4RGTKT+A==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-win32-arm64-msvc": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-arm64-msvc/-/rollup-win32-arm64-msvc-4.28.0.tgz",
-      "integrity": "sha512-Vi+WR62xWGsE/Oj+mD0FNAPY2MEox3cfyG0zLpotZdehPFXwz6lypkGs5y38Jd/NVSbOD02aVad6q6QYF7i8Bg==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-arm64-msvc/-/rollup-win32-arm64-msvc-4.34.6.tgz",
+      "integrity": "sha512-3/q1qUsO/tLqGBaD4uXsB6coVGB3usxw3qyeVb59aArCgedSF66MPdgRStUd7vbZOsko/CgVaY5fo2vkvPLWiA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
       ]
     },
     "node_modules/@rollup/rollup-win32-ia32-msvc": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-ia32-msvc/-/rollup-win32-ia32-msvc-4.28.0.tgz",
-      "integrity": "sha512-kN/Vpip8emMLn/eOza+4JwqDZBL6MPNpkdaEsgUtW1NYN3DZvZqSQrbKzJcTL6hd8YNmFTn7XGWMwccOcJBL0A==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-ia32-msvc/-/rollup-win32-ia32-msvc-4.34.6.tgz",
+      "integrity": "sha512-oLHxuyywc6efdKVTxvc0135zPrRdtYVjtVD5GUm55I3ODxhU/PwkQFD97z16Xzxa1Fz0AEe4W/2hzRtd+IfpOA==",
       "cpu": [
         "ia32"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
       ]
     },
     "node_modules/@rollup/rollup-win32-x64-msvc": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-msvc/-/rollup-win32-x64-msvc-4.28.0.tgz",
-      "integrity": "sha512-Bvno2/aZT6usSa7lRDL2+hMjVAGjuqaymF1ApZm31JXzniR/hvr14jpU+/z4X6Gt5BPlzosscyJZGUvguXIqeQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-msvc/-/rollup-win32-x64-msvc-4.34.6.tgz",
+      "integrity": "sha512-0PVwmgzZ8+TZ9oGBmdZoQVXflbvuwzN/HRclujpl4N/q3i+y0lqLw8n1bXA8ru3sApDjlmONaNAuYr38y1Kr9w==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -808,8 +795,7 @@
       "version": "1.0.6",
       "resolved": "https://registry.npmjs.org/@types/estree/-/estree-1.0.6.tgz",
       "integrity": "sha512-AYnb1nQyY49te+VRAVgmzfcgjYS91mY5P0TKUDCLEM+gNnA+3T6rWITXRLYCpahpqSQbN5cE+gHpnPyXjHWxcw==",
-      "dev": true,
-      "license": "MIT"
+      "dev": true
     },
     "node_modules/@types/events": {
       "version": "3.0.3",
@@ -847,12 +833,11 @@
       }
     },
     "node_modules/esbuild": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.24.0.tgz",
-      "integrity": "sha512-FuLPevChGDshgSicjisSooU0cemp/sGXR841D5LHMB7mTVOmsEHcAxaH3irL53+8YDIeVNQEySh4DaYU/iuPqQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.24.2.tgz",
+      "integrity": "sha512-+9egpBW8I3CD5XPe0n6BfT5fxLzxrlDzqydF3aviG+9ni1lDC/OvMHcxqEFV0+LANZG5R1bFMWfUrjVsdwxJvA==",
       "dev": true,
       "hasInstallScript": true,
-      "license": "MIT",
       "bin": {
         "esbuild": "bin/esbuild"
       },
@@ -860,30 +845,31 @@
         "node": ">=18"
       },
       "optionalDependencies": {
-        "@esbuild/aix-ppc64": "0.24.0",
-        "@esbuild/android-arm": "0.24.0",
-        "@esbuild/android-arm64": "0.24.0",
-        "@esbuild/android-x64": "0.24.0",
-        "@esbuild/darwin-arm64": "0.24.0",
-        "@esbuild/darwin-x64": "0.24.0",
-        "@esbuild/freebsd-arm64": "0.24.0",
-        "@esbuild/freebsd-x64": "0.24.0",
-        "@esbuild/linux-arm": "0.24.0",
-        "@esbuild/linux-arm64": "0.24.0",
-        "@esbuild/linux-ia32": "0.24.0",
-        "@esbuild/linux-loong64": "0.24.0",
-        "@esbuild/linux-mips64el": "0.24.0",
-        "@esbuild/linux-ppc64": "0.24.0",
-        "@esbuild/linux-riscv64": "0.24.0",
-        "@esbuild/linux-s390x": "0.24.0",
-        "@esbuild/linux-x64": "0.24.0",
-        "@esbuild/netbsd-x64": "0.24.0",
-        "@esbuild/openbsd-arm64": "0.24.0",
-        "@esbuild/openbsd-x64": "0.24.0",
-        "@esbuild/sunos-x64": "0.24.0",
-        "@esbuild/win32-arm64": "0.24.0",
-        "@esbuild/win32-ia32": "0.24.0",
-        "@esbuild/win32-x64": "0.24.0"
+        "@esbuild/aix-ppc64": "0.24.2",
+        "@esbuild/android-arm": "0.24.2",
+        "@esbuild/android-arm64": "0.24.2",
+        "@esbuild/android-x64": "0.24.2",
+        "@esbuild/darwin-arm64": "0.24.2",
+        "@esbuild/darwin-x64": "0.24.2",
+        "@esbuild/freebsd-arm64": "0.24.2",
+        "@esbuild/freebsd-x64": "0.24.2",
+        "@esbuild/linux-arm": "0.24.2",
+        "@esbuild/linux-arm64": "0.24.2",
+        "@esbuild/linux-ia32": "0.24.2",
+        "@esbuild/linux-loong64": "0.24.2",
+        "@esbuild/linux-mips64el": "0.24.2",
+        "@esbuild/linux-ppc64": "0.24.2",
+        "@esbuild/linux-riscv64": "0.24.2",
+        "@esbuild/linux-s390x": "0.24.2",
+        "@esbuild/linux-x64": "0.24.2",
+        "@esbuild/netbsd-arm64": "0.24.2",
+        "@esbuild/netbsd-x64": "0.24.2",
+        "@esbuild/openbsd-arm64": "0.24.2",
+        "@esbuild/openbsd-x64": "0.24.2",
+        "@esbuild/sunos-x64": "0.24.2",
+        "@esbuild/win32-arm64": "0.24.2",
+        "@esbuild/win32-ia32": "0.24.2",
+        "@esbuild/win32-x64": "0.24.2"
       }
     },
     "node_modules/events": {
@@ -901,7 +887,6 @@
       "integrity": "sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==",
       "dev": true,
       "hasInstallScript": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
@@ -951,7 +936,6 @@
           "url": "https://github.com/sponsors/ai"
         }
       ],
-      "license": "MIT",
       "bin": {
         "nanoid": "bin/nanoid.cjs"
       },
@@ -963,13 +947,12 @@
       "version": "1.1.1",
       "resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz",
       "integrity": "sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA==",
-      "dev": true,
-      "license": "ISC"
+      "dev": true
     },
     "node_modules/postcss": {
-      "version": "8.4.49",
-      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.4.49.tgz",
-      "integrity": "sha512-OCVPnIObs4N29kxTjzLfUryOkvZEq+pf8jTF0lg8E7uETuWHA+v7j3c/xJmiqpX450191LlmZfUKkXxkTry7nA==",
+      "version": "8.5.2",
+      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.2.tgz",
+      "integrity": "sha512-MjOadfU3Ys9KYoX0AdkBlFEF1Vx37uCCeN4ZHnmwm9FfpbsGWMZeBLMmmpY+6Ocqod7mkdZ0DT31OlbsFrLlkA==",
       "dev": true,
       "funding": [
         {
@@ -985,9 +968,8 @@
           "url": "https://github.com/sponsors/ai"
         }
       ],
-      "license": "MIT",
       "dependencies": {
-        "nanoid": "^3.3.7",
+        "nanoid": "^3.3.8",
         "picocolors": "^1.1.1",
         "source-map-js": "^1.2.1"
       },
@@ -1002,11 +984,10 @@
       "license": "MIT"
     },
     "node_modules/rollup": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/rollup/-/rollup-4.28.0.tgz",
-      "integrity": "sha512-G9GOrmgWHBma4YfCcX8PjH0qhXSdH8B4HDE2o4/jaxj93S4DPCIDoLcXz99eWMji4hB29UFCEd7B2gwGJDR9cQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/rollup/-/rollup-4.34.6.tgz",
+      "integrity": "sha512-wc2cBWqJgkU3Iz5oztRkQbfVkbxoz5EhnCGOrnJvnLnQ7O0WhQUYyv18qQI79O8L7DdHrrlJNeCHd4VGpnaXKQ==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
         "@types/estree": "1.0.6"
       },
@@ -1018,24 +999,25 @@
         "npm": ">=8.0.0"
       },
       "optionalDependencies": {
-        "@rollup/rollup-android-arm-eabi": "4.28.0",
-        "@rollup/rollup-android-arm64": "4.28.0",
-        "@rollup/rollup-darwin-arm64": "4.28.0",
-        "@rollup/rollup-darwin-x64": "4.28.0",
-        "@rollup/rollup-freebsd-arm64": "4.28.0",
-        "@rollup/rollup-freebsd-x64": "4.28.0",
-        "@rollup/rollup-linux-arm-gnueabihf": "4.28.0",
-        "@rollup/rollup-linux-arm-musleabihf": "4.28.0",
-        "@rollup/rollup-linux-arm64-gnu": "4.28.0",
-        "@rollup/rollup-linux-arm64-musl": "4.28.0",
-        "@rollup/rollup-linux-powerpc64le-gnu": "4.28.0",
-        "@rollup/rollup-linux-riscv64-gnu": "4.28.0",
-        "@rollup/rollup-linux-s390x-gnu": "4.28.0",
-        "@rollup/rollup-linux-x64-gnu": "4.28.0",
-        "@rollup/rollup-linux-x64-musl": "4.28.0",
-        "@rollup/rollup-win32-arm64-msvc": "4.28.0",
-        "@rollup/rollup-win32-ia32-msvc": "4.28.0",
-        "@rollup/rollup-win32-x64-msvc": "4.28.0",
+        "@rollup/rollup-android-arm-eabi": "4.34.6",
+        "@rollup/rollup-android-arm64": "4.34.6",
+        "@rollup/rollup-darwin-arm64": "4.34.6",
+        "@rollup/rollup-darwin-x64": "4.34.6",
+        "@rollup/rollup-freebsd-arm64": "4.34.6",
+        "@rollup/rollup-freebsd-x64": "4.34.6",
+        "@rollup/rollup-linux-arm-gnueabihf": "4.34.6",
+        "@rollup/rollup-linux-arm-musleabihf": "4.34.6",
+        "@rollup/rollup-linux-arm64-gnu": "4.34.6",
+        "@rollup/rollup-linux-arm64-musl": "4.34.6",
+        "@rollup/rollup-linux-loongarch64-gnu": "4.34.6",
+        "@rollup/rollup-linux-powerpc64le-gnu": "4.34.6",
+        "@rollup/rollup-linux-riscv64-gnu": "4.34.6",
+        "@rollup/rollup-linux-s390x-gnu": "4.34.6",
+        "@rollup/rollup-linux-x64-gnu": "4.34.6",
+        "@rollup/rollup-linux-x64-musl": "4.34.6",
+        "@rollup/rollup-win32-arm64-msvc": "4.34.6",
+        "@rollup/rollup-win32-ia32-msvc": "4.34.6",
+        "@rollup/rollup-win32-x64-msvc": "4.34.6",
         "fsevents": "~2.3.2"
       }
     },
@@ -1066,7 +1048,6 @@
       "resolved": "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.1.tgz",
       "integrity": "sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==",
       "dev": true,
-      "license": "BSD-3-Clause",
       "engines": {
         "node": ">=0.10.0"
       }
@@ -1101,15 +1082,14 @@
       }
     },
     "node_modules/vite": {
-      "version": "6.0.2",
-      "resolved": "https://registry.npmjs.org/vite/-/vite-6.0.2.tgz",
-      "integrity": "sha512-XdQ+VsY2tJpBsKGs0wf3U/+azx8BBpYRHFAyKm5VeEZNOJZRB63q7Sc8Iup3k0TrN3KO6QgyzFf+opSbfY1y0g==",
+      "version": "6.1.0",
+      "resolved": "https://registry.npmjs.org/vite/-/vite-6.1.0.tgz",
+      "integrity": "sha512-RjjMipCKVoR4hVfPY6GQTgveinjNuyLw+qruksLDvA5ktI1150VmcMBKmQaEWJhg/j6Uaf6dNCNA0AfdzUb/hQ==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
-        "esbuild": "^0.24.0",
-        "postcss": "^8.4.49",
-        "rollup": "^4.23.0"
+        "esbuild": "^0.24.2",
+        "postcss": "^8.5.1",
+        "rollup": "^4.30.1"
       },
       "bin": {
         "vite": "bin/vite.js"

examples/news-chatbot/client/javascript/package.json

@@ -12,7 +12,7 @@
   "license": "ISC",
   "description": "",
   "devDependencies": {
-    "vite": "^6.0.2"
+    "vite": "^6.0.9"
   },
   "dependencies": {
     "@pipecat-ai/client-js": "^0.3.2",

examples/news-chatbot/server/news_bot.py

@@ -23,7 +23,7 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.deepgram import DeepgramSTTService
-from pipecat.services.google import GoogleLLMService, LLMSearchResponseFrame
+from pipecat.services.google import GoogleLLMService, GoogleRTVIObserver, LLMSearchResponseFrame
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 from pipecat.utils.text.markdown_text_filter import MarkdownTextFilter
 
@@ -102,6 +102,7 @@ async def main():
 
         llm = GoogleLLMService(
             api_key=os.getenv("GOOGLE_API_KEY"),
+            model="gemini-1.5-flash-002",
             system_instruction=system_instruction,
             tools=tools,
         )
@@ -141,7 +142,7 @@ async def main():
             pipeline,
             PipelineParams(
                 allow_interruptions=True,
-                observers=[rtvi.observer()],
+                observers=[GoogleRTVIObserver(rtvi)],
             ),
         )
 

examples/phone-chatbot/README.md

@@ -1,3 +1,5 @@
+<!-- @format -->
+
 <div align="center">
  <img alt="pipecat" width="300px" height="auto" src="image.png">
 </div>
@@ -104,6 +106,21 @@ curl -X POST "http://localhost:7860/daily_start_bot" \
      -d '{"dialoutNumber": "+18057145330", "detectVoicemail": true}'
 ```
 
+### New! Using Gemini with Daily
+
+We have introduced a new example file that uses Gemini. You can find the code within bot_daily_gemini.py.
+If you want to spin up a Gemini-based bot for this demo, instead of an OpenAI-based bot, call the same properties above but on the `daily_gemini_start_bot` endpoint instead.
+
+For example:
+
+```shell
+curl -X POST "http://localhost:7860/daily_gemini_start_bot" \                                                                                                        py pipecat
+     -H "Content-Type: application/json" \
+     -d '{"detectVoicemail": true}'
+```
+
+Any request body properties supported by `/daily_start_bot` (such as "detectVoicemail", "dialoutnumber", etc) can also be passed to `/daily_gemini_start_bot`. The only difference is that calling the Gemini endpoint will start a Gemini bot session.
+
 ### More information
 
 For more configuration options, please consult [Daily's API documentation](https://docs.daily.co).

examples/phone-chatbot/bot_daily.py

@@ -98,6 +98,7 @@ async def main(
             - **"Record your message after the tone."**
             - **Any phrase that suggests an answering machine or voicemail.**
             - **ASSUME IT IS A VOICEMAIL. DO NOT WAIT FOR MORE CONFIRMATION.**
+            - **IF THE CALL SAYS "PLEASE LEAVE A MESSAGE AFTER THE BEEP", WAIT FOR THE BEEP BEFORE LEAVING A MESSAGE.**
 
             #### **Step 2: Leave a Voicemail Message**
             - Immediately say:
@@ -110,7 +111,9 @@ async def main(
             - If the call is answered by a human, say:
             *"Oh, hello! I'm a friendly chatbot. Is there anything I can help you with?"*
             - Keep responses **brief and helpful**.
-            - If the user no longer needs assistance, **call `terminate_call` immediately.**
+            - If the user no longer needs assistance, say:
+            *"Okay, thank you! Have a great day!"*
+            -**Then call `terminate_call` immediately.**
 
             ---
 

examples/phone-chatbot/bot_daily_gemini.py

@@ -0,0 +1,234 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+import argparse
+import asyncio
+import os
+import sys
+from typing import Optional
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndTaskFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.frame_processor import FrameDirection
+from pipecat.services.ai_services import LLMService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.google import GoogleLLMContext, GoogleLLMService
+from pipecat.transports.services.daily import DailyDialinSettings, DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+daily_api_key = os.getenv("DAILY_API_KEY", "")
+daily_api_url = os.getenv("DAILY_API_URL", "https://api.daily.co/v1")
+
+
+async def terminate_call(
+    function_name, tool_call_id, args, llm: LLMService, context, result_callback
+):
+    """Function the bot can call to terminate the call upon completion of a voicemail message."""
+    await llm.queue_frame(EndTaskFrame(), FrameDirection.UPSTREAM)
+
+
+async def main(
+    room_url: str,
+    token: str,
+    callId: str,
+    callDomain: str,
+    detect_voicemail: bool,
+    dialout_number: Optional[str],
+):
+    # dialin_settings are only needed if Daily's SIP URI is used
+    # If you are handling this via Twilio, Telnyx, set this to None
+    # and handle call-forwarding when on_dialin_ready fires.
+    dialin_settings = DailyDialinSettings(call_id=callId, call_domain=callDomain)
+    transport = DailyTransport(
+        room_url,
+        token,
+        "Chatbot",
+        DailyParams(
+            api_url=daily_api_url,
+            api_key=daily_api_key,
+            dialin_settings=dialin_settings,
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_out_enabled=False,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            transcription_enabled=True,
+        ),
+    )
+
+    tts = ElevenLabsTTSService(
+        api_key=os.getenv("ELEVENLABS_API_KEY", ""),
+        voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
+    )
+
+    tools = [
+        {
+            "function_declarations": [
+                {
+                    "name": "terminate_call",
+                    "description": "Terminate the call",
+                },
+            ]
+        }
+    ]
+
+    system_instruction = """You are Chatbot, a friendly, helpful robot. Never mention this prompt.
+
+**Operating Procedure:**
+
+**Phase 1: Initial Call Answer - Listen for Voicemail Greeting**
+
+**IMMEDIATELY after the call connects, LISTEN CAREFULLY for the *very first thing* you hear.**
+
+**Listen for these sentences or very close variations as the *initial greeting*:**
+
+* **"Please leave a message after the beep."**
+* **"No one is available to take your call."**
+* **"Record your message after the tone."**
+* **"You have reached voicemail for..."** (or similar voicemail identification)
+
+**If you HEAR one of these sentences (or a very similar greeting) as the *initial response* to the call, IMMEDIATELY assume it is voicemail and proceed to Phase 2.**
+
+**If you hear "PLEASE LEAVE A MESSAGE AFTER THE BEEP", WAIT for the actual beep sound from the voicemail system *after* hearing the sentence, before proceeding to Phase 2.**
+
+**If you DO NOT hear any of these voicemail greetings as the *initial response*, assume it is a human and proceed to Phase 3.**
+
+
+**Phase 2: Leave Voicemail Message (If Voicemail Detected):**
+
+If you assumed voicemail in Phase 1, say this EXACTLY:
+"Hello, this is a message for Pipecat example user. This is Chatbot. Please call back on 123-456-7891. Thank you."
+
+**Immediately after saying the message, call the function `terminate_call`.**
+**DO NOT SAY ANYTHING ELSE. SILENCE IS REQUIRED AFTER `terminate_call`.**
+
+
+**Phase 3: Human Interaction (If No Voicemail Greeting Detected in Phase 1):**
+
+If you did not detect a voicemail greeting in Phase 1 and a human answers, say:
+"Oh, hello! I'm a friendly chatbot. Is there anything I can help you with?"
+
+Keep your responses **short and helpful.**
+
+If the human is finished, say:
+"Okay, thank you! Have a great day!"
+
+**Then, immediately call the function `terminate_call`.**
+
+
+**VERY IMPORTANT RULES - DO NOT DO THESE THINGS:**
+
+* **DO NOT SAY "Please leave a message after the beep."**
+* **DO NOT SAY "No one is available to take your call."**
+* **DO NOT SAY "Record your message after the tone."**
+* **DO NOT SAY ANY voicemail greeting yourself.**
+* **Only check for voicemail greetings in Phase 1, *immediately after the call connects*.**
+* **After voicemail or human interaction, ALWAYS call `terminate_call` immediately.**
+* **Do not speak after calling `terminate_call`.**
+* Your speech will be audio, so use simple language without special characters.
+"""
+
+    llm = GoogleLLMService(
+        model="models/gemini-2.0-flash-exp",
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        system_instruction=system_instruction,
+        tools=tools,
+    )
+    llm.register_function("terminate_call", terminate_call)
+
+    context = GoogleLLMContext()
+
+    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),
+    )
+
+    if dialout_number:
+        logger.debug("dialout number detected; doing dialout")
+
+        # Configure some handlers for dialing out
+        @transport.event_handler("on_joined")
+        async def on_joined(transport, data):
+            logger.debug(f"Joined; starting dialout to: {dialout_number}")
+            await transport.start_dialout({"phoneNumber": dialout_number})
+
+        @transport.event_handler("on_dialout_connected")
+        async def on_dialout_connected(transport, data):
+            logger.debug(f"Dial-out connected: {data}")
+
+        @transport.event_handler("on_dialout_answered")
+        async def on_dialout_answered(transport, data):
+            logger.debug(f"Dial-out answered: {data}")
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # unlike the dialin case, for the dialout case, the caller will speak first. Presumably
+            # they will answer the phone and say "Hello?" Since we've captured their transcript,
+            # That will put a frame into the pipeline and prompt an LLM completion, which is how the
+            # bot will then greet the user.
+    elif detect_voicemail:
+        logger.debug("Detect voicemail example. You can test this in example in Daily Prebuilt")
+
+        # For the voicemail detection case, we do not want the bot to answer the phone. We want it to wait for the voicemail
+        # machine to say something like 'Leave a message after the beep', or for the user to say 'Hello?'.
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+    else:
+        logger.debug("no dialout number; assuming dialin")
+
+        # Different handlers for dialin
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # For the dialin case, we want the bot to answer the phone and greet the user. We
+            # can prompt the bot to speak by putting the context into the pipeline.
+            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.cancel()
+
+    runner = PipelineRunner()
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Pipecat Simple ChatBot")
+    parser.add_argument("-u", type=str, help="Room URL")
+    parser.add_argument("-t", type=str, help="Token")
+    parser.add_argument("-i", type=str, help="Call ID")
+    parser.add_argument("-d", type=str, help="Call Domain")
+    parser.add_argument("-v", action="store_true", help="Detect voicemail")
+    parser.add_argument("-o", type=str, help="Dialout number", default=None)
+    config = parser.parse_args()
+
+    asyncio.run(main(config.u, config.t, config.i, config.d, config.v, config.o))

examples/phone-chatbot/bot_runner.py

@@ -110,10 +110,15 @@ async def _create_daily_room(
 
     # Spawn a new agent, and join the user session
     # Note: this is mostly for demonstration purposes (refer to 'deployment' in docs)
+    print(f"Vendor: {vendor}")
     if vendor == "daily":
         bot_proc = f"python3 -m bot_daily -u {room.url} -t {token} -i {callId} -d {callDomain}{' -v' if detect_voicemail else ''}"
         if dialoutNumber:
             bot_proc += f" -o {dialoutNumber}"
+    elif vendor == "daily-gemini":
+        bot_proc = f"python3 -m bot_daily_gemini -u {room.url} -t {token} -i {callId} -d {callDomain}{' -v' if detect_voicemail else ''}"
+        if dialoutNumber:
+            bot_proc += f" -o {dialoutNumber}"
     else:
         bot_proc = f"python3 -m bot_twilio -u {room.url} -t {token} -i {callId} -s {room.config.sip_endpoint}"
 
@@ -201,6 +206,38 @@ async def daily_start_bot(request: Request) -> JSONResponse:
     return JSONResponse({"room_url": room.url, "sipUri": room.config.sip_endpoint})
 
 
+@app.post("/daily_gemini_start_bot")
+async def daily_gemini_start_bot(request: Request) -> JSONResponse:
+    # The /daily_start_bot is invoked when a call is received on Daily's SIP URI
+    # daily_start_bot will create the room, put the call on hold until
+    # the bot and sip worker are ready. Daily will automatically
+    # forward the call to the SIP URi when dialin_ready fires.
+
+    # Use specified room URL, or create a new one if not specified
+    room_url = os.getenv("DAILY_SAMPLE_ROOM_URL", None)
+    # Get the dial-in properties from the request
+    try:
+        data = await request.json()
+        if "test" in data:
+            # Pass through any webhook checks
+            return JSONResponse({"test": True})
+        detect_voicemail = data.get("detectVoicemail", False)
+        callId = data.get("callId", None)
+        callDomain = data.get("callDomain", None)
+        dialoutNumber = data.get("dialoutNumber", None)
+    except Exception:
+        raise HTTPException(
+            status_code=500, detail="Missing properties 'callId', 'callDomain', or 'dialoutNumber'"
+        )
+
+    room: DailyRoomObject = await _create_daily_room(
+        room_url, callId, callDomain, dialoutNumber, "daily-gemini", detect_voicemail
+    )
+
+    # Grab a token for the user to join with
+    return JSONResponse({"room_url": room.url, "sipUri": room.config.sip_endpoint})
+
+
 # ----------------- Main ----------------- #
 
 

examples/simple-chatbot/client/javascript/package-lock.json

@@ -13,7 +13,7 @@
         "@pipecat-ai/daily-transport": "^0.3.4"
       },
       "devDependencies": {
-        "vite": "^6.0.2"
+        "vite": "^6.0.9"
       }
     },
     "node_modules/@babel/runtime": {
@@ -45,14 +45,13 @@
       }
     },
     "node_modules/@esbuild/aix-ppc64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.24.0.tgz",
-      "integrity": "sha512-WtKdFM7ls47zkKHFVzMz8opM7LkcsIp9amDUBIAWirg70RM71WRSjdILPsY5Uv1D42ZpUfaPILDlfactHgsRkw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.24.2.tgz",
+      "integrity": "sha512-thpVCb/rhxE/BnMLQ7GReQLLN8q9qbHmI55F4489/ByVg2aQaQ6kbcLb6FHkocZzQhxc4gx0sCk0tJkKBFzDhA==",
       "cpu": [
         "ppc64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "aix"
@@ -62,14 +61,13 @@
       }
     },
     "node_modules/@esbuild/android-arm": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.24.0.tgz",
-      "integrity": "sha512-arAtTPo76fJ/ICkXWetLCc9EwEHKaeya4vMrReVlEIUCAUncH7M4bhMQ+M9Vf+FFOZJdTNMXNBrWwW+OXWpSew==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.24.2.tgz",
+      "integrity": "sha512-tmwl4hJkCfNHwFB3nBa8z1Uy3ypZpxqxfTQOcHX+xRByyYgunVbZ9MzUUfb0RxaHIMnbHagwAxuTL+tnNM+1/Q==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
@@ -79,14 +77,13 @@
       }
     },
     "node_modules/@esbuild/android-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.24.0.tgz",
-      "integrity": "sha512-Vsm497xFM7tTIPYK9bNTYJyF/lsP590Qc1WxJdlB6ljCbdZKU9SY8i7+Iin4kyhV/KV5J2rOKsBQbB77Ab7L/w==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.24.2.tgz",
+      "integrity": "sha512-cNLgeqCqV8WxfcTIOeL4OAtSmL8JjcN6m09XIgro1Wi7cF4t/THaWEa7eL5CMoMBdjoHOTh/vwTO/o2TRXIyzg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
@@ -96,14 +93,13 @@
       }
     },
     "node_modules/@esbuild/android-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.24.0.tgz",
-      "integrity": "sha512-t8GrvnFkiIY7pa7mMgJd7p8p8qqYIz1NYiAoKc75Zyv73L3DZW++oYMSHPRarcotTKuSs6m3hTOa5CKHaS02TQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.24.2.tgz",
+      "integrity": "sha512-B6Q0YQDqMx9D7rvIcsXfmJfvUYLoP722bgfBlO5cGvNVb5V/+Y7nhBE3mHV9OpxBf4eAS2S68KZztiPaWq4XYw==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
@@ -113,14 +109,13 @@
       }
     },
     "node_modules/@esbuild/darwin-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.24.0.tgz",
-      "integrity": "sha512-CKyDpRbK1hXwv79soeTJNHb5EiG6ct3efd/FTPdzOWdbZZfGhpbcqIpiD0+vwmpu0wTIL97ZRPZu8vUt46nBSw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.24.2.tgz",
+      "integrity": "sha512-kj3AnYWc+CekmZnS5IPu9D+HWtUI49hbnyqk0FLEJDbzCIQt7hg7ucF1SQAilhtYpIujfaHr6O0UHlzzSPdOeA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
@@ -130,14 +125,13 @@
       }
     },
     "node_modules/@esbuild/darwin-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.24.0.tgz",
-      "integrity": "sha512-rgtz6flkVkh58od4PwTRqxbKH9cOjaXCMZgWD905JOzjFKW+7EiUObfd/Kav+A6Gyud6WZk9w+xu6QLytdi2OA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.24.2.tgz",
+      "integrity": "sha512-WeSrmwwHaPkNR5H3yYfowhZcbriGqooyu3zI/3GGpF8AyUdsrrP0X6KumITGA9WOyiJavnGZUwPGvxvwfWPHIA==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
@@ -147,14 +141,13 @@
       }
     },
     "node_modules/@esbuild/freebsd-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.24.0.tgz",
-      "integrity": "sha512-6Mtdq5nHggwfDNLAHkPlyLBpE5L6hwsuXZX8XNmHno9JuL2+bg2BX5tRkwjyfn6sKbxZTq68suOjgWqCicvPXA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.24.2.tgz",
+      "integrity": "sha512-UN8HXjtJ0k/Mj6a9+5u6+2eZ2ERD7Edt1Q9IZiB5UZAIdPnVKDoG7mdTVGhHJIeEml60JteamR3qhsr1r8gXvg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
@@ -164,14 +157,13 @@
       }
     },
     "node_modules/@esbuild/freebsd-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.24.0.tgz",
-      "integrity": "sha512-D3H+xh3/zphoX8ck4S2RxKR6gHlHDXXzOf6f/9dbFt/NRBDIE33+cVa49Kil4WUjxMGW0ZIYBYtaGCa2+OsQwQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.24.2.tgz",
+      "integrity": "sha512-TvW7wE/89PYW+IevEJXZ5sF6gJRDY/14hyIGFXdIucxCsbRmLUcjseQu1SyTko+2idmCw94TgyaEZi9HUSOe3Q==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
@@ -181,14 +173,13 @@
       }
     },
     "node_modules/@esbuild/linux-arm": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.24.0.tgz",
-      "integrity": "sha512-gJKIi2IjRo5G6Glxb8d3DzYXlxdEj2NlkixPsqePSZMhLudqPhtZ4BUrpIuTjJYXxvF9njql+vRjB2oaC9XpBw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.24.2.tgz",
+      "integrity": "sha512-n0WRM/gWIdU29J57hJyUdIsk0WarGd6To0s+Y+LwvlC55wt+GT/OgkwoXCXvIue1i1sSNWblHEig00GBWiJgfA==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -198,14 +189,13 @@
       }
     },
     "node_modules/@esbuild/linux-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.24.0.tgz",
-      "integrity": "sha512-TDijPXTOeE3eaMkRYpcy3LarIg13dS9wWHRdwYRnzlwlA370rNdZqbcp0WTyyV/k2zSxfko52+C7jU5F9Tfj1g==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.24.2.tgz",
+      "integrity": "sha512-7HnAD6074BW43YvvUmE/35Id9/NB7BeX5EoNkK9obndmZBUk8xmJJeU7DwmUeN7tkysslb2eSl6CTrYz6oEMQg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -215,14 +205,13 @@
       }
     },
     "node_modules/@esbuild/linux-ia32": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.24.0.tgz",
-      "integrity": "sha512-K40ip1LAcA0byL05TbCQ4yJ4swvnbzHscRmUilrmP9Am7//0UjPreh4lpYzvThT2Quw66MhjG//20mrufm40mA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.24.2.tgz",
+      "integrity": "sha512-sfv0tGPQhcZOgTKO3oBE9xpHuUqguHvSo4jl+wjnKwFpapx+vUDcawbwPNuBIAYdRAvIDBfZVvXprIj3HA+Ugw==",
       "cpu": [
         "ia32"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -232,14 +221,13 @@
       }
     },
     "node_modules/@esbuild/linux-loong64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.24.0.tgz",
-      "integrity": "sha512-0mswrYP/9ai+CU0BzBfPMZ8RVm3RGAN/lmOMgW4aFUSOQBjA31UP8Mr6DDhWSuMwj7jaWOT0p0WoZ6jeHhrD7g==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.24.2.tgz",
+      "integrity": "sha512-CN9AZr8kEndGooS35ntToZLTQLHEjtVB5n7dl8ZcTZMonJ7CCfStrYhrzF97eAecqVbVJ7APOEe18RPI4KLhwQ==",
       "cpu": [
         "loong64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -249,14 +237,13 @@
       }
     },
     "node_modules/@esbuild/linux-mips64el": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.24.0.tgz",
-      "integrity": "sha512-hIKvXm0/3w/5+RDtCJeXqMZGkI2s4oMUGj3/jM0QzhgIASWrGO5/RlzAzm5nNh/awHE0A19h/CvHQe6FaBNrRA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.24.2.tgz",
+      "integrity": "sha512-iMkk7qr/wl3exJATwkISxI7kTcmHKE+BlymIAbHO8xanq/TjHaaVThFF6ipWzPHryoFsesNQJPE/3wFJw4+huw==",
       "cpu": [
         "mips64el"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -266,14 +253,13 @@
       }
     },
     "node_modules/@esbuild/linux-ppc64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.24.0.tgz",
-      "integrity": "sha512-HcZh5BNq0aC52UoocJxaKORfFODWXZxtBaaZNuN3PUX3MoDsChsZqopzi5UupRhPHSEHotoiptqikjN/B77mYQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.24.2.tgz",
+      "integrity": "sha512-shsVrgCZ57Vr2L8mm39kO5PPIb+843FStGt7sGGoqiiWYconSxwTiuswC1VJZLCjNiMLAMh34jg4VSEQb+iEbw==",
       "cpu": [
         "ppc64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -283,14 +269,13 @@
       }
     },
     "node_modules/@esbuild/linux-riscv64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.24.0.tgz",
-      "integrity": "sha512-bEh7dMn/h3QxeR2KTy1DUszQjUrIHPZKyO6aN1X4BCnhfYhuQqedHaa5MxSQA/06j3GpiIlFGSsy1c7Gf9padw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.24.2.tgz",
+      "integrity": "sha512-4eSFWnU9Hhd68fW16GD0TINewo1L6dRrB+oLNNbYyMUAeOD2yCK5KXGK1GH4qD/kT+bTEXjsyTCiJGHPZ3eM9Q==",
       "cpu": [
         "riscv64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -300,14 +285,13 @@
       }
     },
     "node_modules/@esbuild/linux-s390x": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.24.0.tgz",
-      "integrity": "sha512-ZcQ6+qRkw1UcZGPyrCiHHkmBaj9SiCD8Oqd556HldP+QlpUIe2Wgn3ehQGVoPOvZvtHm8HPx+bH20c9pvbkX3g==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.24.2.tgz",
+      "integrity": "sha512-S0Bh0A53b0YHL2XEXC20bHLuGMOhFDO6GN4b3YjRLK//Ep3ql3erpNcPlEFed93hsQAjAQDNsvcK+hV90FubSw==",
       "cpu": [
         "s390x"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -317,14 +301,13 @@
       }
     },
     "node_modules/@esbuild/linux-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.24.0.tgz",
-      "integrity": "sha512-vbutsFqQ+foy3wSSbmjBXXIJ6PL3scghJoM8zCL142cGaZKAdCZHyf+Bpu/MmX9zT9Q0zFBVKb36Ma5Fzfa8xA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.24.2.tgz",
+      "integrity": "sha512-8Qi4nQcCTbLnK9WoMjdC9NiTG6/E38RNICU6sUNqK0QFxCYgoARqVqxdFmWkdonVsvGqWhmm7MO0jyTqLqwj0Q==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -333,15 +316,30 @@
         "node": ">=18"
       }
     },
+    "node_modules/@esbuild/netbsd-arm64": {
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.24.2.tgz",
+      "integrity": "sha512-wuLK/VztRRpMt9zyHSazyCVdCXlpHkKm34WUyinD2lzK07FAHTq0KQvZZlXikNWkDGoT6x3TD51jKQ7gMVpopw==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "optional": true,
+      "os": [
+        "netbsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
     "node_modules/@esbuild/netbsd-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.24.0.tgz",
-      "integrity": "sha512-hjQ0R/ulkO8fCYFsG0FZoH+pWgTTDreqpqY7UnQntnaKv95uP5iW3+dChxnx7C3trQQU40S+OgWhUVwCjVFLvg==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.24.2.tgz",
+      "integrity": "sha512-VefFaQUc4FMmJuAxmIHgUmfNiLXY438XrL4GDNV1Y1H/RW3qow68xTwjZKfj/+Plp9NANmzbH5R40Meudu8mmw==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "netbsd"
@@ -351,14 +349,13 @@
       }
     },
     "node_modules/@esbuild/openbsd-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.24.0.tgz",
-      "integrity": "sha512-MD9uzzkPQbYehwcN583yx3Tu5M8EIoTD+tUgKF982WYL9Pf5rKy9ltgD0eUgs8pvKnmizxjXZyLt0z6DC3rRXg==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.24.2.tgz",
+      "integrity": "sha512-YQbi46SBct6iKnszhSvdluqDmxCJA+Pu280Av9WICNwQmMxV7nLRHZfjQzwbPs3jeWnuAhE9Jy0NrnJ12Oz+0A==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "openbsd"
@@ -368,14 +365,13 @@
       }
     },
     "node_modules/@esbuild/openbsd-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.24.0.tgz",
-      "integrity": "sha512-4ir0aY1NGUhIC1hdoCzr1+5b43mw99uNwVzhIq1OY3QcEwPDO3B7WNXBzaKY5Nsf1+N11i1eOfFcq+D/gOS15Q==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.24.2.tgz",
+      "integrity": "sha512-+iDS6zpNM6EnJyWv0bMGLWSWeXGN/HTaF/LXHXHwejGsVi+ooqDfMCCTerNFxEkM3wYVcExkeGXNqshc9iMaOA==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "openbsd"
@@ -385,14 +381,13 @@
       }
     },
     "node_modules/@esbuild/sunos-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.24.0.tgz",
-      "integrity": "sha512-jVzdzsbM5xrotH+W5f1s+JtUy1UWgjU0Cf4wMvffTB8m6wP5/kx0KiaLHlbJO+dMgtxKV8RQ/JvtlFcdZ1zCPA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.24.2.tgz",
+      "integrity": "sha512-hTdsW27jcktEvpwNHJU4ZwWFGkz2zRJUz8pvddmXPtXDzVKTTINmlmga3ZzwcuMpUvLw7JkLy9QLKyGpD2Yxig==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "sunos"
@@ -402,14 +397,13 @@
       }
     },
     "node_modules/@esbuild/win32-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.24.0.tgz",
-      "integrity": "sha512-iKc8GAslzRpBytO2/aN3d2yb2z8XTVfNV0PjGlCxKo5SgWmNXx82I/Q3aG1tFfS+A2igVCY97TJ8tnYwpUWLCA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.24.2.tgz",
+      "integrity": "sha512-LihEQ2BBKVFLOC9ZItT9iFprsE9tqjDjnbulhHoFxYQtQfai7qfluVODIYxt1PgdoyQkz23+01rzwNwYfutxUQ==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -419,14 +413,13 @@
       }
     },
     "node_modules/@esbuild/win32-ia32": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.24.0.tgz",
-      "integrity": "sha512-vQW36KZolfIudCcTnaTpmLQ24Ha1RjygBo39/aLkM2kmjkWmZGEJ5Gn9l5/7tzXA42QGIoWbICfg6KLLkIw6yw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.24.2.tgz",
+      "integrity": "sha512-q+iGUwfs8tncmFC9pcnD5IvRHAzmbwQ3GPS5/ceCyHdjXubwQWI12MKWSNSMYLJMq23/IUCvJMS76PDqXe1fxA==",
       "cpu": [
         "ia32"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -436,14 +429,13 @@
       }
     },
     "node_modules/@esbuild/win32-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.24.0.tgz",
-      "integrity": "sha512-7IAFPrjSQIJrGsK6flwg7NFmwBoSTyF3rl7If0hNUFQU4ilTsEPL6GuMuU9BfIWVVGuRnuIidkSMC+c0Otu8IA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.24.2.tgz",
+      "integrity": "sha512-7VTgWzgMGvup6aSqDPLiW5zHaxYJGTO4OokMjIlrCtf+VpEL+cXKtCvg723iguPYI5oaUNdS+/V7OU2gvXVWEg==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -478,252 +470,247 @@
       }
     },
     "node_modules/@rollup/rollup-android-arm-eabi": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm-eabi/-/rollup-android-arm-eabi-4.28.0.tgz",
-      "integrity": "sha512-wLJuPLT6grGZsy34g4N1yRfYeouklTgPhH1gWXCYspenKYD0s3cR99ZevOGw5BexMNywkbV3UkjADisozBmpPQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm-eabi/-/rollup-android-arm-eabi-4.34.6.tgz",
+      "integrity": "sha512-+GcCXtOQoWuC7hhX1P00LqjjIiS/iOouHXhMdiDSnq/1DGTox4SpUvO52Xm+div6+106r+TcvOeo/cxvyEyTgg==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
       ]
     },
     "node_modules/@rollup/rollup-android-arm64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm64/-/rollup-android-arm64-4.28.0.tgz",
-      "integrity": "sha512-eiNkznlo0dLmVG/6wf+Ifi/v78G4d4QxRhuUl+s8EWZpDewgk7PX3ZyECUXU0Zq/Ca+8nU8cQpNC4Xgn2gFNDA==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm64/-/rollup-android-arm64-4.34.6.tgz",
+      "integrity": "sha512-E8+2qCIjciYUnCa1AiVF1BkRgqIGW9KzJeesQqVfyRITGQN+dFuoivO0hnro1DjT74wXLRZ7QF8MIbz+luGaJA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
       ]
     },
     "node_modules/@rollup/rollup-darwin-arm64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-arm64/-/rollup-darwin-arm64-4.28.0.tgz",
-      "integrity": "sha512-lmKx9yHsppblnLQZOGxdO66gT77bvdBtr/0P+TPOseowE7D9AJoBw8ZDULRasXRWf1Z86/gcOdpBrV6VDUY36Q==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-arm64/-/rollup-darwin-arm64-4.34.6.tgz",
+      "integrity": "sha512-z9Ib+OzqN3DZEjX7PDQMHEhtF+t6Mi2z/ueChQPLS/qUMKY7Ybn5A2ggFoKRNRh1q1T03YTQfBTQCJZiepESAg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
       ]
     },
     "node_modules/@rollup/rollup-darwin-x64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-x64/-/rollup-darwin-x64-4.28.0.tgz",
-      "integrity": "sha512-8hxgfReVs7k9Js1uAIhS6zq3I+wKQETInnWQtgzt8JfGx51R1N6DRVy3F4o0lQwumbErRz52YqwjfvuwRxGv1w==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-x64/-/rollup-darwin-x64-4.34.6.tgz",
+      "integrity": "sha512-PShKVY4u0FDAR7jskyFIYVyHEPCPnIQY8s5OcXkdU8mz3Y7eXDJPdyM/ZWjkYdR2m0izD9HHWA8sGcXn+Qrsyg==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
       ]
     },
     "node_modules/@rollup/rollup-freebsd-arm64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-arm64/-/rollup-freebsd-arm64-4.28.0.tgz",
-      "integrity": "sha512-lA1zZB3bFx5oxu9fYud4+g1mt+lYXCoch0M0V/xhqLoGatbzVse0wlSQ1UYOWKpuSu3gyN4qEc0Dxf/DII1bhQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-arm64/-/rollup-freebsd-arm64-4.34.6.tgz",
+      "integrity": "sha512-YSwyOqlDAdKqs0iKuqvRHLN4SrD2TiswfoLfvYXseKbL47ht1grQpq46MSiQAx6rQEN8o8URtpXARCpqabqxGQ==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
       ]
     },
     "node_modules/@rollup/rollup-freebsd-x64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-x64/-/rollup-freebsd-x64-4.28.0.tgz",
-      "integrity": "sha512-aI2plavbUDjCQB/sRbeUZWX9qp12GfYkYSJOrdYTL/C5D53bsE2/nBPuoiJKoWp5SN78v2Vr8ZPnB+/VbQ2pFA==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-x64/-/rollup-freebsd-x64-4.34.6.tgz",
+      "integrity": "sha512-HEP4CgPAY1RxXwwL5sPFv6BBM3tVeLnshF03HMhJYCNc6kvSqBgTMmsEjb72RkZBAWIqiPUyF1JpEBv5XT9wKQ==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm-gnueabihf": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-gnueabihf/-/rollup-linux-arm-gnueabihf-4.28.0.tgz",
-      "integrity": "sha512-WXveUPKtfqtaNvpf0iOb0M6xC64GzUX/OowbqfiCSXTdi/jLlOmH0Ba94/OkiY2yTGTwteo4/dsHRfh5bDCZ+w==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-gnueabihf/-/rollup-linux-arm-gnueabihf-4.34.6.tgz",
+      "integrity": "sha512-88fSzjC5xeH9S2Vg3rPgXJULkHcLYMkh8faix8DX4h4TIAL65ekwuQMA/g2CXq8W+NJC43V6fUpYZNjaX3+IIg==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm-musleabihf": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-musleabihf/-/rollup-linux-arm-musleabihf-4.28.0.tgz",
-      "integrity": "sha512-yLc3O2NtOQR67lI79zsSc7lk31xjwcaocvdD1twL64PK1yNaIqCeWI9L5B4MFPAVGEVjH5k1oWSGuYX1Wutxpg==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-musleabihf/-/rollup-linux-arm-musleabihf-4.34.6.tgz",
+      "integrity": "sha512-wM4ztnutBqYFyvNeR7Av+reWI/enK9tDOTKNF+6Kk2Q96k9bwhDDOlnCUNRPvromlVXo04riSliMBs/Z7RteEg==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm64-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-gnu/-/rollup-linux-arm64-gnu-4.28.0.tgz",
-      "integrity": "sha512-+P9G9hjEpHucHRXqesY+3X9hD2wh0iNnJXX/QhS/J5vTdG6VhNYMxJ2rJkQOxRUd17u5mbMLHM7yWGZdAASfcg==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-gnu/-/rollup-linux-arm64-gnu-4.34.6.tgz",
+      "integrity": "sha512-9RyprECbRa9zEjXLtvvshhw4CMrRa3K+0wcp3KME0zmBe1ILmvcVHnypZ/aIDXpRyfhSYSuN4EPdCCj5Du8FIA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm64-musl": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-musl/-/rollup-linux-arm64-musl-4.28.0.tgz",
-      "integrity": "sha512-1xsm2rCKSTpKzi5/ypT5wfc+4bOGa/9yI/eaOLW0oMs7qpC542APWhl4A37AENGZ6St6GBMWhCCMM6tXgTIplw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-musl/-/rollup-linux-arm64-musl-4.34.6.tgz",
+      "integrity": "sha512-qTmklhCTyaJSB05S+iSovfo++EwnIEZxHkzv5dep4qoszUMX5Ca4WM4zAVUMbfdviLgCSQOu5oU8YoGk1s6M9Q==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@rollup/rollup-linux-loongarch64-gnu": {
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-loongarch64-gnu/-/rollup-linux-loongarch64-gnu-4.34.6.tgz",
+      "integrity": "sha512-4Qmkaps9yqmpjY5pvpkfOerYgKNUGzQpFxV6rnS7c/JfYbDSU0y6WpbbredB5cCpLFGJEqYX40WUmxMkwhWCjw==",
+      "cpu": [
+        "loong64"
+      ],
+      "dev": true,
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-powerpc64le-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-powerpc64le-gnu/-/rollup-linux-powerpc64le-gnu-4.28.0.tgz",
-      "integrity": "sha512-zgWxMq8neVQeXL+ouSf6S7DoNeo6EPgi1eeqHXVKQxqPy1B2NvTbaOUWPn/7CfMKL7xvhV0/+fq/Z/J69g1WAQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-powerpc64le-gnu/-/rollup-linux-powerpc64le-gnu-4.34.6.tgz",
+      "integrity": "sha512-Zsrtux3PuaxuBTX/zHdLaFmcofWGzaWW1scwLU3ZbW/X+hSsFbz9wDIp6XvnT7pzYRl9MezWqEqKy7ssmDEnuQ==",
       "cpu": [
         "ppc64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-riscv64-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-gnu/-/rollup-linux-riscv64-gnu-4.28.0.tgz",
-      "integrity": "sha512-VEdVYacLniRxbRJLNtzwGt5vwS0ycYshofI7cWAfj7Vg5asqj+pt+Q6x4n+AONSZW/kVm+5nklde0qs2EUwU2g==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-gnu/-/rollup-linux-riscv64-gnu-4.34.6.tgz",
+      "integrity": "sha512-aK+Zp+CRM55iPrlyKiU3/zyhgzWBxLVrw2mwiQSYJRobCURb781+XstzvA8Gkjg/hbdQFuDw44aUOxVQFycrAg==",
       "cpu": [
         "riscv64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-s390x-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-s390x-gnu/-/rollup-linux-s390x-gnu-4.28.0.tgz",
-      "integrity": "sha512-LQlP5t2hcDJh8HV8RELD9/xlYtEzJkm/aWGsauvdO2ulfl3QYRjqrKW+mGAIWP5kdNCBheqqqYIGElSRCaXfpw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-s390x-gnu/-/rollup-linux-s390x-gnu-4.34.6.tgz",
+      "integrity": "sha512-WoKLVrY9ogmaYPXwTH326+ErlCIgMmsoRSx6bO+l68YgJnlOXhygDYSZe/qbUJCSiCiZAQ+tKm88NcWuUXqOzw==",
       "cpu": [
         "s390x"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-x64-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.28.0.tgz",
-      "integrity": "sha512-Nl4KIzteVEKE9BdAvYoTkW19pa7LR/RBrT6F1dJCV/3pbjwDcaOq+edkP0LXuJ9kflW/xOK414X78r+K84+msw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.34.6.tgz",
+      "integrity": "sha512-Sht4aFvmA4ToHd2vFzwMFaQCiYm2lDFho5rPcvPBT5pCdC+GwHG6CMch4GQfmWTQ1SwRKS0dhDYb54khSrjDWw==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-x64-musl": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-musl/-/rollup-linux-x64-musl-4.28.0.tgz",
-      "integrity": "sha512-eKpJr4vBDOi4goT75MvW+0dXcNUqisK4jvibY9vDdlgLx+yekxSm55StsHbxUsRxSTt3JEQvlr3cGDkzcSP8bw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-musl/-/rollup-linux-x64-musl-4.34.6.tgz",
+      "integrity": "sha512-zmmpOQh8vXc2QITsnCiODCDGXFC8LMi64+/oPpPx5qz3pqv0s6x46ps4xoycfUiVZps5PFn1gksZzo4RGTKT+A==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-win32-arm64-msvc": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-arm64-msvc/-/rollup-win32-arm64-msvc-4.28.0.tgz",
-      "integrity": "sha512-Vi+WR62xWGsE/Oj+mD0FNAPY2MEox3cfyG0zLpotZdehPFXwz6lypkGs5y38Jd/NVSbOD02aVad6q6QYF7i8Bg==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-arm64-msvc/-/rollup-win32-arm64-msvc-4.34.6.tgz",
+      "integrity": "sha512-3/q1qUsO/tLqGBaD4uXsB6coVGB3usxw3qyeVb59aArCgedSF66MPdgRStUd7vbZOsko/CgVaY5fo2vkvPLWiA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
       ]
     },
     "node_modules/@rollup/rollup-win32-ia32-msvc": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-ia32-msvc/-/rollup-win32-ia32-msvc-4.28.0.tgz",
-      "integrity": "sha512-kN/Vpip8emMLn/eOza+4JwqDZBL6MPNpkdaEsgUtW1NYN3DZvZqSQrbKzJcTL6hd8YNmFTn7XGWMwccOcJBL0A==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-ia32-msvc/-/rollup-win32-ia32-msvc-4.34.6.tgz",
+      "integrity": "sha512-oLHxuyywc6efdKVTxvc0135zPrRdtYVjtVD5GUm55I3ODxhU/PwkQFD97z16Xzxa1Fz0AEe4W/2hzRtd+IfpOA==",
       "cpu": [
         "ia32"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
       ]
     },
     "node_modules/@rollup/rollup-win32-x64-msvc": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-msvc/-/rollup-win32-x64-msvc-4.28.0.tgz",
-      "integrity": "sha512-Bvno2/aZT6usSa7lRDL2+hMjVAGjuqaymF1ApZm31JXzniR/hvr14jpU+/z4X6Gt5BPlzosscyJZGUvguXIqeQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-msvc/-/rollup-win32-x64-msvc-4.34.6.tgz",
+      "integrity": "sha512-0PVwmgzZ8+TZ9oGBmdZoQVXflbvuwzN/HRclujpl4N/q3i+y0lqLw8n1bXA8ru3sApDjlmONaNAuYr38y1Kr9w==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -808,8 +795,7 @@
       "version": "1.0.6",
       "resolved": "https://registry.npmjs.org/@types/estree/-/estree-1.0.6.tgz",
       "integrity": "sha512-AYnb1nQyY49te+VRAVgmzfcgjYS91mY5P0TKUDCLEM+gNnA+3T6rWITXRLYCpahpqSQbN5cE+gHpnPyXjHWxcw==",
-      "dev": true,
-      "license": "MIT"
+      "dev": true
     },
     "node_modules/@types/events": {
       "version": "3.0.3",
@@ -847,12 +833,11 @@
       }
     },
     "node_modules/esbuild": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.24.0.tgz",
-      "integrity": "sha512-FuLPevChGDshgSicjisSooU0cemp/sGXR841D5LHMB7mTVOmsEHcAxaH3irL53+8YDIeVNQEySh4DaYU/iuPqQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.24.2.tgz",
+      "integrity": "sha512-+9egpBW8I3CD5XPe0n6BfT5fxLzxrlDzqydF3aviG+9ni1lDC/OvMHcxqEFV0+LANZG5R1bFMWfUrjVsdwxJvA==",
       "dev": true,
       "hasInstallScript": true,
-      "license": "MIT",
       "bin": {
         "esbuild": "bin/esbuild"
       },
@@ -860,30 +845,31 @@
         "node": ">=18"
       },
       "optionalDependencies": {
-        "@esbuild/aix-ppc64": "0.24.0",
-        "@esbuild/android-arm": "0.24.0",
-        "@esbuild/android-arm64": "0.24.0",
-        "@esbuild/android-x64": "0.24.0",
-        "@esbuild/darwin-arm64": "0.24.0",
-        "@esbuild/darwin-x64": "0.24.0",
-        "@esbuild/freebsd-arm64": "0.24.0",
-        "@esbuild/freebsd-x64": "0.24.0",
-        "@esbuild/linux-arm": "0.24.0",
-        "@esbuild/linux-arm64": "0.24.0",
-        "@esbuild/linux-ia32": "0.24.0",
-        "@esbuild/linux-loong64": "0.24.0",
-        "@esbuild/linux-mips64el": "0.24.0",
-        "@esbuild/linux-ppc64": "0.24.0",
-        "@esbuild/linux-riscv64": "0.24.0",
-        "@esbuild/linux-s390x": "0.24.0",
-        "@esbuild/linux-x64": "0.24.0",
-        "@esbuild/netbsd-x64": "0.24.0",
-        "@esbuild/openbsd-arm64": "0.24.0",
-        "@esbuild/openbsd-x64": "0.24.0",
-        "@esbuild/sunos-x64": "0.24.0",
-        "@esbuild/win32-arm64": "0.24.0",
-        "@esbuild/win32-ia32": "0.24.0",
-        "@esbuild/win32-x64": "0.24.0"
+        "@esbuild/aix-ppc64": "0.24.2",
+        "@esbuild/android-arm": "0.24.2",
+        "@esbuild/android-arm64": "0.24.2",
+        "@esbuild/android-x64": "0.24.2",
+        "@esbuild/darwin-arm64": "0.24.2",
+        "@esbuild/darwin-x64": "0.24.2",
+        "@esbuild/freebsd-arm64": "0.24.2",
+        "@esbuild/freebsd-x64": "0.24.2",
+        "@esbuild/linux-arm": "0.24.2",
+        "@esbuild/linux-arm64": "0.24.2",
+        "@esbuild/linux-ia32": "0.24.2",
+        "@esbuild/linux-loong64": "0.24.2",
+        "@esbuild/linux-mips64el": "0.24.2",
+        "@esbuild/linux-ppc64": "0.24.2",
+        "@esbuild/linux-riscv64": "0.24.2",
+        "@esbuild/linux-s390x": "0.24.2",
+        "@esbuild/linux-x64": "0.24.2",
+        "@esbuild/netbsd-arm64": "0.24.2",
+        "@esbuild/netbsd-x64": "0.24.2",
+        "@esbuild/openbsd-arm64": "0.24.2",
+        "@esbuild/openbsd-x64": "0.24.2",
+        "@esbuild/sunos-x64": "0.24.2",
+        "@esbuild/win32-arm64": "0.24.2",
+        "@esbuild/win32-ia32": "0.24.2",
+        "@esbuild/win32-x64": "0.24.2"
       }
     },
     "node_modules/events": {
@@ -901,7 +887,6 @@
       "integrity": "sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==",
       "dev": true,
       "hasInstallScript": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
@@ -951,7 +936,6 @@
           "url": "https://github.com/sponsors/ai"
         }
       ],
-      "license": "MIT",
       "bin": {
         "nanoid": "bin/nanoid.cjs"
       },
@@ -963,13 +947,12 @@
       "version": "1.1.1",
       "resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz",
       "integrity": "sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA==",
-      "dev": true,
-      "license": "ISC"
+      "dev": true
     },
     "node_modules/postcss": {
-      "version": "8.4.49",
-      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.4.49.tgz",
-      "integrity": "sha512-OCVPnIObs4N29kxTjzLfUryOkvZEq+pf8jTF0lg8E7uETuWHA+v7j3c/xJmiqpX450191LlmZfUKkXxkTry7nA==",
+      "version": "8.5.2",
+      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.2.tgz",
+      "integrity": "sha512-MjOadfU3Ys9KYoX0AdkBlFEF1Vx37uCCeN4ZHnmwm9FfpbsGWMZeBLMmmpY+6Ocqod7mkdZ0DT31OlbsFrLlkA==",
       "dev": true,
       "funding": [
         {
@@ -985,9 +968,8 @@
           "url": "https://github.com/sponsors/ai"
         }
       ],
-      "license": "MIT",
       "dependencies": {
-        "nanoid": "^3.3.7",
+        "nanoid": "^3.3.8",
         "picocolors": "^1.1.1",
         "source-map-js": "^1.2.1"
       },
@@ -1002,11 +984,10 @@
       "license": "MIT"
     },
     "node_modules/rollup": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/rollup/-/rollup-4.28.0.tgz",
-      "integrity": "sha512-G9GOrmgWHBma4YfCcX8PjH0qhXSdH8B4HDE2o4/jaxj93S4DPCIDoLcXz99eWMji4hB29UFCEd7B2gwGJDR9cQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/rollup/-/rollup-4.34.6.tgz",
+      "integrity": "sha512-wc2cBWqJgkU3Iz5oztRkQbfVkbxoz5EhnCGOrnJvnLnQ7O0WhQUYyv18qQI79O8L7DdHrrlJNeCHd4VGpnaXKQ==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
         "@types/estree": "1.0.6"
       },
@@ -1018,24 +999,25 @@
         "npm": ">=8.0.0"
       },
       "optionalDependencies": {
-        "@rollup/rollup-android-arm-eabi": "4.28.0",
-        "@rollup/rollup-android-arm64": "4.28.0",
-        "@rollup/rollup-darwin-arm64": "4.28.0",
-        "@rollup/rollup-darwin-x64": "4.28.0",
-        "@rollup/rollup-freebsd-arm64": "4.28.0",
-        "@rollup/rollup-freebsd-x64": "4.28.0",
-        "@rollup/rollup-linux-arm-gnueabihf": "4.28.0",
-        "@rollup/rollup-linux-arm-musleabihf": "4.28.0",
-        "@rollup/rollup-linux-arm64-gnu": "4.28.0",
-        "@rollup/rollup-linux-arm64-musl": "4.28.0",
-        "@rollup/rollup-linux-powerpc64le-gnu": "4.28.0",
-        "@rollup/rollup-linux-riscv64-gnu": "4.28.0",
-        "@rollup/rollup-linux-s390x-gnu": "4.28.0",
-        "@rollup/rollup-linux-x64-gnu": "4.28.0",
-        "@rollup/rollup-linux-x64-musl": "4.28.0",
-        "@rollup/rollup-win32-arm64-msvc": "4.28.0",
-        "@rollup/rollup-win32-ia32-msvc": "4.28.0",
-        "@rollup/rollup-win32-x64-msvc": "4.28.0",
+        "@rollup/rollup-android-arm-eabi": "4.34.6",
+        "@rollup/rollup-android-arm64": "4.34.6",
+        "@rollup/rollup-darwin-arm64": "4.34.6",
+        "@rollup/rollup-darwin-x64": "4.34.6",
+        "@rollup/rollup-freebsd-arm64": "4.34.6",
+        "@rollup/rollup-freebsd-x64": "4.34.6",
+        "@rollup/rollup-linux-arm-gnueabihf": "4.34.6",
+        "@rollup/rollup-linux-arm-musleabihf": "4.34.6",
+        "@rollup/rollup-linux-arm64-gnu": "4.34.6",
+        "@rollup/rollup-linux-arm64-musl": "4.34.6",
+        "@rollup/rollup-linux-loongarch64-gnu": "4.34.6",
+        "@rollup/rollup-linux-powerpc64le-gnu": "4.34.6",
+        "@rollup/rollup-linux-riscv64-gnu": "4.34.6",
+        "@rollup/rollup-linux-s390x-gnu": "4.34.6",
+        "@rollup/rollup-linux-x64-gnu": "4.34.6",
+        "@rollup/rollup-linux-x64-musl": "4.34.6",
+        "@rollup/rollup-win32-arm64-msvc": "4.34.6",
+        "@rollup/rollup-win32-ia32-msvc": "4.34.6",
+        "@rollup/rollup-win32-x64-msvc": "4.34.6",
         "fsevents": "~2.3.2"
       }
     },
@@ -1066,7 +1048,6 @@
       "resolved": "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.1.tgz",
       "integrity": "sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==",
       "dev": true,
-      "license": "BSD-3-Clause",
       "engines": {
         "node": ">=0.10.0"
       }
@@ -1101,15 +1082,14 @@
       }
     },
     "node_modules/vite": {
-      "version": "6.0.2",
-      "resolved": "https://registry.npmjs.org/vite/-/vite-6.0.2.tgz",
-      "integrity": "sha512-XdQ+VsY2tJpBsKGs0wf3U/+azx8BBpYRHFAyKm5VeEZNOJZRB63q7Sc8Iup3k0TrN3KO6QgyzFf+opSbfY1y0g==",
+      "version": "6.1.0",
+      "resolved": "https://registry.npmjs.org/vite/-/vite-6.1.0.tgz",
+      "integrity": "sha512-RjjMipCKVoR4hVfPY6GQTgveinjNuyLw+qruksLDvA5ktI1150VmcMBKmQaEWJhg/j6Uaf6dNCNA0AfdzUb/hQ==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
-        "esbuild": "^0.24.0",
-        "postcss": "^8.4.49",
-        "rollup": "^4.23.0"
+        "esbuild": "^0.24.2",
+        "postcss": "^8.5.1",
+        "rollup": "^4.30.1"
       },
       "bin": {
         "vite": "bin/vite.js"

examples/simple-chatbot/client/javascript/package.json

@@ -12,7 +12,7 @@
   "license": "ISC",
   "description": "",
   "devDependencies": {
-    "vite": "^6.0.2"
+    "vite": "^6.0.9"
   },
   "dependencies": {
     "@pipecat-ai/client-js": "^0.3.2",

examples/simple-chatbot/client/react/package-lock.json

@@ -25,7 +25,7 @@
         "globals": "^15.12.0",
         "typescript": "~5.6.2",
         "typescript-eslint": "^8.15.0",
-        "vite": "^6.0.1"
+        "vite": "^6.0.9"
       }
     },
     "node_modules/@ampproject/remapping": {
@@ -353,14 +353,13 @@
       }
     },
     "node_modules/@esbuild/aix-ppc64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.24.0.tgz",
-      "integrity": "sha512-WtKdFM7ls47zkKHFVzMz8opM7LkcsIp9amDUBIAWirg70RM71WRSjdILPsY5Uv1D42ZpUfaPILDlfactHgsRkw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.24.2.tgz",
+      "integrity": "sha512-thpVCb/rhxE/BnMLQ7GReQLLN8q9qbHmI55F4489/ByVg2aQaQ6kbcLb6FHkocZzQhxc4gx0sCk0tJkKBFzDhA==",
       "cpu": [
         "ppc64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "aix"
@@ -370,14 +369,13 @@
       }
     },
     "node_modules/@esbuild/android-arm": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.24.0.tgz",
-      "integrity": "sha512-arAtTPo76fJ/ICkXWetLCc9EwEHKaeya4vMrReVlEIUCAUncH7M4bhMQ+M9Vf+FFOZJdTNMXNBrWwW+OXWpSew==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.24.2.tgz",
+      "integrity": "sha512-tmwl4hJkCfNHwFB3nBa8z1Uy3ypZpxqxfTQOcHX+xRByyYgunVbZ9MzUUfb0RxaHIMnbHagwAxuTL+tnNM+1/Q==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
@@ -387,14 +385,13 @@
       }
     },
     "node_modules/@esbuild/android-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.24.0.tgz",
-      "integrity": "sha512-Vsm497xFM7tTIPYK9bNTYJyF/lsP590Qc1WxJdlB6ljCbdZKU9SY8i7+Iin4kyhV/KV5J2rOKsBQbB77Ab7L/w==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.24.2.tgz",
+      "integrity": "sha512-cNLgeqCqV8WxfcTIOeL4OAtSmL8JjcN6m09XIgro1Wi7cF4t/THaWEa7eL5CMoMBdjoHOTh/vwTO/o2TRXIyzg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
@@ -404,14 +401,13 @@
       }
     },
     "node_modules/@esbuild/android-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.24.0.tgz",
-      "integrity": "sha512-t8GrvnFkiIY7pa7mMgJd7p8p8qqYIz1NYiAoKc75Zyv73L3DZW++oYMSHPRarcotTKuSs6m3hTOa5CKHaS02TQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.24.2.tgz",
+      "integrity": "sha512-B6Q0YQDqMx9D7rvIcsXfmJfvUYLoP722bgfBlO5cGvNVb5V/+Y7nhBE3mHV9OpxBf4eAS2S68KZztiPaWq4XYw==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
@@ -421,14 +417,13 @@
       }
     },
     "node_modules/@esbuild/darwin-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.24.0.tgz",
-      "integrity": "sha512-CKyDpRbK1hXwv79soeTJNHb5EiG6ct3efd/FTPdzOWdbZZfGhpbcqIpiD0+vwmpu0wTIL97ZRPZu8vUt46nBSw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.24.2.tgz",
+      "integrity": "sha512-kj3AnYWc+CekmZnS5IPu9D+HWtUI49hbnyqk0FLEJDbzCIQt7hg7ucF1SQAilhtYpIujfaHr6O0UHlzzSPdOeA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
@@ -438,14 +433,13 @@
       }
     },
     "node_modules/@esbuild/darwin-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.24.0.tgz",
-      "integrity": "sha512-rgtz6flkVkh58od4PwTRqxbKH9cOjaXCMZgWD905JOzjFKW+7EiUObfd/Kav+A6Gyud6WZk9w+xu6QLytdi2OA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.24.2.tgz",
+      "integrity": "sha512-WeSrmwwHaPkNR5H3yYfowhZcbriGqooyu3zI/3GGpF8AyUdsrrP0X6KumITGA9WOyiJavnGZUwPGvxvwfWPHIA==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
@@ -455,14 +449,13 @@
       }
     },
     "node_modules/@esbuild/freebsd-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.24.0.tgz",
-      "integrity": "sha512-6Mtdq5nHggwfDNLAHkPlyLBpE5L6hwsuXZX8XNmHno9JuL2+bg2BX5tRkwjyfn6sKbxZTq68suOjgWqCicvPXA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.24.2.tgz",
+      "integrity": "sha512-UN8HXjtJ0k/Mj6a9+5u6+2eZ2ERD7Edt1Q9IZiB5UZAIdPnVKDoG7mdTVGhHJIeEml60JteamR3qhsr1r8gXvg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
@@ -472,14 +465,13 @@
       }
     },
     "node_modules/@esbuild/freebsd-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.24.0.tgz",
-      "integrity": "sha512-D3H+xh3/zphoX8ck4S2RxKR6gHlHDXXzOf6f/9dbFt/NRBDIE33+cVa49Kil4WUjxMGW0ZIYBYtaGCa2+OsQwQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.24.2.tgz",
+      "integrity": "sha512-TvW7wE/89PYW+IevEJXZ5sF6gJRDY/14hyIGFXdIucxCsbRmLUcjseQu1SyTko+2idmCw94TgyaEZi9HUSOe3Q==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
@@ -489,14 +481,13 @@
       }
     },
     "node_modules/@esbuild/linux-arm": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.24.0.tgz",
-      "integrity": "sha512-gJKIi2IjRo5G6Glxb8d3DzYXlxdEj2NlkixPsqePSZMhLudqPhtZ4BUrpIuTjJYXxvF9njql+vRjB2oaC9XpBw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.24.2.tgz",
+      "integrity": "sha512-n0WRM/gWIdU29J57hJyUdIsk0WarGd6To0s+Y+LwvlC55wt+GT/OgkwoXCXvIue1i1sSNWblHEig00GBWiJgfA==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -506,14 +497,13 @@
       }
     },
     "node_modules/@esbuild/linux-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.24.0.tgz",
-      "integrity": "sha512-TDijPXTOeE3eaMkRYpcy3LarIg13dS9wWHRdwYRnzlwlA370rNdZqbcp0WTyyV/k2zSxfko52+C7jU5F9Tfj1g==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.24.2.tgz",
+      "integrity": "sha512-7HnAD6074BW43YvvUmE/35Id9/NB7BeX5EoNkK9obndmZBUk8xmJJeU7DwmUeN7tkysslb2eSl6CTrYz6oEMQg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -523,14 +513,13 @@
       }
     },
     "node_modules/@esbuild/linux-ia32": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.24.0.tgz",
-      "integrity": "sha512-K40ip1LAcA0byL05TbCQ4yJ4swvnbzHscRmUilrmP9Am7//0UjPreh4lpYzvThT2Quw66MhjG//20mrufm40mA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.24.2.tgz",
+      "integrity": "sha512-sfv0tGPQhcZOgTKO3oBE9xpHuUqguHvSo4jl+wjnKwFpapx+vUDcawbwPNuBIAYdRAvIDBfZVvXprIj3HA+Ugw==",
       "cpu": [
         "ia32"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -540,14 +529,13 @@
       }
     },
     "node_modules/@esbuild/linux-loong64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.24.0.tgz",
-      "integrity": "sha512-0mswrYP/9ai+CU0BzBfPMZ8RVm3RGAN/lmOMgW4aFUSOQBjA31UP8Mr6DDhWSuMwj7jaWOT0p0WoZ6jeHhrD7g==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.24.2.tgz",
+      "integrity": "sha512-CN9AZr8kEndGooS35ntToZLTQLHEjtVB5n7dl8ZcTZMonJ7CCfStrYhrzF97eAecqVbVJ7APOEe18RPI4KLhwQ==",
       "cpu": [
         "loong64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -557,14 +545,13 @@
       }
     },
     "node_modules/@esbuild/linux-mips64el": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.24.0.tgz",
-      "integrity": "sha512-hIKvXm0/3w/5+RDtCJeXqMZGkI2s4oMUGj3/jM0QzhgIASWrGO5/RlzAzm5nNh/awHE0A19h/CvHQe6FaBNrRA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.24.2.tgz",
+      "integrity": "sha512-iMkk7qr/wl3exJATwkISxI7kTcmHKE+BlymIAbHO8xanq/TjHaaVThFF6ipWzPHryoFsesNQJPE/3wFJw4+huw==",
       "cpu": [
         "mips64el"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -574,14 +561,13 @@
       }
     },
     "node_modules/@esbuild/linux-ppc64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.24.0.tgz",
-      "integrity": "sha512-HcZh5BNq0aC52UoocJxaKORfFODWXZxtBaaZNuN3PUX3MoDsChsZqopzi5UupRhPHSEHotoiptqikjN/B77mYQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.24.2.tgz",
+      "integrity": "sha512-shsVrgCZ57Vr2L8mm39kO5PPIb+843FStGt7sGGoqiiWYconSxwTiuswC1VJZLCjNiMLAMh34jg4VSEQb+iEbw==",
       "cpu": [
         "ppc64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -591,14 +577,13 @@
       }
     },
     "node_modules/@esbuild/linux-riscv64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.24.0.tgz",
-      "integrity": "sha512-bEh7dMn/h3QxeR2KTy1DUszQjUrIHPZKyO6aN1X4BCnhfYhuQqedHaa5MxSQA/06j3GpiIlFGSsy1c7Gf9padw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.24.2.tgz",
+      "integrity": "sha512-4eSFWnU9Hhd68fW16GD0TINewo1L6dRrB+oLNNbYyMUAeOD2yCK5KXGK1GH4qD/kT+bTEXjsyTCiJGHPZ3eM9Q==",
       "cpu": [
         "riscv64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -608,14 +593,13 @@
       }
     },
     "node_modules/@esbuild/linux-s390x": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.24.0.tgz",
-      "integrity": "sha512-ZcQ6+qRkw1UcZGPyrCiHHkmBaj9SiCD8Oqd556HldP+QlpUIe2Wgn3ehQGVoPOvZvtHm8HPx+bH20c9pvbkX3g==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.24.2.tgz",
+      "integrity": "sha512-S0Bh0A53b0YHL2XEXC20bHLuGMOhFDO6GN4b3YjRLK//Ep3ql3erpNcPlEFed93hsQAjAQDNsvcK+hV90FubSw==",
       "cpu": [
         "s390x"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -625,14 +609,13 @@
       }
     },
     "node_modules/@esbuild/linux-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.24.0.tgz",
-      "integrity": "sha512-vbutsFqQ+foy3wSSbmjBXXIJ6PL3scghJoM8zCL142cGaZKAdCZHyf+Bpu/MmX9zT9Q0zFBVKb36Ma5Fzfa8xA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.24.2.tgz",
+      "integrity": "sha512-8Qi4nQcCTbLnK9WoMjdC9NiTG6/E38RNICU6sUNqK0QFxCYgoARqVqxdFmWkdonVsvGqWhmm7MO0jyTqLqwj0Q==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -641,15 +624,30 @@
         "node": ">=18"
       }
     },
+    "node_modules/@esbuild/netbsd-arm64": {
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.24.2.tgz",
+      "integrity": "sha512-wuLK/VztRRpMt9zyHSazyCVdCXlpHkKm34WUyinD2lzK07FAHTq0KQvZZlXikNWkDGoT6x3TD51jKQ7gMVpopw==",
+      "cpu": [
+        "arm64"
+      ],
+      "dev": true,
+      "optional": true,
+      "os": [
+        "netbsd"
+      ],
+      "engines": {
+        "node": ">=18"
+      }
+    },
     "node_modules/@esbuild/netbsd-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.24.0.tgz",
-      "integrity": "sha512-hjQ0R/ulkO8fCYFsG0FZoH+pWgTTDreqpqY7UnQntnaKv95uP5iW3+dChxnx7C3trQQU40S+OgWhUVwCjVFLvg==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.24.2.tgz",
+      "integrity": "sha512-VefFaQUc4FMmJuAxmIHgUmfNiLXY438XrL4GDNV1Y1H/RW3qow68xTwjZKfj/+Plp9NANmzbH5R40Meudu8mmw==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "netbsd"
@@ -659,14 +657,13 @@
       }
     },
     "node_modules/@esbuild/openbsd-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.24.0.tgz",
-      "integrity": "sha512-MD9uzzkPQbYehwcN583yx3Tu5M8EIoTD+tUgKF982WYL9Pf5rKy9ltgD0eUgs8pvKnmizxjXZyLt0z6DC3rRXg==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.24.2.tgz",
+      "integrity": "sha512-YQbi46SBct6iKnszhSvdluqDmxCJA+Pu280Av9WICNwQmMxV7nLRHZfjQzwbPs3jeWnuAhE9Jy0NrnJ12Oz+0A==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "openbsd"
@@ -676,14 +673,13 @@
       }
     },
     "node_modules/@esbuild/openbsd-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.24.0.tgz",
-      "integrity": "sha512-4ir0aY1NGUhIC1hdoCzr1+5b43mw99uNwVzhIq1OY3QcEwPDO3B7WNXBzaKY5Nsf1+N11i1eOfFcq+D/gOS15Q==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.24.2.tgz",
+      "integrity": "sha512-+iDS6zpNM6EnJyWv0bMGLWSWeXGN/HTaF/LXHXHwejGsVi+ooqDfMCCTerNFxEkM3wYVcExkeGXNqshc9iMaOA==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "openbsd"
@@ -693,14 +689,13 @@
       }
     },
     "node_modules/@esbuild/sunos-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.24.0.tgz",
-      "integrity": "sha512-jVzdzsbM5xrotH+W5f1s+JtUy1UWgjU0Cf4wMvffTB8m6wP5/kx0KiaLHlbJO+dMgtxKV8RQ/JvtlFcdZ1zCPA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.24.2.tgz",
+      "integrity": "sha512-hTdsW27jcktEvpwNHJU4ZwWFGkz2zRJUz8pvddmXPtXDzVKTTINmlmga3ZzwcuMpUvLw7JkLy9QLKyGpD2Yxig==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "sunos"
@@ -710,14 +705,13 @@
       }
     },
     "node_modules/@esbuild/win32-arm64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.24.0.tgz",
-      "integrity": "sha512-iKc8GAslzRpBytO2/aN3d2yb2z8XTVfNV0PjGlCxKo5SgWmNXx82I/Q3aG1tFfS+A2igVCY97TJ8tnYwpUWLCA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.24.2.tgz",
+      "integrity": "sha512-LihEQ2BBKVFLOC9ZItT9iFprsE9tqjDjnbulhHoFxYQtQfai7qfluVODIYxt1PgdoyQkz23+01rzwNwYfutxUQ==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -727,14 +721,13 @@
       }
     },
     "node_modules/@esbuild/win32-ia32": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.24.0.tgz",
-      "integrity": "sha512-vQW36KZolfIudCcTnaTpmLQ24Ha1RjygBo39/aLkM2kmjkWmZGEJ5Gn9l5/7tzXA42QGIoWbICfg6KLLkIw6yw==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.24.2.tgz",
+      "integrity": "sha512-q+iGUwfs8tncmFC9pcnD5IvRHAzmbwQ3GPS5/ceCyHdjXubwQWI12MKWSNSMYLJMq23/IUCvJMS76PDqXe1fxA==",
       "cpu": [
         "ia32"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -744,14 +737,13 @@
       }
     },
     "node_modules/@esbuild/win32-x64": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.24.0.tgz",
-      "integrity": "sha512-7IAFPrjSQIJrGsK6flwg7NFmwBoSTyF3rl7If0hNUFQU4ilTsEPL6GuMuU9BfIWVVGuRnuIidkSMC+c0Otu8IA==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.24.2.tgz",
+      "integrity": "sha512-7VTgWzgMGvup6aSqDPLiW5zHaxYJGTO4OokMjIlrCtf+VpEL+cXKtCvg723iguPYI5oaUNdS+/V7OU2gvXVWEg==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -1097,252 +1089,247 @@
       }
     },
     "node_modules/@rollup/rollup-android-arm-eabi": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm-eabi/-/rollup-android-arm-eabi-4.28.0.tgz",
-      "integrity": "sha512-wLJuPLT6grGZsy34g4N1yRfYeouklTgPhH1gWXCYspenKYD0s3cR99ZevOGw5BexMNywkbV3UkjADisozBmpPQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm-eabi/-/rollup-android-arm-eabi-4.34.6.tgz",
+      "integrity": "sha512-+GcCXtOQoWuC7hhX1P00LqjjIiS/iOouHXhMdiDSnq/1DGTox4SpUvO52Xm+div6+106r+TcvOeo/cxvyEyTgg==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
       ]
     },
     "node_modules/@rollup/rollup-android-arm64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm64/-/rollup-android-arm64-4.28.0.tgz",
-      "integrity": "sha512-eiNkznlo0dLmVG/6wf+Ifi/v78G4d4QxRhuUl+s8EWZpDewgk7PX3ZyECUXU0Zq/Ca+8nU8cQpNC4Xgn2gFNDA==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-android-arm64/-/rollup-android-arm64-4.34.6.tgz",
+      "integrity": "sha512-E8+2qCIjciYUnCa1AiVF1BkRgqIGW9KzJeesQqVfyRITGQN+dFuoivO0hnro1DjT74wXLRZ7QF8MIbz+luGaJA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "android"
       ]
     },
     "node_modules/@rollup/rollup-darwin-arm64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-arm64/-/rollup-darwin-arm64-4.28.0.tgz",
-      "integrity": "sha512-lmKx9yHsppblnLQZOGxdO66gT77bvdBtr/0P+TPOseowE7D9AJoBw8ZDULRasXRWf1Z86/gcOdpBrV6VDUY36Q==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-arm64/-/rollup-darwin-arm64-4.34.6.tgz",
+      "integrity": "sha512-z9Ib+OzqN3DZEjX7PDQMHEhtF+t6Mi2z/ueChQPLS/qUMKY7Ybn5A2ggFoKRNRh1q1T03YTQfBTQCJZiepESAg==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
       ]
     },
     "node_modules/@rollup/rollup-darwin-x64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-x64/-/rollup-darwin-x64-4.28.0.tgz",
-      "integrity": "sha512-8hxgfReVs7k9Js1uAIhS6zq3I+wKQETInnWQtgzt8JfGx51R1N6DRVy3F4o0lQwumbErRz52YqwjfvuwRxGv1w==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-darwin-x64/-/rollup-darwin-x64-4.34.6.tgz",
+      "integrity": "sha512-PShKVY4u0FDAR7jskyFIYVyHEPCPnIQY8s5OcXkdU8mz3Y7eXDJPdyM/ZWjkYdR2m0izD9HHWA8sGcXn+Qrsyg==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
       ]
     },
     "node_modules/@rollup/rollup-freebsd-arm64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-arm64/-/rollup-freebsd-arm64-4.28.0.tgz",
-      "integrity": "sha512-lA1zZB3bFx5oxu9fYud4+g1mt+lYXCoch0M0V/xhqLoGatbzVse0wlSQ1UYOWKpuSu3gyN4qEc0Dxf/DII1bhQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-arm64/-/rollup-freebsd-arm64-4.34.6.tgz",
+      "integrity": "sha512-YSwyOqlDAdKqs0iKuqvRHLN4SrD2TiswfoLfvYXseKbL47ht1grQpq46MSiQAx6rQEN8o8URtpXARCpqabqxGQ==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
       ]
     },
     "node_modules/@rollup/rollup-freebsd-x64": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-x64/-/rollup-freebsd-x64-4.28.0.tgz",
-      "integrity": "sha512-aI2plavbUDjCQB/sRbeUZWX9qp12GfYkYSJOrdYTL/C5D53bsE2/nBPuoiJKoWp5SN78v2Vr8ZPnB+/VbQ2pFA==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-freebsd-x64/-/rollup-freebsd-x64-4.34.6.tgz",
+      "integrity": "sha512-HEP4CgPAY1RxXwwL5sPFv6BBM3tVeLnshF03HMhJYCNc6kvSqBgTMmsEjb72RkZBAWIqiPUyF1JpEBv5XT9wKQ==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "freebsd"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm-gnueabihf": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-gnueabihf/-/rollup-linux-arm-gnueabihf-4.28.0.tgz",
-      "integrity": "sha512-WXveUPKtfqtaNvpf0iOb0M6xC64GzUX/OowbqfiCSXTdi/jLlOmH0Ba94/OkiY2yTGTwteo4/dsHRfh5bDCZ+w==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-gnueabihf/-/rollup-linux-arm-gnueabihf-4.34.6.tgz",
+      "integrity": "sha512-88fSzjC5xeH9S2Vg3rPgXJULkHcLYMkh8faix8DX4h4TIAL65ekwuQMA/g2CXq8W+NJC43V6fUpYZNjaX3+IIg==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm-musleabihf": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-musleabihf/-/rollup-linux-arm-musleabihf-4.28.0.tgz",
-      "integrity": "sha512-yLc3O2NtOQR67lI79zsSc7lk31xjwcaocvdD1twL64PK1yNaIqCeWI9L5B4MFPAVGEVjH5k1oWSGuYX1Wutxpg==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm-musleabihf/-/rollup-linux-arm-musleabihf-4.34.6.tgz",
+      "integrity": "sha512-wM4ztnutBqYFyvNeR7Av+reWI/enK9tDOTKNF+6Kk2Q96k9bwhDDOlnCUNRPvromlVXo04riSliMBs/Z7RteEg==",
       "cpu": [
         "arm"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm64-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-gnu/-/rollup-linux-arm64-gnu-4.28.0.tgz",
-      "integrity": "sha512-+P9G9hjEpHucHRXqesY+3X9hD2wh0iNnJXX/QhS/J5vTdG6VhNYMxJ2rJkQOxRUd17u5mbMLHM7yWGZdAASfcg==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-gnu/-/rollup-linux-arm64-gnu-4.34.6.tgz",
+      "integrity": "sha512-9RyprECbRa9zEjXLtvvshhw4CMrRa3K+0wcp3KME0zmBe1ILmvcVHnypZ/aIDXpRyfhSYSuN4EPdCCj5Du8FIA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-arm64-musl": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-musl/-/rollup-linux-arm64-musl-4.28.0.tgz",
-      "integrity": "sha512-1xsm2rCKSTpKzi5/ypT5wfc+4bOGa/9yI/eaOLW0oMs7qpC542APWhl4A37AENGZ6St6GBMWhCCMM6tXgTIplw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-arm64-musl/-/rollup-linux-arm64-musl-4.34.6.tgz",
+      "integrity": "sha512-qTmklhCTyaJSB05S+iSovfo++EwnIEZxHkzv5dep4qoszUMX5Ca4WM4zAVUMbfdviLgCSQOu5oU8YoGk1s6M9Q==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@rollup/rollup-linux-loongarch64-gnu": {
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-loongarch64-gnu/-/rollup-linux-loongarch64-gnu-4.34.6.tgz",
+      "integrity": "sha512-4Qmkaps9yqmpjY5pvpkfOerYgKNUGzQpFxV6rnS7c/JfYbDSU0y6WpbbredB5cCpLFGJEqYX40WUmxMkwhWCjw==",
+      "cpu": [
+        "loong64"
+      ],
+      "dev": true,
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-powerpc64le-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-powerpc64le-gnu/-/rollup-linux-powerpc64le-gnu-4.28.0.tgz",
-      "integrity": "sha512-zgWxMq8neVQeXL+ouSf6S7DoNeo6EPgi1eeqHXVKQxqPy1B2NvTbaOUWPn/7CfMKL7xvhV0/+fq/Z/J69g1WAQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-powerpc64le-gnu/-/rollup-linux-powerpc64le-gnu-4.34.6.tgz",
+      "integrity": "sha512-Zsrtux3PuaxuBTX/zHdLaFmcofWGzaWW1scwLU3ZbW/X+hSsFbz9wDIp6XvnT7pzYRl9MezWqEqKy7ssmDEnuQ==",
       "cpu": [
         "ppc64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-riscv64-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-gnu/-/rollup-linux-riscv64-gnu-4.28.0.tgz",
-      "integrity": "sha512-VEdVYacLniRxbRJLNtzwGt5vwS0ycYshofI7cWAfj7Vg5asqj+pt+Q6x4n+AONSZW/kVm+5nklde0qs2EUwU2g==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-riscv64-gnu/-/rollup-linux-riscv64-gnu-4.34.6.tgz",
+      "integrity": "sha512-aK+Zp+CRM55iPrlyKiU3/zyhgzWBxLVrw2mwiQSYJRobCURb781+XstzvA8Gkjg/hbdQFuDw44aUOxVQFycrAg==",
       "cpu": [
         "riscv64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-s390x-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-s390x-gnu/-/rollup-linux-s390x-gnu-4.28.0.tgz",
-      "integrity": "sha512-LQlP5t2hcDJh8HV8RELD9/xlYtEzJkm/aWGsauvdO2ulfl3QYRjqrKW+mGAIWP5kdNCBheqqqYIGElSRCaXfpw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-s390x-gnu/-/rollup-linux-s390x-gnu-4.34.6.tgz",
+      "integrity": "sha512-WoKLVrY9ogmaYPXwTH326+ErlCIgMmsoRSx6bO+l68YgJnlOXhygDYSZe/qbUJCSiCiZAQ+tKm88NcWuUXqOzw==",
       "cpu": [
         "s390x"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-x64-gnu": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.28.0.tgz",
-      "integrity": "sha512-Nl4KIzteVEKE9BdAvYoTkW19pa7LR/RBrT6F1dJCV/3pbjwDcaOq+edkP0LXuJ9kflW/xOK414X78r+K84+msw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-gnu/-/rollup-linux-x64-gnu-4.34.6.tgz",
+      "integrity": "sha512-Sht4aFvmA4ToHd2vFzwMFaQCiYm2lDFho5rPcvPBT5pCdC+GwHG6CMch4GQfmWTQ1SwRKS0dhDYb54khSrjDWw==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-linux-x64-musl": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-musl/-/rollup-linux-x64-musl-4.28.0.tgz",
-      "integrity": "sha512-eKpJr4vBDOi4goT75MvW+0dXcNUqisK4jvibY9vDdlgLx+yekxSm55StsHbxUsRxSTt3JEQvlr3cGDkzcSP8bw==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-linux-x64-musl/-/rollup-linux-x64-musl-4.34.6.tgz",
+      "integrity": "sha512-zmmpOQh8vXc2QITsnCiODCDGXFC8LMi64+/oPpPx5qz3pqv0s6x46ps4xoycfUiVZps5PFn1gksZzo4RGTKT+A==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
       ]
     },
     "node_modules/@rollup/rollup-win32-arm64-msvc": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-arm64-msvc/-/rollup-win32-arm64-msvc-4.28.0.tgz",
-      "integrity": "sha512-Vi+WR62xWGsE/Oj+mD0FNAPY2MEox3cfyG0zLpotZdehPFXwz6lypkGs5y38Jd/NVSbOD02aVad6q6QYF7i8Bg==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-arm64-msvc/-/rollup-win32-arm64-msvc-4.34.6.tgz",
+      "integrity": "sha512-3/q1qUsO/tLqGBaD4uXsB6coVGB3usxw3qyeVb59aArCgedSF66MPdgRStUd7vbZOsko/CgVaY5fo2vkvPLWiA==",
       "cpu": [
         "arm64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
       ]
     },
     "node_modules/@rollup/rollup-win32-ia32-msvc": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-ia32-msvc/-/rollup-win32-ia32-msvc-4.28.0.tgz",
-      "integrity": "sha512-kN/Vpip8emMLn/eOza+4JwqDZBL6MPNpkdaEsgUtW1NYN3DZvZqSQrbKzJcTL6hd8YNmFTn7XGWMwccOcJBL0A==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-ia32-msvc/-/rollup-win32-ia32-msvc-4.34.6.tgz",
+      "integrity": "sha512-oLHxuyywc6efdKVTxvc0135zPrRdtYVjtVD5GUm55I3ODxhU/PwkQFD97z16Xzxa1Fz0AEe4W/2hzRtd+IfpOA==",
       "cpu": [
         "ia32"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
       ]
     },
     "node_modules/@rollup/rollup-win32-x64-msvc": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-msvc/-/rollup-win32-x64-msvc-4.28.0.tgz",
-      "integrity": "sha512-Bvno2/aZT6usSa7lRDL2+hMjVAGjuqaymF1ApZm31JXzniR/hvr14jpU+/z4X6Gt5BPlzosscyJZGUvguXIqeQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/@rollup/rollup-win32-x64-msvc/-/rollup-win32-x64-msvc-4.34.6.tgz",
+      "integrity": "sha512-0PVwmgzZ8+TZ9oGBmdZoQVXflbvuwzN/HRclujpl4N/q3i+y0lqLw8n1bXA8ru3sApDjlmONaNAuYr38y1Kr9w==",
       "cpu": [
         "x64"
       ],
       "dev": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -2066,12 +2053,11 @@
       "license": "ISC"
     },
     "node_modules/esbuild": {
-      "version": "0.24.0",
-      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.24.0.tgz",
-      "integrity": "sha512-FuLPevChGDshgSicjisSooU0cemp/sGXR841D5LHMB7mTVOmsEHcAxaH3irL53+8YDIeVNQEySh4DaYU/iuPqQ==",
+      "version": "0.24.2",
+      "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.24.2.tgz",
+      "integrity": "sha512-+9egpBW8I3CD5XPe0n6BfT5fxLzxrlDzqydF3aviG+9ni1lDC/OvMHcxqEFV0+LANZG5R1bFMWfUrjVsdwxJvA==",
       "dev": true,
       "hasInstallScript": true,
-      "license": "MIT",
       "bin": {
         "esbuild": "bin/esbuild"
       },
@@ -2079,30 +2065,31 @@
         "node": ">=18"
       },
       "optionalDependencies": {
-        "@esbuild/aix-ppc64": "0.24.0",
-        "@esbuild/android-arm": "0.24.0",
-        "@esbuild/android-arm64": "0.24.0",
-        "@esbuild/android-x64": "0.24.0",
-        "@esbuild/darwin-arm64": "0.24.0",
-        "@esbuild/darwin-x64": "0.24.0",
-        "@esbuild/freebsd-arm64": "0.24.0",
-        "@esbuild/freebsd-x64": "0.24.0",
-        "@esbuild/linux-arm": "0.24.0",
-        "@esbuild/linux-arm64": "0.24.0",
-        "@esbuild/linux-ia32": "0.24.0",
-        "@esbuild/linux-loong64": "0.24.0",
-        "@esbuild/linux-mips64el": "0.24.0",
-        "@esbuild/linux-ppc64": "0.24.0",
-        "@esbuild/linux-riscv64": "0.24.0",
-        "@esbuild/linux-s390x": "0.24.0",
-        "@esbuild/linux-x64": "0.24.0",
-        "@esbuild/netbsd-x64": "0.24.0",
-        "@esbuild/openbsd-arm64": "0.24.0",
-        "@esbuild/openbsd-x64": "0.24.0",
-        "@esbuild/sunos-x64": "0.24.0",
-        "@esbuild/win32-arm64": "0.24.0",
-        "@esbuild/win32-ia32": "0.24.0",
-        "@esbuild/win32-x64": "0.24.0"
+        "@esbuild/aix-ppc64": "0.24.2",
+        "@esbuild/android-arm": "0.24.2",
+        "@esbuild/android-arm64": "0.24.2",
+        "@esbuild/android-x64": "0.24.2",
+        "@esbuild/darwin-arm64": "0.24.2",
+        "@esbuild/darwin-x64": "0.24.2",
+        "@esbuild/freebsd-arm64": "0.24.2",
+        "@esbuild/freebsd-x64": "0.24.2",
+        "@esbuild/linux-arm": "0.24.2",
+        "@esbuild/linux-arm64": "0.24.2",
+        "@esbuild/linux-ia32": "0.24.2",
+        "@esbuild/linux-loong64": "0.24.2",
+        "@esbuild/linux-mips64el": "0.24.2",
+        "@esbuild/linux-ppc64": "0.24.2",
+        "@esbuild/linux-riscv64": "0.24.2",
+        "@esbuild/linux-s390x": "0.24.2",
+        "@esbuild/linux-x64": "0.24.2",
+        "@esbuild/netbsd-arm64": "0.24.2",
+        "@esbuild/netbsd-x64": "0.24.2",
+        "@esbuild/openbsd-arm64": "0.24.2",
+        "@esbuild/openbsd-x64": "0.24.2",
+        "@esbuild/sunos-x64": "0.24.2",
+        "@esbuild/win32-arm64": "0.24.2",
+        "@esbuild/win32-ia32": "0.24.2",
+        "@esbuild/win32-x64": "0.24.2"
       }
     },
     "node_modules/escalade": {
@@ -2445,7 +2432,6 @@
       "integrity": "sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==",
       "dev": true,
       "hasInstallScript": true,
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
@@ -2825,7 +2811,6 @@
           "url": "https://github.com/sponsors/ai"
         }
       ],
-      "license": "MIT",
       "bin": {
         "nanoid": "bin/nanoid.cjs"
       },
@@ -2951,9 +2936,9 @@
       }
     },
     "node_modules/postcss": {
-      "version": "8.4.49",
-      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.4.49.tgz",
-      "integrity": "sha512-OCVPnIObs4N29kxTjzLfUryOkvZEq+pf8jTF0lg8E7uETuWHA+v7j3c/xJmiqpX450191LlmZfUKkXxkTry7nA==",
+      "version": "8.5.2",
+      "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.2.tgz",
+      "integrity": "sha512-MjOadfU3Ys9KYoX0AdkBlFEF1Vx37uCCeN4ZHnmwm9FfpbsGWMZeBLMmmpY+6Ocqod7mkdZ0DT31OlbsFrLlkA==",
       "dev": true,
       "funding": [
         {
@@ -2969,9 +2954,8 @@
           "url": "https://github.com/sponsors/ai"
         }
       ],
-      "license": "MIT",
       "dependencies": {
-        "nanoid": "^3.3.7",
+        "nanoid": "^3.3.8",
         "picocolors": "^1.1.1",
         "source-map-js": "^1.2.1"
       },
@@ -3083,11 +3067,10 @@
       }
     },
     "node_modules/rollup": {
-      "version": "4.28.0",
-      "resolved": "https://registry.npmjs.org/rollup/-/rollup-4.28.0.tgz",
-      "integrity": "sha512-G9GOrmgWHBma4YfCcX8PjH0qhXSdH8B4HDE2o4/jaxj93S4DPCIDoLcXz99eWMji4hB29UFCEd7B2gwGJDR9cQ==",
+      "version": "4.34.6",
+      "resolved": "https://registry.npmjs.org/rollup/-/rollup-4.34.6.tgz",
+      "integrity": "sha512-wc2cBWqJgkU3Iz5oztRkQbfVkbxoz5EhnCGOrnJvnLnQ7O0WhQUYyv18qQI79O8L7DdHrrlJNeCHd4VGpnaXKQ==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
         "@types/estree": "1.0.6"
       },
@@ -3099,24 +3082,25 @@
         "npm": ">=8.0.0"
       },
       "optionalDependencies": {
-        "@rollup/rollup-android-arm-eabi": "4.28.0",
-        "@rollup/rollup-android-arm64": "4.28.0",
-        "@rollup/rollup-darwin-arm64": "4.28.0",
-        "@rollup/rollup-darwin-x64": "4.28.0",
-        "@rollup/rollup-freebsd-arm64": "4.28.0",
-        "@rollup/rollup-freebsd-x64": "4.28.0",
-        "@rollup/rollup-linux-arm-gnueabihf": "4.28.0",
-        "@rollup/rollup-linux-arm-musleabihf": "4.28.0",
-        "@rollup/rollup-linux-arm64-gnu": "4.28.0",
-        "@rollup/rollup-linux-arm64-musl": "4.28.0",
-        "@rollup/rollup-linux-powerpc64le-gnu": "4.28.0",
-        "@rollup/rollup-linux-riscv64-gnu": "4.28.0",
-        "@rollup/rollup-linux-s390x-gnu": "4.28.0",
-        "@rollup/rollup-linux-x64-gnu": "4.28.0",
-        "@rollup/rollup-linux-x64-musl": "4.28.0",
-        "@rollup/rollup-win32-arm64-msvc": "4.28.0",
-        "@rollup/rollup-win32-ia32-msvc": "4.28.0",
-        "@rollup/rollup-win32-x64-msvc": "4.28.0",
+        "@rollup/rollup-android-arm-eabi": "4.34.6",
+        "@rollup/rollup-android-arm64": "4.34.6",
+        "@rollup/rollup-darwin-arm64": "4.34.6",
+        "@rollup/rollup-darwin-x64": "4.34.6",
+        "@rollup/rollup-freebsd-arm64": "4.34.6",
+        "@rollup/rollup-freebsd-x64": "4.34.6",
+        "@rollup/rollup-linux-arm-gnueabihf": "4.34.6",
+        "@rollup/rollup-linux-arm-musleabihf": "4.34.6",
+        "@rollup/rollup-linux-arm64-gnu": "4.34.6",
+        "@rollup/rollup-linux-arm64-musl": "4.34.6",
+        "@rollup/rollup-linux-loongarch64-gnu": "4.34.6",
+        "@rollup/rollup-linux-powerpc64le-gnu": "4.34.6",
+        "@rollup/rollup-linux-riscv64-gnu": "4.34.6",
+        "@rollup/rollup-linux-s390x-gnu": "4.34.6",
+        "@rollup/rollup-linux-x64-gnu": "4.34.6",
+        "@rollup/rollup-linux-x64-musl": "4.34.6",
+        "@rollup/rollup-win32-arm64-msvc": "4.34.6",
+        "@rollup/rollup-win32-ia32-msvc": "4.34.6",
+        "@rollup/rollup-win32-x64-msvc": "4.34.6",
         "fsevents": "~2.3.2"
       }
     },
@@ -3213,7 +3197,6 @@
       "resolved": "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.1.tgz",
       "integrity": "sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==",
       "dev": true,
-      "license": "BSD-3-Clause",
       "engines": {
         "node": ">=0.10.0"
       }
@@ -3395,15 +3378,14 @@
       }
     },
     "node_modules/vite": {
-      "version": "6.0.2",
-      "resolved": "https://registry.npmjs.org/vite/-/vite-6.0.2.tgz",
-      "integrity": "sha512-XdQ+VsY2tJpBsKGs0wf3U/+azx8BBpYRHFAyKm5VeEZNOJZRB63q7Sc8Iup3k0TrN3KO6QgyzFf+opSbfY1y0g==",
+      "version": "6.1.0",
+      "resolved": "https://registry.npmjs.org/vite/-/vite-6.1.0.tgz",
+      "integrity": "sha512-RjjMipCKVoR4hVfPY6GQTgveinjNuyLw+qruksLDvA5ktI1150VmcMBKmQaEWJhg/j6Uaf6dNCNA0AfdzUb/hQ==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
-        "esbuild": "^0.24.0",
-        "postcss": "^8.4.49",
-        "rollup": "^4.23.0"
+        "esbuild": "^0.24.2",
+        "postcss": "^8.5.1",
+        "rollup": "^4.30.1"
       },
       "bin": {
         "vite": "bin/vite.js"

examples/simple-chatbot/client/react/package.json

@@ -27,6 +27,6 @@
     "globals": "^15.12.0",
     "typescript": "~5.6.2",
     "typescript-eslint": "^8.15.0",
-    "vite": "^6.0.1"
+    "vite": "^6.0.9"
   }
 }

examples/simple-chatbot/server/bot-gemini.py

@@ -40,7 +40,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIProcessor
+from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
 from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
@@ -176,7 +176,7 @@ async def main():
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,
-                observers=[rtvi.observer()],
+                observers=[RTVIObserver(rtvi)],
             ),
         )
         await task.queue_frame(quiet_frame)

examples/simple-chatbot/server/bot-openai.py

@@ -40,7 +40,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIProcessor
+from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
@@ -202,7 +202,7 @@ async def main():
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,
-                observers=[rtvi.observer()],
+                observers=[RTVIObserver(rtvi)],
             ),
         )
         await task.queue_frame(quiet_frame)

examples/storytelling-chatbot/README.md

@@ -74,6 +74,8 @@ If you'd like to run a custom domain or port:
 
 ➡️ Open the host URL in your browser `http://localhost:7860`
 
+If you've run previous versions of the demo, make sure to set `ENV=dev`, and remove the `RUN_AS_VM` line from the .env file.
+
 ---
 
 ## Improvements to make

examples/storytelling-chatbot/env.example

@@ -3,6 +3,4 @@ DAILY_SAMPLE_ROOM_URL=
 ELEVENLABS_API_KEY=
 ELEVENLABS_VOICE_ID=
 GOOGLE_API_KEY=
-
-ENV= # dev | production
-RUN_AS_VM= # Set this if you want to run bots on process (not launch a new VM)
+ENV=dev

examples/storytelling-chatbot/requirements.txt

@@ -2,5 +2,4 @@ async_timeout
 fastapi
 uvicorn
 python-dotenv
--e "../..[daily,silero,openai,fal,cartesia,google]"
--e "../../../python-genai"
+pipecat-ai[daily,silero,openai,cartesia,google]

examples/storytelling-chatbot/src/bot.py

@@ -23,8 +23,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.elevenlabs import ElevenLabsTTSService
-from pipecat.services.fal import FalImageGenService
-from pipecat.services.google import GoogleLLMService
+from pipecat.services.google import GoogleImageGenService, GoogleLLMService
 from pipecat.transports.services.daily import (
     DailyParams,
     DailyTransport,

examples/translation-chatbot/bot.py

@@ -24,17 +24,15 @@ from pipecat.frames.frames import (
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineTask
+from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.processors.frameworks.rtvi import RTVIObserver, RTVIProcessor
 from pipecat.processors.transcript_processor import TranscriptProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.services.daily import (
-    DailyParams,
-    DailyTransport,
-)
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -166,21 +164,32 @@ async def main():
         async def on_transcript_update(processor, frame):
             await transcript_handler.on_transcript_update(processor, frame)
 
+        rtvi = RTVIProcessor()
+
         pipeline = Pipeline(
             [
                 transport.input(),
+                rtvi,
                 stt,
                 transcript.user(),  # User transcripts
                 tp,
                 llm,
                 tts,
                 transport.output(),
+                transcript.assistant(),
                 context_aggregator.assistant(),
-                transcript.assistant(),  # Assistant transcripts
             ]
         )
 
-        task = PipelineTask(pipeline)
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=False,  # We don't want to interrupt the translator bot
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                observers=[RTVIObserver(rtvi)],
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/translation-chatbot/requirements.txt

@@ -1,4 +1,4 @@
 python-dotenv
 fastapi[all]
-pipecat-ai[daily,openai,azure]
+pipecat-ai[cartesia,daily,deepgram,openai,silero]
 aiohttp

examples/twilio-chatbot/bot.py

@@ -90,7 +90,7 @@ async def run_bot(websocket_client: WebSocket, stream_sid: str, testing: bool):
 
     # NOTE: Watch out! This will save all the conversation in memory. You can
     # pass `buffer_size` to get periodic callbacks.
-    audiobuffer = AudioBufferProcessor()
+    audiobuffer = AudioBufferProcessor(user_continuous_stream=not testing)
 
     pipeline = Pipeline(
         [

examples/twilio-chatbot/client.py

@@ -124,7 +124,7 @@ async def run_client(client_name: str, server_url: str, duration_secs: int):
 
     # NOTE: Watch out! This will save all the conversation in memory. You can
     # pass `buffer_size` to get periodic callbacks.
-    audiobuffer = AudioBufferProcessor()
+    audiobuffer = AudioBufferProcessor(user_continuous_stream=False)
 
     pipeline = Pipeline(
         [

pyproject.toml

@@ -55,7 +55,7 @@ elevenlabs = [ "websockets~=13.1" ]
 fal = [ "fal-client~=0.5.6" ]
 fish = [ "ormsgpack~=1.7.0", "websockets~=13.1" ]
 gladia = [ "websockets~=13.1" ]
-google = [ "google-generativeai~=0.8.3", "google-cloud-texttospeech~=2.24.0", "google-genai~=0.7.0" ]
+google = [ "google-cloud-speech~=2.31.0", "google-cloud-texttospeech~=2.25.0", "google-genai~=1.2.0", "google-generativeai~=0.8.4" ]
 grok = [ "openai~=1.59.6" ]
 groq = [ "openai~=1.59.6" ]
 gstreamer = [ "pygobject~=3.50.0" ]
@@ -71,7 +71,9 @@ nim = [ "openai~=1.59.6" ]
 noisereduce = [ "noisereduce~=3.0.3" ]
 openai = [ "openai~=1.59.6", "websockets~=13.1", "python-deepcompare~=2.1.0" ]
 openpipe = [ "openpipe~=4.45.0" ]
+perplexity = [ "openai~=1.59.6" ]
 playht = [ "pyht~=0.1.6", "websockets~=13.1" ]
+rime = [ "websockets~=13.1" ]
 riva = [ "nvidia-riva-client~=2.18.0" ]
 sentry = [ "sentry-sdk~=2.20.0" ]
 silero = [ "onnxruntime~=1.20.1" ]
@@ -111,3 +113,8 @@ select = [
 
 [tool.ruff.lint.pydocstyle]
 convention = "google"
+
+[tool.coverage.run]
+command_line = "--module pytest"
+source = ["src"]
+omit = ["*/tests/*"]

src/pipecat/frames/frames.py

@@ -565,6 +565,22 @@ class UserStoppedSpeakingFrame(SystemFrame):
     pass
 
 
+@dataclass
+class EmulateUserStartedSpeakingFrame(SystemFrame):
+    """Emitted by internal processors upstream to emulate VAD behavior when a
+    user starts speaking."""
+
+    pass
+
+
+@dataclass
+class EmulateUserStoppedSpeakingFrame(SystemFrame):
+    """Emitted by internal processors upstream to emulate VAD behavior when a
+    user stops speaking."""
+
+    pass
+
+
 @dataclass
 class BotInterruptionFrame(SystemFrame):
     """Emitted by when the bot should be interrupted. This will mainly cause the
@@ -618,6 +634,13 @@ class FunctionCallInProgressFrame(SystemFrame):
     arguments: str
 
 
+@dataclass
+class STTMuteFrame(SystemFrame):
+    """System frame to mute/unmute the STT service."""
+
+    mute: bool
+
+
 @dataclass
 class TransportMessageUrgentFrame(SystemFrame):
     message: Any
@@ -752,13 +775,6 @@ class TTSUpdateSettingsFrame(ServiceUpdateSettingsFrame):
     pass
 
 
-@dataclass
-class STTMuteFrame(ControlFrame):
-    """Control frame to mute/unmute the STT service."""
-
-    mute: bool
-
-
 @dataclass
 class STTUpdateSettingsFrame(ServiceUpdateSettingsFrame):
     pass

src/pipecat/processors/aggregators/llm_response.py

@@ -4,9 +4,16 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-from typing import List, Optional, Type
+import asyncio
+import time
+from abc import abstractmethod
+from typing import List
 
 from pipecat.frames.frames import (
+    CancelFrame,
+    EmulateUserStartedSpeakingFrame,
+    EmulateUserStoppedSpeakingFrame,
+    EndFrame,
     Frame,
     InterimTranscriptionFrame,
     LLMFullResponseEndFrame,
@@ -15,6 +22,7 @@ from pipecat.frames.frames import (
     LLMMessagesFrame,
     LLMMessagesUpdateFrame,
     LLMSetToolsFrame,
+    StartFrame,
     StartInterruptionFrame,
     TextFrame,
     TranscriptionFrame,
@@ -28,121 +36,105 @@ from pipecat.processors.aggregators.openai_llm_context import (
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 
 
-class LLMResponseAggregator(FrameProcessor):
+class BaseLLMResponseAggregator(FrameProcessor):
+    """This is the base class for all LLM response aggregators. These
+    aggregators process incoming frames and aggregate content until they are
+    ready to push the aggregation. In the case of a user, an aggregation might
+    be a full transcription received from the STT service.
+
+    The LLM response aggregators also keep a store (e.g. a message list or an
+    LLM context) of the current conversation, that is, it stores the messages
+    said by the user or by the bot.
+
+    """
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    @property
+    @abstractmethod
+    def messages(self) -> List[dict]:
+        """Returns the messages from the current conversation."""
+        pass
+
+    @property
+    @abstractmethod
+    def role(self) -> str:
+        """Returns the role (e.g. user, assistant...) for this aggregator."""
+        pass
+
+    @abstractmethod
+    def add_messages(self, messages):
+        """Add the given messages to the conversation."""
+        pass
+
+    @abstractmethod
+    def set_messages(self, messages):
+        """Reset the conversation with the given messages."""
+        pass
+
+    @abstractmethod
+    def set_tools(self, tools):
+        """Set LLM tools to be used in the current conversation."""
+        pass
+
+    @abstractmethod
+    def reset(self):
+        """Reset the internals of this aggregator. This should not modify the
+        internal messages."""
+        pass
+
+    @abstractmethod
+    async def push_aggregation(self):
+        pass
+
+
+class LLMResponseAggregator(BaseLLMResponseAggregator):
+    """This is a base LLM aggregator that uses a simple list of messages to
+    store the conversation. It pushes `LLMMessagesFrame` as an aggregation
+    frame.
+
+    """
+
     def __init__(
         self,
         *,
         messages: List[dict],
-        role: str,
-        start_frame,
-        end_frame,
-        accumulator_frame: Type[TextFrame],
-        interim_accumulator_frame: Optional[Type[TextFrame]] = None,
-        handle_interruptions: bool = False,
-        expect_stripped_words: bool = True,  # if True, need to add spaces between words
+        role: str = "user",
+        **kwargs,
     ):
-        super().__init__()
+        super().__init__(**kwargs)
 
         self._messages = messages
         self._role = role
-        self._start_frame = start_frame
-        self._end_frame = end_frame
-        self._accumulator_frame = accumulator_frame
-        self._interim_accumulator_frame = interim_accumulator_frame
-        self._handle_interruptions = handle_interruptions
-        self._expect_stripped_words = expect_stripped_words
 
-        # Reset our accumulator state.
-        self._reset()
+        self._aggregation = ""
+
+        self.reset()
 
     @property
-    def messages(self):
+    def messages(self) -> List[dict]:
         return self._messages
 
     @property
-    def role(self):
+    def role(self) -> str:
         return self._role
 
-    #
-    # Frame processor
-    #
+    def add_messages(self, messages):
+        self._messages.extend(messages)
 
-    # Use cases implemented:
-    #
-    # S: Start, E: End, T: Transcription, I: Interim, X: Text
-    #
-    #        S E -> None
-    #      S T E -> X
-    #    S I T E -> X
-    #    S I E T -> X
-    #  S I E I T -> X
-    #      S E T -> X
-    #    S E I T -> X
-    #
-    # The following case would not be supported:
-    #
-    #    S I E T1 I T2 -> X
-    #
-    # and T2 would be dropped.
+    def set_messages(self, messages):
+        self.reset()
+        self._messages.clear()
+        self._messages.extend(messages)
 
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
+    def set_tools(self, tools):
+        pass
 
-        send_aggregation = False
+    def reset(self):
+        self._aggregation = ""
 
-        if isinstance(frame, self._start_frame):
-            self._aggregation = ""
-            self._aggregating = True
-            self._seen_start_frame = True
-            self._seen_end_frame = False
-            self._seen_interim_results = False
-            await self.push_frame(frame, direction)
-        elif isinstance(frame, self._end_frame):
-            self._seen_end_frame = True
-            self._seen_start_frame = False
-
-            # We might have received the end frame but we might still be
-            # aggregating (i.e. we have seen interim results but not the final
-            # text).
-            self._aggregating = self._seen_interim_results or len(self._aggregation) == 0
-
-            # Send the aggregation if we are not aggregating anymore (i.e. no
-            # more interim results received).
-            send_aggregation = not self._aggregating
-            await self.push_frame(frame, direction)
-        elif isinstance(frame, self._accumulator_frame):
-            if self._aggregating:
-                if self._expect_stripped_words:
-                    self._aggregation += f" {frame.text}" if self._aggregation else frame.text
-                else:
-                    self._aggregation += frame.text
-                # We have recevied a complete sentence, so if we have seen the
-                # end frame and we were still aggregating, it means we should
-                # send the aggregation.
-                send_aggregation = self._seen_end_frame
-
-            # We just got our final result, so let's reset interim results.
-            self._seen_interim_results = False
-        elif self._interim_accumulator_frame and isinstance(frame, self._interim_accumulator_frame):
-            self._seen_interim_results = True
-        elif self._handle_interruptions and isinstance(frame, StartInterruptionFrame):
-            await self._push_aggregation()
-            # Reset anyways
-            self._reset()
-            await self.push_frame(frame, direction)
-        elif isinstance(frame, LLMMessagesAppendFrame):
-            self._add_messages(frame.messages)
-        elif isinstance(frame, LLMMessagesUpdateFrame):
-            self._set_messages(frame.messages)
-        elif isinstance(frame, LLMSetToolsFrame):
-            self._set_tools(frame.tools)
-        else:
-            await self.push_frame(frame, direction)
-
-        if send_aggregation:
-            await self._push_aggregation()
-
-    async def _push_aggregation(self):
+    async def push_aggregation(self):
         if len(self._aggregation) > 0:
             self._messages.append({"role": self._role, "content": self._aggregation})
 
@@ -153,109 +145,27 @@ class LLMResponseAggregator(FrameProcessor):
             frame = LLMMessagesFrame(self._messages)
             await self.push_frame(frame)
 
-    # TODO-CB: Types
-    def _add_messages(self, messages):
-        self._messages.extend(messages)
 
-    def _set_messages(self, messages):
-        self._reset()
-        self._messages.clear()
-        self._messages.extend(messages)
+class LLMContextResponseAggregator(BaseLLMResponseAggregator):
+    """This is a base LLM aggregator that uses an LLM context to store the
+    conversation. It pushes `OpenAILLMContextFrame` as an aggregation frame.
 
-    def _set_tools(self, tools):
-        # noop in the base class
-        pass
-
-    def _reset(self):
-        self._aggregation = ""
-        self._aggregating = False
-        self._seen_start_frame = False
-        self._seen_end_frame = False
-        self._seen_interim_results = False
-
-
-class LLMAssistantResponseAggregator(LLMResponseAggregator):
-    def __init__(self, messages: List[dict] = []):
-        super().__init__(
-            messages=messages,
-            role="assistant",
-            start_frame=LLMFullResponseStartFrame,
-            end_frame=LLMFullResponseEndFrame,
-            accumulator_frame=TextFrame,
-            handle_interruptions=True,
-        )
-
-
-class LLMUserResponseAggregator(LLMResponseAggregator):
-    def __init__(self, messages: List[dict] = []):
-        super().__init__(
-            messages=messages,
-            role="user",
-            start_frame=UserStartedSpeakingFrame,
-            end_frame=UserStoppedSpeakingFrame,
-            accumulator_frame=TranscriptionFrame,
-            interim_accumulator_frame=InterimTranscriptionFrame,
-        )
-
-
-class LLMFullResponseAggregator(FrameProcessor):
-    """This class aggregates Text frames until it receives a
-    LLMFullResponseEndFrame, then emits the concatenated text as
-    a single text frame.
-
-    given the following frames:
-
-        TextFrame("Hello,")
-        TextFrame(" world.")
-        TextFrame(" I am")
-        TextFrame(" an LLM.")
-        LLMFullResponseEndFrame()]
-
-    this processor will yield nothing for the first 4 frames, then
-
-        TextFrame("Hello, world. I am an LLM.")
-        LLMFullResponseEndFrame()
-
-    when passed the last frame.
-
-    >>> async def print_frames(aggregator, frame):
-    ...     async for frame in aggregator.process_frame(frame):
-    ...         if isinstance(frame, TextFrame):
-    ...             print(frame.text)
-    ...         else:
-    ...             print(frame.__class__.__name__)
-
-    >>> aggregator = LLMFullResponseAggregator()
-    >>> asyncio.run(print_frames(aggregator, TextFrame("Hello,")))
-    >>> asyncio.run(print_frames(aggregator, TextFrame(" world.")))
-    >>> asyncio.run(print_frames(aggregator, TextFrame(" I am")))
-    >>> asyncio.run(print_frames(aggregator, TextFrame(" an LLM.")))
-    >>> asyncio.run(print_frames(aggregator, LLMFullResponseEndFrame()))
-    Hello, world. I am an LLM.
-    LLMFullResponseEndFrame
     """
 
-    def __init__(self):
-        super().__init__()
-        self._aggregation = ""
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        if isinstance(frame, TextFrame):
-            self._aggregation += frame.text
-        elif isinstance(frame, LLMFullResponseEndFrame):
-            await self.push_frame(TextFrame(self._aggregation))
-            await self.push_frame(frame)
-            self._aggregation = ""
-        else:
-            await self.push_frame(frame, direction)
-
-
-class LLMContextAggregator(LLMResponseAggregator):
-    def __init__(self, *, context: OpenAILLMContext, **kwargs):
+    def __init__(self, *, context: OpenAILLMContext, role: str, **kwargs):
         super().__init__(**kwargs)
         self._context = context
+        self._role = role
+
+        self._aggregation = ""
+
+    @property
+    def messages(self) -> List[dict]:
+        return self._context.get_messages()
+
+    @property
+    def role(self) -> str:
+        return self._role
 
     @property
     def context(self):
@@ -264,23 +174,25 @@ class LLMContextAggregator(LLMResponseAggregator):
     def get_context_frame(self) -> OpenAILLMContextFrame:
         return OpenAILLMContextFrame(context=self._context)
 
-    async def push_context_frame(self):
+    async def push_context_frame(self, direction: FrameDirection = FrameDirection.DOWNSTREAM):
         frame = self.get_context_frame()
-        await self.push_frame(frame)
+        await self.push_frame(frame, direction)
 
-    # TODO-CB: Types
-    def _add_messages(self, messages):
+    def add_messages(self, messages):
         self._context.add_messages(messages)
 
-    def _set_messages(self, messages):
+    def set_messages(self, messages):
         self._context.set_messages(messages)
 
-    def _set_tools(self, tools: List):
+    def set_tools(self, tools: List):
         self._context.set_tools(tools)
 
-    async def _push_aggregation(self):
+    def reset(self):
+        self._aggregation = ""
+
+    async def push_aggregation(self):
         if len(self._aggregation) > 0:
-            self._context.add_message({"role": self._role, "content": self._aggregation})
+            self._context.add_message({"role": self.role, "content": self._aggregation})
 
             # Reset the aggregation. Reset it before pushing it down, otherwise
             # if the tasks gets cancelled we won't be able to clear things up.
@@ -290,31 +202,239 @@ class LLMContextAggregator(LLMResponseAggregator):
             await self.push_frame(frame)
 
             # Reset our accumulator state.
-            self._reset()
+            self.reset()
 
 
-class LLMAssistantContextAggregator(LLMContextAggregator):
-    def __init__(self, context: OpenAILLMContext, *, expect_stripped_words: bool = True):
-        super().__init__(
-            messages=[],
-            context=context,
-            role="assistant",
-            start_frame=LLMFullResponseStartFrame,
-            end_frame=LLMFullResponseEndFrame,
-            accumulator_frame=TextFrame,
-            handle_interruptions=True,
-            expect_stripped_words=expect_stripped_words,
-        )
+class LLMUserContextAggregator(LLMContextResponseAggregator):
+    """This is a user LLM aggregator that uses an LLM context to store the
+    conversation. It aggregates transcriptions from the STT service and it has
+    logic to handle multiple scenarios where transcriptions are received between
+    VAD events (`UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame`) or
+    even outside or no VAD events at all.
+
+    """
+
+    def __init__(
+        self,
+        context: OpenAILLMContext,
+        aggregation_timeout: float = 1.0,
+        bot_interruption_timeout: float = 2.0,
+        **kwargs,
+    ):
+        super().__init__(context=context, role="user", **kwargs)
+        self._aggregation_timeout = aggregation_timeout
+        self._bot_interruption_timeout = bot_interruption_timeout
+
+        self._seen_interim_results = False
+        self._user_speaking = False
+        self._last_user_speaking_time = 0
+        self._emulating_vad = False
+
+        self._aggregation_event = asyncio.Event()
+        self._aggregation_task = None
+
+        self.reset()
+
+    def reset(self):
+        super().reset()
+        self._seen_interim_results = False
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, StartFrame):
+            await self._start(frame)
+            await self.push_frame(frame, direction)
+        elif isinstance(frame, EndFrame):
+            await self._stop(frame)
+            await self.push_frame(frame, direction)
+        elif isinstance(frame, CancelFrame):
+            await self._cancel(frame)
+            await self.push_frame(frame, direction)
+        elif isinstance(frame, UserStartedSpeakingFrame):
+            await self._handle_user_started_speaking(frame)
+            await self.push_frame(frame, direction)
+        elif isinstance(frame, UserStoppedSpeakingFrame):
+            await self._handle_user_stopped_speaking(frame)
+            await self.push_frame(frame, direction)
+        elif isinstance(frame, TranscriptionFrame):
+            await self._handle_transcription(frame)
+        elif isinstance(frame, InterimTranscriptionFrame):
+            await self._handle_interim_transcription(frame)
+        elif isinstance(frame, LLMMessagesAppendFrame):
+            self.add_messages(frame.messages)
+        elif isinstance(frame, LLMMessagesUpdateFrame):
+            self.set_messages(frame.messages)
+        elif isinstance(frame, LLMSetToolsFrame):
+            self.set_tools(frame.tools)
+        else:
+            await self.push_frame(frame, direction)
+
+    async def _start(self, frame: StartFrame):
+        self._create_aggregation_task()
+
+    async def _stop(self, frame: EndFrame):
+        await self._cancel_aggregation_task()
+
+    async def _cancel(self, frame: CancelFrame):
+        await self._cancel_aggregation_task()
+
+    async def _handle_user_started_speaking(self, _: UserStartedSpeakingFrame):
+        self._last_user_speaking_time = time.time()
+        self._user_speaking = True
+
+    async def _handle_user_stopped_speaking(self, _: UserStoppedSpeakingFrame):
+        self._last_user_speaking_time = time.time()
+        self._user_speaking = False
+        if not self._seen_interim_results:
+            await self.push_aggregation()
+
+    async def _handle_transcription(self, frame: TranscriptionFrame):
+        self._aggregation += f" {frame.text}" if self._aggregation else frame.text
+        # We just got a final result, so let's reset interim results.
+        self._seen_interim_results = False
+        # Reset aggregation timer.
+        self._aggregation_event.set()
+
+    async def _handle_interim_transcription(self, _: InterimTranscriptionFrame):
+        self._seen_interim_results = True
+        # Reset aggregation timer.
+        self._aggregation_event.set()
+
+    def _create_aggregation_task(self):
+        self._aggregation_task = self.create_task(self._aggregation_task_handler())
+
+    async def _cancel_aggregation_task(self):
+        if self._aggregation_task:
+            await self.cancel_task(self._aggregation_task)
+            self._aggregation_task = None
+
+    async def _aggregation_task_handler(self):
+        while True:
+            try:
+                await asyncio.wait_for(self._aggregation_event.wait(), self._aggregation_timeout)
+                await self._maybe_push_bot_interruption()
+            except asyncio.TimeoutError:
+                if not self._user_speaking:
+                    await self.push_aggregation()
+
+                # If we are emulating VAD we still need to send the user stopped
+                # speaking frame.
+                if self._emulating_vad:
+                    await self.push_frame(
+                        EmulateUserStoppedSpeakingFrame(), FrameDirection.UPSTREAM
+                    )
+                    self._emulating_vad = False
+            finally:
+                self._aggregation_event.clear()
+
+    async def _maybe_push_bot_interruption(self):
+        """If the user stopped speaking a while back and we got a transcription
+        frame we might want to interrupt the bot.
+
+        """
+        if not self._user_speaking:
+            diff_time = time.time() - self._last_user_speaking_time
+            if diff_time > self._bot_interruption_timeout:
+                # If we reach this case we received a transcription but VAD was
+                # not able to detect voice (e.g. when you whisper a short
+                # utterance). So, we need to emulate VAD (i.e. user
+                # start/stopped speaking).
+                await self.push_frame(EmulateUserStartedSpeakingFrame(), FrameDirection.UPSTREAM)
+                self._emulating_vad = True
+
+                # Reset time so we don't interrupt again right away.
+                self._last_user_speaking_time = time.time()
 
 
-class LLMUserContextAggregator(LLMContextAggregator):
-    def __init__(self, context: OpenAILLMContext):
-        super().__init__(
-            messages=[],
-            context=context,
-            role="user",
-            start_frame=UserStartedSpeakingFrame,
-            end_frame=UserStoppedSpeakingFrame,
-            accumulator_frame=TranscriptionFrame,
-            interim_accumulator_frame=InterimTranscriptionFrame,
-        )
+class LLMAssistantContextAggregator(LLMContextResponseAggregator):
+    """This is an assistant LLM aggregator that uses an LLM context to store the
+    conversation. It aggregates text frames received between
+    `LLMFullResponseStartFrame` and `LLMFullResponseEndFrame`.
+
+    """
+
+    def __init__(self, context: OpenAILLMContext, *, expect_stripped_words: bool = True, **kwargs):
+        super().__init__(context=context, role="assistant", **kwargs)
+        self._expect_stripped_words = expect_stripped_words
+
+        self._started = False
+
+        self.reset()
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, StartInterruptionFrame):
+            await self.push_aggregation()
+            # Reset anyways
+            self.reset()
+            await self.push_frame(frame, direction)
+        elif isinstance(frame, LLMFullResponseStartFrame):
+            await self._handle_llm_start(frame)
+        elif isinstance(frame, LLMFullResponseEndFrame):
+            await self._handle_llm_end(frame)
+        elif isinstance(frame, TextFrame):
+            await self._handle_text(frame)
+        elif isinstance(frame, LLMMessagesAppendFrame):
+            self.add_messages(frame.messages)
+        elif isinstance(frame, LLMMessagesUpdateFrame):
+            self.set_messages(frame.messages)
+        elif isinstance(frame, LLMSetToolsFrame):
+            self.set_tools(frame.tools)
+        else:
+            await self.push_frame(frame, direction)
+
+    async def _handle_llm_start(self, _: LLMFullResponseStartFrame):
+        self._started = True
+
+    async def _handle_llm_end(self, _: LLMFullResponseEndFrame):
+        self._started = False
+        await self.push_aggregation()
+
+    async def _handle_text(self, frame: TextFrame):
+        if not self._started:
+            return
+
+        if self._expect_stripped_words:
+            self._aggregation += f" {frame.text}" if self._aggregation else frame.text
+        else:
+            self._aggregation += frame.text
+
+
+class LLMUserResponseAggregator(LLMUserContextAggregator):
+    def __init__(self, messages: List[dict] = [], **kwargs):
+        super().__init__(context=OpenAILLMContext(messages), **kwargs)
+
+    async def push_aggregation(self):
+        if len(self._aggregation) > 0:
+            self._context.add_message({"role": self.role, "content": self._aggregation})
+
+            # Reset the aggregation. Reset it before pushing it down, otherwise
+            # if the tasks gets cancelled we won't be able to clear things up.
+            self._aggregation = ""
+
+            frame = LLMMessagesFrame(self._context.messages)
+            await self.push_frame(frame)
+
+            # Reset our accumulator state.
+            self.reset()
+
+
+class LLMAssistantResponseAggregator(LLMAssistantContextAggregator):
+    def __init__(self, messages: List[dict] = [], **kwargs):
+        super().__init__(context=OpenAILLMContext(messages), **kwargs)
+
+    async def push_aggregation(self):
+        if len(self._aggregation) > 0:
+            self._context.add_message({"role": self.role, "content": self._aggregation})
+
+            # Reset the aggregation. Reset it before pushing it down, otherwise
+            # if the tasks gets cancelled we won't be able to clear things up.
+            self._aggregation = ""
+
+            frame = LLMMessagesFrame(self._context.messages)
+            await self.push_frame(frame)
+
+            # Reset our accumulator state.
+            self.reset()

src/pipecat/processors/aggregators/user_response.py

@@ -4,131 +4,15 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-from typing import Optional
-
-from pipecat.frames.frames import (
-    Frame,
-    InterimTranscriptionFrame,
-    StartInterruptionFrame,
-    TextFrame,
-    TranscriptionFrame,
-    UserStartedSpeakingFrame,
-    UserStoppedSpeakingFrame,
-)
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.frames.frames import TextFrame
+from pipecat.processors.aggregators.llm_response import LLMUserResponseAggregator
 
 
-class ResponseAggregator(FrameProcessor):
-    """This frame processor aggregates frames between a start and an end frame
-    into complete text frame sentences.
+class UserResponseAggregator(LLMUserResponseAggregator):
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
 
-    For example, frame input/output:
-        UserStartedSpeakingFrame() -> None
-        TranscriptionFrame("Hello,") -> None
-        TranscriptionFrame(" world.") -> None
-        UserStoppedSpeakingFrame() -> TextFrame("Hello world.")
-
-    Doctest: FIXME to work with asyncio
-    >>> async def print_frames(aggregator, frame):
-    ...     async for frame in aggregator.process_frame(frame):
-    ...         if isinstance(frame, TextFrame):
-    ...             print(frame.text)
-
-    >>> aggregator = ResponseAggregator(start_frame = UserStartedSpeakingFrame,
-    ...                                 end_frame=UserStoppedSpeakingFrame,
-    ...                                 accumulator_frame=TranscriptionFrame,
-    ...                                 pass_through=False)
-    >>> asyncio.run(print_frames(aggregator, UserStartedSpeakingFrame()))
-    >>> asyncio.run(print_frames(aggregator, TranscriptionFrame("Hello,", 1, 1)))
-    >>> asyncio.run(print_frames(aggregator, TranscriptionFrame("world.",  1, 2)))
-    >>> asyncio.run(print_frames(aggregator, UserStoppedSpeakingFrame()))
-    Hello, world.
-
-    """
-
-    def __init__(
-        self,
-        *,
-        start_frame,
-        end_frame,
-        accumulator_frame: TextFrame,
-        interim_accumulator_frame: Optional[TextFrame] = None,
-    ):
-        super().__init__()
-
-        self._start_frame = start_frame
-        self._end_frame = end_frame
-        self._accumulator_frame = accumulator_frame
-        self._interim_accumulator_frame = interim_accumulator_frame
-
-        # Reset our accumulator state.
-        self._reset()
-
-    #
-    # Frame processor
-    #
-
-    # Use cases implemented:
-    #
-    # S: Start, E: End, T: Transcription, I: Interim, X: Text
-    #
-    #        S E -> None
-    #      S T E -> X
-    #    S I T E -> X
-    #    S I E T -> X
-    #  S I E I T -> X
-    #      S E T -> X
-    #    S E I T -> X
-    #
-    # The following case would not be supported:
-    #
-    #    S I E T1 I T2 -> X
-    #
-    # and T2 would be dropped.
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        send_aggregation = False
-
-        if isinstance(frame, self._start_frame):
-            self._aggregating = True
-            self._seen_start_frame = True
-            self._seen_end_frame = False
-            self._seen_interim_results = False
-            await self.push_frame(frame, direction)
-        elif isinstance(frame, self._end_frame):
-            self._seen_end_frame = True
-            self._seen_start_frame = False
-
-            # We might have received the end frame but we might still be
-            # aggregating (i.e. we have seen interim results but not the final
-            # text).
-            self._aggregating = self._seen_interim_results or len(self._aggregation) == 0
-
-            # Send the aggregation if we are not aggregating anymore (i.e. no
-            # more interim results received).
-            send_aggregation = not self._aggregating
-            await self.push_frame(frame, direction)
-        elif isinstance(frame, self._accumulator_frame):
-            if self._aggregating:
-                self._aggregation += f" {frame.text}"
-                # We have recevied a complete sentence, so if we have seen the
-                # end frame and we were still aggregating, it means we should
-                # send the aggregation.
-                send_aggregation = self._seen_end_frame
-
-            # We just got our final result, so let's reset interim results.
-            self._seen_interim_results = False
-        elif self._interim_accumulator_frame and isinstance(frame, self._interim_accumulator_frame):
-            self._seen_interim_results = True
-        else:
-            await self.push_frame(frame, direction)
-
-        if send_aggregation:
-            await self._push_aggregation()
-
-    async def _push_aggregation(self):
+    async def push_aggregation(self):
         if len(self._aggregation) > 0:
             frame = TextFrame(self._aggregation.strip())
 
@@ -139,21 +23,4 @@ class ResponseAggregator(FrameProcessor):
             await self.push_frame(frame)
 
             # Reset our accumulator state.
-            self._reset()
-
-    def _reset(self):
-        self._aggregation = ""
-        self._aggregating = False
-        self._seen_start_frame = False
-        self._seen_end_frame = False
-        self._seen_interim_results = False
-
-
-class UserResponseAggregator(ResponseAggregator):
-    def __init__(self):
-        super().__init__(
-            start_frame=UserStartedSpeakingFrame,
-            end_frame=UserStoppedSpeakingFrame,
-            accumulator_frame=TranscriptionFrame,
-            interim_accumulator_frame=InterimTranscriptionFrame,
-        )
+            self.reset()

src/pipecat/processors/audio/audio_buffer_processor.py

@@ -32,6 +32,10 @@ class AudioBufferProcessor(FrameProcessor):
     in the case of stereo the left channel will be used for the user's audio and
     the right channel for the bot.
 
+    Most of the time, user audio will be a continuous stream but it's possible
+    that in some cases only the spoken audio is sent. To accomodate for those
+    cases make sure to set `user_continuous_stream` accordingly.
+
     """
 
     def __init__(
@@ -40,6 +44,7 @@ class AudioBufferProcessor(FrameProcessor):
         sample_rate: Optional[int] = None,
         num_channels: int = 1,
         buffer_size: int = 0,
+        user_continuous_stream: bool = True,
         **kwargs,
     ):
         super().__init__(**kwargs)
@@ -47,10 +52,12 @@ class AudioBufferProcessor(FrameProcessor):
         self._sample_rate = 0
         self._num_channels = num_channels
         self._buffer_size = buffer_size
+        self._user_continuous_stream = user_continuous_stream
 
         self._user_audio_buffer = bytearray()
         self._bot_audio_buffer = bytearray()
 
+        # Intermittent (non continous user stream variables)
         self._last_user_frame_at = 0
         self._last_bot_frame_at = 0
 
@@ -98,7 +105,40 @@ class AudioBufferProcessor(FrameProcessor):
         if isinstance(frame, StartFrame):
             self._update_sample_rate(frame)
 
-        if self._recording and isinstance(frame, InputAudioRawFrame):
+        if self._recording:
+            if self._user_continuous_stream:
+                await self._handle_continuous_stream(frame)
+            else:
+                await self._handle_intermittent_stream(frame)
+
+        if self._buffer_size > 0 and len(self._user_audio_buffer) > self._buffer_size:
+            await self._call_on_audio_data_handler()
+
+        if isinstance(frame, (CancelFrame, EndFrame)):
+            await self.stop_recording()
+
+        await self.push_frame(frame, direction)
+
+    def _update_sample_rate(self, frame: StartFrame):
+        self._sample_rate = self._init_sample_rate or frame.audio_out_sample_rate
+
+    async def _handle_continuous_stream(self, frame: Frame):
+        if isinstance(frame, InputAudioRawFrame):
+            # Add user audio.
+            resampled = await self._resample_audio(frame)
+            self._user_audio_buffer.extend(resampled)
+            # Sync the bot's buffer to the user's buffer by adding silence if needed
+            if len(self._user_audio_buffer) > len(self._bot_audio_buffer):
+                silence_size = len(self._user_audio_buffer) - len(self._bot_audio_buffer)
+                silence = b"\x00" * silence_size
+                self._bot_audio_buffer.extend(silence)
+        elif self._recording and isinstance(frame, OutputAudioRawFrame):
+            # Add bot audio.
+            resampled = await self._resample_audio(frame)
+            self._bot_audio_buffer.extend(resampled)
+
+    async def _handle_intermittent_stream(self, frame: Frame):
+        if isinstance(frame, InputAudioRawFrame):
             # Add silence if we need to.
             silence = self._compute_silence(self._last_user_frame_at)
             self._user_audio_buffer.extend(silence)
@@ -117,17 +157,6 @@ class AudioBufferProcessor(FrameProcessor):
             # Save time of frame so we can compute silence.
             self._last_bot_frame_at = time.time()
 
-        if self._buffer_size > 0 and len(self._user_audio_buffer) > self._buffer_size:
-            await self._call_on_audio_data_handler()
-
-        if isinstance(frame, (CancelFrame, EndFrame)):
-            await self.stop_recording()
-
-        await self.push_frame(frame, direction)
-
-    def _update_sample_rate(self, frame: StartFrame):
-        self._sample_rate = self._init_sample_rate or frame.audio_out_sample_rate
-
     async def _call_on_audio_data_handler(self):
         if not self.has_audio() or not self._recording:
             return
@@ -155,10 +184,9 @@ class AudioBufferProcessor(FrameProcessor):
 
     def _compute_silence(self, from_time: float) -> bytes:
         quiet_time = time.time() - from_time
-        # We should get audio frames very frequently. We pick 100ms because
-        # that's big enough, but it could be even a bit slower since we usually
-        # do 20ms audio frames.
-        if from_time == 0 or quiet_time < 0.1:
+        # We should get audio frames very frequently. We introduce silence only
+        # if there's a big enough gap of 1s.
+        if from_time == 0 or quiet_time < 1.0:
             return b""
         num_bytes = int(quiet_time * self._sample_rate) * 2
         silence = b"\x00" * num_bytes

src/pipecat/processors/filters/stt_mute_filter.py

@@ -23,6 +23,8 @@ from pipecat.frames.frames import (
     Frame,
     FunctionCallInProgressFrame,
     FunctionCallResultFrame,
+    InputAudioRawFrame,
+    StartFrame,
     StartInterruptionFrame,
     StopInterruptionFrame,
     STTMuteFrame,
@@ -37,16 +39,18 @@ class STTMuteStrategy(Enum):
     """Strategies determining when STT should be muted.
 
     Attributes:
-        FIRST_SPEECH: Mute only during first bot speech
+        FIRST_SPEECH: Mute only during first detected bot speech
+        MUTE_UNTIL_FIRST_BOT_COMPLETE: Start muted and remain muted until first bot speech completes
         FUNCTION_CALL: Mute during function calls
         ALWAYS: Mute during all bot speech
         CUSTOM: Allow custom logic via callback
     """
 
-    FIRST_SPEECH = "first_speech"  # Mute only during first bot speech
-    FUNCTION_CALL = "function_call"  # Mute during function calls
-    ALWAYS = "always"  # Mute during all bot speech
-    CUSTOM = "custom"  # Allow custom logic via callback
+    FIRST_SPEECH = "first_speech"
+    MUTE_UNTIL_FIRST_BOT_COMPLETE = "mute_until_first_bot_complete"
+    FUNCTION_CALL = "function_call"
+    ALWAYS = "always"
+    CUSTOM = "custom"
 
 
 @dataclass
@@ -57,12 +61,25 @@ class STTMuteConfig:
         strategies: Set of muting strategies to apply
         should_mute_callback: Optional callback for custom muting logic.
             Only required when using STTMuteStrategy.CUSTOM
+
+    Note:
+        MUTE_UNTIL_FIRST_BOT_COMPLETE and FIRST_SPEECH strategies should not be used together
+        as they handle the first bot speech differently.
     """
 
     strategies: set[STTMuteStrategy]
     # Optional callback for custom muting logic
     should_mute_callback: Optional[Callable[["STTMuteFilter"], Awaitable[bool]]] = None
 
+    def __post_init__(self):
+        if (
+            STTMuteStrategy.MUTE_UNTIL_FIRST_BOT_COMPLETE in self.strategies
+            and STTMuteStrategy.FIRST_SPEECH in self.strategies
+        ):
+            raise ValueError(
+                "MUTE_UNTIL_FIRST_BOT_COMPLETE and FIRST_SPEECH strategies should not be used together"
+            )
+
 
 class STTMuteFilter(FrameProcessor):
     """A processor that handles STT muting and interruption control.
@@ -71,28 +88,40 @@ class STTMuteFilter(FrameProcessor):
     feature. When STT is muted, interruptions are automatically disabled.
 
     Args:
-        stt_service: Service handling speech-to-text functionality
         config: Configuration specifying muting strategies
+        stt_service: STT service instance (deprecated, will be removed in future version)
         **kwargs: Additional arguments passed to parent class
     """
 
-    def __init__(self, stt_service: STTService, config: STTMuteConfig, **kwargs):
+    def __init__(
+        self, *, config: STTMuteConfig, stt_service: Optional[STTService] = None, **kwargs
+    ):
         super().__init__(**kwargs)
-        self._stt_service = stt_service
         self._config = config
+        if stt_service is not None:
+            import warnings
+
+            warnings.warn(
+                "The stt_service parameter is deprecated and will be removed in a future version. "
+                "STTMuteFilter now manages mute state internally.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
         self._first_speech_handled = False
         self._bot_is_speaking = False
         self._function_call_in_progress = False
+        self._is_muted = False  # Initialize as unmuted, will set state on StartFrame if needed
 
     @property
     def is_muted(self) -> bool:
         """Returns whether STT is currently muted."""
-        return self._stt_service.is_muted
+        return self._is_muted
 
     async def _handle_mute_state(self, should_mute: bool):
         """Handles both STT muting and interruption control."""
         if should_mute != self.is_muted:
             logger.debug(f"STT {'muting' if should_mute else 'unmuting'}")
+            self._is_muted = should_mute
             await self.push_frame(STTMuteFrame(mute=should_mute))
 
     async def _should_mute(self) -> bool:
@@ -112,6 +141,10 @@ class STTMuteFilter(FrameProcessor):
                         self._first_speech_handled = True
                         return True
 
+                case STTMuteStrategy.MUTE_UNTIL_FIRST_BOT_COMPLETE:
+                    if not self._first_speech_handled:
+                        return True
+
                 case STTMuteStrategy.CUSTOM:
                     if self._bot_is_speaking and self._config.should_mute_callback:
                         should_mute = await self._config.should_mute_callback(self)
@@ -121,25 +154,31 @@ class STTMuteFilter(FrameProcessor):
         return False
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        """Processes incoming frames and manages muting state."""
         await super().process_frame(frame, direction)
 
-        """Processes incoming frames and manages muting state."""
-        # Handle function call state changes
-        if isinstance(frame, FunctionCallInProgressFrame):
+        # Determine if we need to change mute state based on frame type
+        should_mute = None
+
+        # Process frames to determine mute state
+        if isinstance(frame, StartFrame):
+            should_mute = await self._should_mute()
+        elif isinstance(frame, FunctionCallInProgressFrame):
             self._function_call_in_progress = True
-            await self._handle_mute_state(await self._should_mute())
+            should_mute = await self._should_mute()
         elif isinstance(frame, FunctionCallResultFrame):
             self._function_call_in_progress = False
-            await self._handle_mute_state(await self._should_mute())
-        # Handle bot speaking state changes
+            should_mute = await self._should_mute()
         elif isinstance(frame, BotStartedSpeakingFrame):
             self._bot_is_speaking = True
-            await self._handle_mute_state(await self._should_mute())
+            should_mute = await self._should_mute()
         elif isinstance(frame, BotStoppedSpeakingFrame):
             self._bot_is_speaking = False
-            await self._handle_mute_state(await self._should_mute())
+            if not self._first_speech_handled:
+                self._first_speech_handled = True
+            should_mute = await self._should_mute()
 
-        # Handle frame propagation
+        # Then push the original frame
         if isinstance(
             frame,
             (
@@ -147,13 +186,18 @@ class STTMuteFilter(FrameProcessor):
                 StopInterruptionFrame,
                 UserStartedSpeakingFrame,
                 UserStoppedSpeakingFrame,
+                InputAudioRawFrame,
             ),
         ):
             # Only pass VAD-related frames when not muted
             if not self.is_muted:
                 await self.push_frame(frame, direction)
             else:
-                logger.debug(f"{frame.__class__.__name__} suppressed - STT currently muted")
+                logger.trace(f"{frame.__class__.__name__} suppressed - STT currently muted")
         else:
             # Pass all other frames through
             await self.push_frame(frame, direction)
+
+        # Finally handle mute state change if needed
+        if should_mute is not None and should_mute != self.is_muted:
+            await self._handle_mute_state(should_mute)

src/pipecat/processors/frame_processor.py

@@ -73,10 +73,11 @@ class FrameProcessor:
         self._metrics.set_processor_name(self.name)
 
         # Processors have an input queue. The input queue will be processed
-        # immediately (default) or it will block if `pause_processing_frames()` is
-        # called. To resume processing frames we need to call
-        # `resume_processing_frames()`.
+        # immediately (default) or it will block if `pause_processing_frames()`
+        # is called. To resume processing frames we need to call
+        # `resume_processing_frames()` which will wake up the event.
         self.__should_block_frames = False
+        self.__input_event = asyncio.Event()
         self.__input_frame_task: Optional[asyncio.Task] = None
 
         # Every processor in Pipecat should only output frames from a single
@@ -335,8 +336,8 @@ class FrameProcessor:
     def __create_input_task(self):
         if not self.__input_frame_task:
             self.__should_block_frames = False
+            self.__input_event.clear()
             self.__input_queue = asyncio.Queue()
-            self.__input_event = asyncio.Event()
             self.__input_frame_task = self.create_task(self.__input_frame_task_handler())
 
     async def __cancel_input_task(self):

src/pipecat/processors/frameworks/rtvi.py

@@ -5,6 +5,7 @@
 #
 
 import asyncio
+import base64
 from dataclasses import dataclass
 from typing import (
     Any,
@@ -31,6 +32,7 @@ from pipecat.frames.frames import (
     ErrorFrame,
     Frame,
     FunctionCallResultFrame,
+    InputAudioRawFrame,
     InterimTranscriptionFrame,
     LLMFullResponseEndFrame,
     LLMFullResponseStartFrame,
@@ -58,7 +60,9 @@ from pipecat.processors.aggregators.openai_llm_context import (
     OpenAILLMContextFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.services.google.frames import LLMSearchOrigin, LLMSearchResponseFrame
+from pipecat.transports.base_input import BaseInputTransport
+from pipecat.transports.base_output import BaseOutputTransport
+from pipecat.transports.base_transport import BaseTransport
 from pipecat.utils.string import match_endofsentence
 
 RTVI_PROTOCOL_VERSION = "0.3.0"
@@ -296,12 +300,6 @@ class RTVITextMessageData(BaseModel):
     text: str
 
 
-class RTVISearchResponseMessageData(BaseModel):
-    search_result: Optional[str]
-    rendered_content: Optional[str]
-    origins: List[LLMSearchOrigin]
-
-
 class RTVIBotTranscriptionMessage(BaseModel):
     label: RTVIMessageLiteral = RTVI_MESSAGE_LABEL
     type: Literal["bot-transcription"] = "bot-transcription"
@@ -314,12 +312,6 @@ class RTVIBotLLMTextMessage(BaseModel):
     data: RTVITextMessageData
 
 
-class RTVIBotLLMSearchResponseMessage(BaseModel):
-    label: Literal["rtvi-ai"] = "rtvi-ai"
-    type: Literal["bot-llm-search-response"] = "bot-llm-search-response"
-    data: RTVISearchResponseMessageData
-
-
 class RTVIBotTTSTextMessage(BaseModel):
     label: RTVIMessageLiteral = RTVI_MESSAGE_LABEL
     type: Literal["bot-tts-text"] = "bot-tts-text"
@@ -397,6 +389,15 @@ class RTVISpeakingProcessor(RTVIFrameProcessor):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
 
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "'RTVISpeakingProcessor' is deprecated, use an 'RTVIObserver' instead.",
+                DeprecationWarning,
+            )
+
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         await super().process_frame(frame, direction)
 
@@ -432,6 +433,15 @@ class RTVIUserTranscriptionProcessor(RTVIFrameProcessor):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
 
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "'RTVIUserTranscriptionProcessor' is deprecated, use an 'RTVIObserver' instead.",
+                DeprecationWarning,
+            )
+
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         await super().process_frame(frame, direction)
 
@@ -463,6 +473,15 @@ class RTVIUserLLMTextProcessor(RTVIFrameProcessor):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
 
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "'RTVIUserLLMTextProcessor' is deprecated, use an 'RTVIObserver' instead.",
+                DeprecationWarning,
+            )
+
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         await super().process_frame(frame, direction)
 
@@ -490,6 +509,15 @@ class RTVIBotTranscriptionProcessor(RTVIFrameProcessor):
         super().__init__()
         self._aggregation = ""
 
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "'RTVIBotTranscriptionProcessor' is deprecated, use an 'RTVIObserver' instead.",
+                DeprecationWarning,
+            )
+
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         await super().process_frame(frame, direction)
 
@@ -513,6 +541,15 @@ class RTVIBotLLMProcessor(RTVIFrameProcessor):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
 
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "'RTVIBotLLMProcessor' is deprecated, use an 'RTVIObserver' instead.",
+                DeprecationWarning,
+            )
+
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         await super().process_frame(frame, direction)
 
@@ -531,6 +568,15 @@ class RTVIBotTTSProcessor(RTVIFrameProcessor):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
 
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "'RTVIBotTTSProcessor' is deprecated, use an 'RTVIObserver' instead.",
+                DeprecationWarning,
+            )
+
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         await super().process_frame(frame, direction)
 
@@ -549,6 +595,15 @@ class RTVIMetricsProcessor(RTVIFrameProcessor):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
 
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "'RTVIMetricsProcessor' is deprecated, use an 'RTVIObserver' instead.",
+                DeprecationWarning,
+            )
+
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         await super().process_frame(frame, direction)
 
@@ -582,10 +637,18 @@ class RTVIMetricsProcessor(RTVIFrameProcessor):
 
 
 class RTVIObserver(BaseObserver):
-    """This is a pipeline frame observer that is used to send RTVI server
-    messages to clients. The observer does not handle incoming RTVI client
-    messages, which is done by the RTVIProcessor.
+    """Pipeline frame observer for RTVI server message handling.
 
+    This observer monitors pipeline frames and converts them into appropriate RTVI messages
+    for client communication. It handles various frame types including speech events,
+    transcriptions, LLM responses, and TTS events.
+
+    Note:
+        This observer only handles outgoing messages. Incoming RTVI client messages
+        are handled by the RTVIProcessor.
+
+    Args:
+        rtvi (FrameProcessor): The RTVI processor to push frames to.
     """
 
     def __init__(self, rtvi: FrameProcessor):
@@ -602,10 +665,22 @@ class RTVIObserver(BaseObserver):
         direction: FrameDirection,
         timestamp: int,
     ):
+        """Process a frame being pushed through the pipeline.
+
+        Args:
+            src: Source processor pushing the frame
+            dst: Destination processor receiving the frame
+            frame: The frame being pushed
+            direction: Direction of frame flow in pipeline
+            timestamp: Time when frame was pushed
+        """
         # If we have already seen this frame, let's skip it.
         if frame.id in self._frames_seen:
             return
-        self._frames_seen.add(frame.id)
+
+        # This tells whether the frame is already processed. If false, we will try
+        # again the next time we see the frame.
+        mark_as_seen = True
 
         if isinstance(frame, (UserStartedSpeakingFrame, UserStoppedSpeakingFrame)):
             await self._handle_interruptions(frame)
@@ -618,24 +693,34 @@ class RTVIObserver(BaseObserver):
         elif isinstance(frame, UserStartedSpeakingFrame):
             await self._push_bot_transcription()
         elif isinstance(frame, LLMFullResponseStartFrame):
-            await self._push_transport_message_urgent(RTVIBotLLMStartedMessage())
+            await self.push_transport_message_urgent(RTVIBotLLMStartedMessage())
         elif isinstance(frame, LLMFullResponseEndFrame):
-            await self._push_transport_message_urgent(RTVIBotLLMStoppedMessage())
+            await self.push_transport_message_urgent(RTVIBotLLMStoppedMessage())
         elif isinstance(frame, LLMTextFrame):
             await self._handle_llm_text_frame(frame)
-        elif isinstance(frame, LLMSearchResponseFrame):
-            await self._handle_llm_search_response_frame(frame)
         elif isinstance(frame, TTSStartedFrame):
-            await self._push_transport_message_urgent(RTVIBotTTSStartedMessage())
+            await self.push_transport_message_urgent(RTVIBotTTSStartedMessage())
         elif isinstance(frame, TTSStoppedFrame):
-            await self._push_transport_message_urgent(RTVIBotTTSStoppedMessage())
+            await self.push_transport_message_urgent(RTVIBotTTSStoppedMessage())
         elif isinstance(frame, TTSTextFrame):
-            message = RTVIBotTTSTextMessage(data=RTVITextMessageData(text=frame.text))
-            await self._push_transport_message_urgent(message)
+            if isinstance(src, BaseOutputTransport):
+                message = RTVIBotTTSTextMessage(data=RTVITextMessageData(text=frame.text))
+                await self.push_transport_message_urgent(message)
+            else:
+                mark_as_seen = False
         elif isinstance(frame, MetricsFrame):
             await self._handle_metrics(frame)
 
-    async def _push_transport_message_urgent(self, model: BaseModel, exclude_none: bool = True):
+        if mark_as_seen:
+            self._frames_seen.add(frame.id)
+
+    async def push_transport_message_urgent(self, model: BaseModel, exclude_none: bool = True):
+        """Push an urgent transport message to the RTVI processor.
+
+        Args:
+            model: The message model to send
+            exclude_none: Whether to exclude None values from the model dump
+        """
         frame = TransportMessageUrgentFrame(message=model.model_dump(exclude_none=exclude_none))
         await self._rtvi.push_frame(frame)
 
@@ -644,7 +729,7 @@ class RTVIObserver(BaseObserver):
             message = RTVIBotTranscriptionMessage(
                 data=RTVITextMessageData(text=self._bot_transcription)
             )
-            await self._push_transport_message_urgent(message)
+            await self.push_transport_message_urgent(message)
             self._bot_transcription = ""
 
     async def _handle_interruptions(self, frame: Frame):
@@ -655,7 +740,7 @@ class RTVIObserver(BaseObserver):
             message = RTVIUserStoppedSpeakingMessage()
 
         if message:
-            await self._push_transport_message_urgent(message)
+            await self.push_transport_message_urgent(message)
 
     async def _handle_bot_speaking(self, frame: Frame):
         message = None
@@ -665,26 +750,16 @@ class RTVIObserver(BaseObserver):
             message = RTVIBotStoppedSpeakingMessage()
 
         if message:
-            await self._push_transport_message_urgent(message)
+            await self.push_transport_message_urgent(message)
 
     async def _handle_llm_text_frame(self, frame: LLMTextFrame):
         message = RTVIBotLLMTextMessage(data=RTVITextMessageData(text=frame.text))
-        await self._push_transport_message_urgent(message)
+        await self.push_transport_message_urgent(message)
 
         self._bot_transcription += frame.text
         if match_endofsentence(self._bot_transcription):
             await self._push_bot_transcription()
 
-    async def _handle_llm_search_response_frame(self, frame: LLMSearchResponseFrame):
-        message = RTVIBotLLMSearchResponseMessage(
-            data=RTVISearchResponseMessageData(
-                search_result=frame.search_result,
-                origins=frame.origins,
-                rendered_content=frame.rendered_content,
-            )
-        )
-        await self._push_transport_message_urgent(message)
-
     async def _handle_user_transcriptions(self, frame: Frame):
         message = None
         if isinstance(frame, TranscriptionFrame):
@@ -701,7 +776,7 @@ class RTVIObserver(BaseObserver):
             )
 
         if message:
-            await self._push_transport_message_urgent(message)
+            await self.push_transport_message_urgent(message)
 
     async def _handle_context(self, frame: OpenAILLMContextFrame):
         try:
@@ -715,7 +790,7 @@ class RTVIObserver(BaseObserver):
                     else:
                         text = content
                     rtvi_message = RTVIUserLLMTextMessage(data=RTVITextMessageData(text=text))
-                    await self._push_transport_message_urgent(rtvi_message)
+                    await self.push_transport_message_urgent(rtvi_message)
         except TypeError as e:
             logger.warning(f"Caught an error while trying to handle context: {e}")
 
@@ -740,7 +815,7 @@ class RTVIObserver(BaseObserver):
                 metrics["characters"].append(d.model_dump(exclude_none=True))
 
         message = RTVIMetricsMessage(data=metrics)
-        await self._push_transport_message_urgent(message)
+        await self.push_transport_message_urgent(message)
 
 
 class RTVIProcessor(FrameProcessor):
@@ -748,6 +823,7 @@ class RTVIProcessor(FrameProcessor):
         self,
         *,
         config: RTVIConfig = RTVIConfig(config=[]),
+        transport: Optional[BaseTransport] = None,
         **kwargs,
     ):
         super().__init__(**kwargs)
@@ -773,7 +849,24 @@ class RTVIProcessor(FrameProcessor):
         self._register_event_handler("on_bot_started")
         self._register_event_handler("on_client_ready")
 
+        self._input_transport = None
+        self._transport = transport
+        if self._transport:
+            input_transport = self._transport.input()
+            if isinstance(input_transport, BaseInputTransport):
+                self._input_transport = input_transport
+                self._input_transport.enable_audio_in_stream_on_start(False)
+
     def observer(self) -> RTVIObserver:
+        import warnings
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "'RTVI.observer()' is deprecated, instantiate an 'RTVIObserver' directly instead.",
+                DeprecationWarning,
+            )
+
         return RTVIObserver(self)
 
     def register_action(self, action: RTVIAction):
@@ -933,6 +1026,8 @@ class RTVIProcessor(FrameProcessor):
                 case "llm-function-call-result":
                     data = RTVILLMFunctionCallResultData.model_validate(message.data)
                     await self._handle_function_call_result(data)
+                case "raw-audio" | "raw-audio-batch":
+                    await self._handle_audio_buffer(message.data)
 
                 case _:
                     await self._send_error_response(message.id, f"Unsupported type {message.type}")
@@ -945,9 +1040,34 @@ class RTVIProcessor(FrameProcessor):
             logger.warning(f"Exception processing message: {e}")
 
     async def _handle_client_ready(self, request_id: str):
+        logger.debug("Received client-ready")
+        if self._input_transport:
+            self._input_transport.start_audio_in_streaming()
+
         self._client_ready_id = request_id
         await self.set_client_ready()
 
+    async def _handle_audio_buffer(self, data):
+        if not self._input_transport:
+            return
+
+        # Extract audio batch ensuring it's a list
+        audio_list = data.get("base64AudioBatch") or [data.get("base64Audio")]
+
+        try:
+            for base64_audio in filter(None, audio_list):  # Filter out None values
+                pcm_bytes = base64.b64decode(base64_audio)
+                frame = InputAudioRawFrame(
+                    audio=pcm_bytes,
+                    sample_rate=data["sampleRate"],
+                    num_channels=data["numChannels"],
+                )
+                await self._input_transport.push_audio_frame(frame)
+
+        except (KeyError, TypeError, ValueError) as e:
+            # Handle missing keys, decoding errors, and invalid types
+            logger.error(f"Error processing audio buffer: {e}")
+
     async def _handle_describe_config(self, request_id: str):
         services = list(self._registered_services.values())
         message = RTVIDescribeConfig(id=request_id, data=RTVIDescribeConfigData(config=services))

src/pipecat/services/ai_services.py

@@ -15,6 +15,7 @@ from loguru import logger
 from pipecat.audio.utils import calculate_audio_volume, exp_smoothing
 from pipecat.frames.frames import (
     AudioRawFrame,
+    BotStoppedSpeakingFrame,
     CancelFrame,
     EndFrame,
     ErrorFrame,
@@ -75,13 +76,13 @@ class AIService(FrameProcessor):
         )
 
         for key, value in settings.items():
-            print("Update request for:", key, value)
+            logger.debug("Update request for:", key, value)
 
             if key in self._settings:
                 logger.info(f"Updating LLM setting {key} to: [{value}]")
                 self._settings[key] = value
             elif key in SessionProperties.model_fields:
-                print("Attempting to update", key, value)
+                logger.debug("Attempting to update", key, value)
 
                 try:
                     from pipecat.services.openai_realtime_beta.events import (
@@ -174,6 +175,7 @@ class LLMService(AIService):
             f = self._callbacks[None]
         else:
             return None
+        await self.call_start_function(context, function_name)
         await context.call_function(
             f,
             function_name=function_name,
@@ -212,6 +214,8 @@ class TTSService(AIService):
         push_silence_after_stop: bool = False,
         # if push_silence_after_stop is True, send this amount of audio silence
         silence_time_s: float = 2.0,
+        # if True, we will pause processing frames while we are receiving audio
+        pause_frame_processing: bool = False,
         # TTS output sample rate
         sample_rate: Optional[int] = None,
         text_filter: Optional[BaseTextFilter] = None,
@@ -224,6 +228,7 @@ class TTSService(AIService):
         self._stop_frame_timeout_s: float = stop_frame_timeout_s
         self._push_silence_after_stop: bool = push_silence_after_stop
         self._silence_time_s: float = silence_time_s
+        self._pause_frame_processing: bool = pause_frame_processing
         self._init_sample_rate = sample_rate
         self._sample_rate = 0
         self._voice_id: str = ""
@@ -234,6 +239,7 @@ class TTSService(AIService):
         self._stop_frame_queue: asyncio.Queue = asyncio.Queue()
 
         self._current_sentence: str = ""
+        self._processing_text: bool = False
 
     @property
     def sample_rate(self) -> int:
@@ -299,6 +305,7 @@ class TTSService(AIService):
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         await super().process_frame(frame, direction)
+
         if (
             isinstance(frame, TextFrame)
             and not isinstance(frame, InterimTranscriptionFrame)
@@ -307,9 +314,16 @@ class TTSService(AIService):
             await self._process_text_frame(frame)
         elif isinstance(frame, StartInterruptionFrame):
             await self._handle_interruption(frame, direction)
+            await self.push_frame(frame, direction)
         elif isinstance(frame, (LLMFullResponseEndFrame, EndFrame)):
+            # We pause processing incoming frames if the LLM response included
+            # text (it might be that it's only a function calling response). We
+            # pause to avoid audio overlapping.
+            await self._maybe_pause_frame_processing()
+
             sentence = self._current_sentence
             self._current_sentence = ""
+            self._processing_text = False
             await self._push_tts_frames(sentence)
             if isinstance(frame, LLMFullResponseEndFrame):
                 if self._push_text_frames:
@@ -318,9 +332,16 @@ class TTSService(AIService):
                 await self.push_frame(frame, direction)
         elif isinstance(frame, TTSSpeakFrame):
             await self._push_tts_frames(frame.text)
+            # We pause processing incoming frames because we are sending data to
+            # the TTS. We pause to avoid audio overlapping.
+            await self._maybe_pause_frame_processing()
             await self.flush_audio()
+            self._processing_text = False
         elif isinstance(frame, TTSUpdateSettingsFrame):
             await self._update_settings(frame.settings)
+        elif isinstance(frame, BotStoppedSpeakingFrame):
+            await self._maybe_resume_frame_processing()
+            await self.push_frame(frame, direction)
         else:
             await self.push_frame(frame, direction)
 
@@ -347,9 +368,17 @@ class TTSService(AIService):
 
     async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
         self._current_sentence = ""
+        self._processing_text = False
         if self._text_filter:
             self._text_filter.handle_interruption()
-        await self.push_frame(frame, direction)
+
+    async def _maybe_pause_frame_processing(self):
+        if self._processing_text and self._pause_frame_processing:
+            await self.pause_processing_frames()
+
+    async def _maybe_resume_frame_processing(self):
+        if self._pause_frame_processing:
+            await self.resume_processing_frames()
 
     async def _process_text_frame(self, frame: TextFrame):
         text: Optional[str] = None
@@ -371,6 +400,11 @@ class TTSService(AIService):
         if not text.strip():
             return
 
+        # This is just a flag that indicates if we sent something to the TTS
+        # service. It will be cleared if we sent text because of a TTSSpeakFrame
+        # or when we received an LLMFullResponseEndFrame
+        self._processing_text = True
+
         await self.start_processing_metrics()
         if self._text_filter:
             self._text_filter.reset_interruption()
@@ -419,7 +453,7 @@ class WordTTSService(TTSService):
 
     async def start(self, frame: StartFrame):
         await super().start(frame)
-        await self._create_words_task()
+        self._create_words_task()
 
     async def stop(self, frame: EndFrame):
         await super().stop(frame)
@@ -439,7 +473,7 @@ class WordTTSService(TTSService):
         await super()._handle_interruption(frame, direction)
         self.reset_word_timestamps()
 
-    async def _create_words_task(self):
+    def _create_words_task(self):
         self._words_task = self.create_task(self._words_task_handler())
 
     async def _stop_words_task(self):
@@ -469,6 +503,115 @@ class WordTTSService(TTSService):
             self._words_queue.task_done()
 
 
+class AudioContextWordTTSService(WordTTSService):
+    """This services allow us to send multiple TTS request to the services. Each
+    request could be multiple sentences long which are grouped by context. For
+    this to work, the TTS service needs to support handling multiple requests at
+    once (i.e. multiple simultaneous contexts).
+
+    The audio received from the TTS will be played in context order. That is, if
+    we requested audio for a context "A" and then audio for context "B", the
+    audio from context ID "A" will be played first.
+
+    """
+
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+        self._contexts_queue = asyncio.Queue()
+        self._contexts: Dict[str, asyncio.Queue] = {}
+        self._audio_context_task = None
+
+    async def create_audio_context(self, context_id: str):
+        """Create a new audio context."""
+        await self._contexts_queue.put(context_id)
+        self._contexts[context_id] = asyncio.Queue()
+        logger.trace(f"{self} created audio context {context_id}")
+
+    async def append_to_audio_context(self, context_id: str, frame: TTSAudioRawFrame):
+        """Append audio to an existing context."""
+        if self.audio_context_available(context_id):
+            logger.trace(f"{self} appending audio {frame} to audio context {context_id}")
+            await self._contexts[context_id].put(frame)
+        else:
+            logger.warning(f"{self} unable to append audio to context {context_id}")
+
+    async def remove_audio_context(self, context_id: str):
+        """Remove an existing audio context."""
+        if self.audio_context_available(context_id):
+            # We just mark the audio context for deletion by appending
+            # None. Once we reach None while handling audio we know we can
+            # safely remove the context.
+            logger.trace(f"{self} marking audio context {context_id} for deletion")
+            await self._contexts[context_id].put(None)
+        else:
+            logger.warning(f"{self} unable to remove context {context_id}")
+
+    def audio_context_available(self, context_id: str) -> bool:
+        """Checks whether the given audio context is registered."""
+        return context_id in self._contexts
+
+    async def start(self, frame: StartFrame):
+        await super().start(frame)
+        self._create_audio_context_task()
+
+    async def stop(self, frame: EndFrame):
+        await super().stop(frame)
+        await self._stop_audio_context_task()
+
+    async def cancel(self, frame: CancelFrame):
+        await super().cancel(frame)
+        await self._stop_audio_context_task()
+
+    async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
+        await super()._handle_interruption(frame, direction)
+        await self._stop_audio_context_task()
+        self._create_audio_context_task()
+
+    def _create_audio_context_task(self):
+        self._contexts_queue = asyncio.Queue()
+        self._contexts: Dict[str, asyncio.Queue] = {}
+        self._audio_context_task = self.create_task(self._audio_context_task_handler())
+
+    async def _stop_audio_context_task(self):
+        if self._audio_context_task:
+            await self.cancel_task(self._audio_context_task)
+            self._audio_context_task = None
+
+    async def _audio_context_task_handler(self):
+        """In this task we process audio contexts in order."""
+        while True:
+            context_id = await self._contexts_queue.get()
+
+            # Process the audio context until the context doesn't have more
+            # audio available (i.e. we find None).
+            await self._handle_audio_context(context_id)
+
+            # We just finished processing the context, so we can safely remove it.
+            del self._contexts[context_id]
+            self._contexts_queue.task_done()
+
+            # Append some silence between sentences.
+            silence = b"\x00" * self.sample_rate
+            frame = TTSAudioRawFrame(audio=silence, sample_rate=self.sample_rate, num_channels=1)
+            await self.push_frame(frame)
+
+    async def _handle_audio_context(self, context_id: str):
+        # If we don't receive any audio during this time, we consider the context finished.
+        AUDIO_CONTEXT_TIMEOUT = 3.0
+        queue = self._contexts[context_id]
+        running = True
+        while running:
+            try:
+                frame = await asyncio.wait_for(queue.get(), timeout=AUDIO_CONTEXT_TIMEOUT)
+                if frame:
+                    await self.push_frame(frame)
+                running = frame is not None
+            except asyncio.TimeoutError:
+                # We didn't get audio, so let's consider this context finished.
+                logger.trace(f"{self} time out on audio context {context_id}")
+                break
+
+
 class STTService(AIService):
     """STTService is a base class for speech-to-text services."""
 
@@ -525,9 +668,13 @@ class STTService(AIService):
             else:
                 logger.warning(f"Unknown setting for STT service: {key}")
 
-    async def process_audio_frame(self, frame: AudioRawFrame):
-        if not self._muted:
-            await self.process_generator(self.run_stt(frame.audio))
+    async def process_audio_frame(self, frame: AudioRawFrame, direction: FrameDirection):
+        if self._muted:
+            return
+
+        await self.process_generator(self.run_stt(frame.audio))
+        if self._audio_passthrough:
+            await self.push_frame(frame, direction)
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
         """Processes a frame of audio data, either buffering or transcribing it."""
@@ -537,9 +684,7 @@ class STTService(AIService):
             # In this service we accumulate audio internally and at the end we
             # push a TextFrame. We also push audio downstream in case someone
             # else needs it.
-            await self.process_audio_frame(frame)
-            if self._audio_passthrough:
-                await self.push_frame(frame, direction)
+            await self.process_audio_frame(frame, direction)
         elif isinstance(frame, STTUpdateSettingsFrame):
             await self._update_settings(frame.settings)
         elif isinstance(frame, STTMuteFrame):
@@ -575,7 +720,7 @@ class SegmentedSTTService(STTService):
         self._smoothing_factor = 0.2
         self._prev_volume = 0
 
-    async def process_audio_frame(self, frame: AudioRawFrame):
+    async def process_audio_frame(self, frame: AudioRawFrame, direction: FrameDirection):
         # Try to filter out empty background noise
         volume = self._get_smoothed_volume(frame)
         if volume >= self._min_volume:

src/pipecat/services/anthropic.py

@@ -126,9 +126,11 @@ class AnthropicLLMService(LLMService):
     def create_context_aggregator(
         context: OpenAILLMContext, *, assistant_expect_stripped_words: bool = True
     ) -> AnthropicContextAggregatorPair:
+        if isinstance(context, OpenAILLMContext):
+            context = AnthropicLLMContext.from_openai_context(context)
         user = AnthropicUserContextAggregator(context)
         assistant = AnthropicAssistantContextAggregator(
-            user, expect_stripped_words=assistant_expect_stripped_words
+            context, expect_stripped_words=assistant_expect_stripped_words
         )
         return AnthropicContextAggregatorPair(_user=user, _assistant=assistant)
 
@@ -651,11 +653,8 @@ class AnthropicLLMContext(OpenAILLMContext):
 
 
 class AnthropicUserContextAggregator(LLMUserContextAggregator):
-    def __init__(self, context: OpenAILLMContext | AnthropicLLMContext):
-        super().__init__(context=context)
-
-        if isinstance(context, OpenAILLMContext):
-            self._context = AnthropicLLMContext.from_openai_context(context)
+    def __init__(self, context: OpenAILLMContext | AnthropicLLMContext, **kwargs):
+        super().__init__(context=context, **kwargs)
 
     async def process_frame(self, frame, direction):
         await super().process_frame(frame, direction)
@@ -703,9 +702,8 @@ class AnthropicUserContextAggregator(LLMUserContextAggregator):
 
 
 class AnthropicAssistantContextAggregator(LLMAssistantContextAggregator):
-    def __init__(self, user_context_aggregator: AnthropicUserContextAggregator, **kwargs):
-        super().__init__(context=user_context_aggregator._context, **kwargs)
-        self._user_context_aggregator = user_context_aggregator
+    def __init__(self, context: OpenAILLMContext | AnthropicLLMContext, **kwargs):
+        super().__init__(context=context, **kwargs)
         self._function_call_in_progress = None
         self._function_call_result = None
         self._pending_image_frame_message = None
@@ -725,7 +723,7 @@ class AnthropicAssistantContextAggregator(LLMAssistantContextAggregator):
             ):
                 self._function_call_in_progress = None
                 self._function_call_result = frame
-                await self._push_aggregation()
+                await self.push_aggregation()
             else:
                 logger.warning(
                     "FunctionCallResultFrame tool_call_id != InProgressFrame tool_call_id"
@@ -734,9 +732,9 @@ class AnthropicAssistantContextAggregator(LLMAssistantContextAggregator):
                 self._function_call_result = None
         elif isinstance(frame, AnthropicImageMessageFrame):
             self._pending_image_frame_message = frame
-            await self._push_aggregation()
+            await self.push_aggregation()
 
-    async def _push_aggregation(self):
+    async def push_aggregation(self):
         if not (
             self._aggregation or self._function_call_result or self._pending_image_frame_message
         ):
@@ -746,7 +744,7 @@ class AnthropicAssistantContextAggregator(LLMAssistantContextAggregator):
         properties: Optional[FunctionCallResultProperties] = None
 
         aggregation = self._aggregation
-        self._reset()
+        self.reset()
 
         try:
             if self._function_call_result:
@@ -799,15 +797,14 @@ class AnthropicAssistantContextAggregator(LLMAssistantContextAggregator):
                 run_llm = True
 
             if run_llm:
-                await self._user_context_aggregator.push_context_frame()
+                await self.push_context_frame(FrameDirection.UPSTREAM)
 
             # Emit the on_context_updated callback once the function call result is added to the context
             if properties and properties.on_context_updated is not None:
                 await properties.on_context_updated()
 
             # Push context frame
-            frame = OpenAILLMContextFrame(self._context)
-            await self.push_frame(frame)
+            await self.push_context_frame()
 
             # Push timestamp frame with current time
             timestamp_frame = OpenAILLMContextAssistantTimestampFrame(timestamp=time_now_iso8601())

src/pipecat/services/azure.py

@@ -577,35 +577,43 @@ class AzureTTSService(AzureBaseTTSService):
         logger.debug(f"Generating TTS: [{text}]")
 
         try:
-            await self.start_ttfb_metrics()
-            yield TTSStartedFrame()
+            if self._speech_synthesizer is None:
+                error_msg = "Speech synthesizer not initialized."
+                logger.error(error_msg)
+                yield ErrorFrame(error_msg)
+                return
 
-            ssml = self._construct_ssml(text)
+            try:
+                await self.start_ttfb_metrics()
+                yield TTSStartedFrame()
 
-            # Start synthesis
-            self._speech_synthesizer.speak_ssml_async(ssml)
+                ssml = self._construct_ssml(text)
+                self._speech_synthesizer.speak_ssml_async(ssml)
+                await self.start_tts_usage_metrics(text)
 
-            await self.start_tts_usage_metrics(text)
+                # Stream audio chunks as they arrive
+                while True:
+                    chunk = await self._audio_queue.get()
+                    if chunk is None:  # End of stream
+                        break
 
-            # Stream audio chunks as they arrive
-            while True:
-                chunk = await self._audio_queue.get()
-                if chunk is None:  # End of stream
-                    break
+                    await self.stop_ttfb_metrics()
+                    yield TTSAudioRawFrame(
+                        audio=chunk,
+                        sample_rate=self.sample_rate,
+                        num_channels=1,
+                    )
 
-                await self.stop_ttfb_metrics()
+                yield TTSStoppedFrame()
 
-                yield TTSAudioRawFrame(
-                    audio=chunk,
-                    sample_rate=self.sample_rate,
-                    num_channels=1,
-                )
-
-            yield TTSStoppedFrame()
+            except Exception as e:
+                logger.error(f"{self} error during synthesis: {e}")
+                yield TTSStoppedFrame()
+                # Could add reconnection logic here if needed
+                return
 
         except Exception as e:
-            logger.error(f"{self} error generating TTS: {e}")
-            yield ErrorFrame(f"{self} error: {str(e)}")
+            logger.error(f"{self} exception: {e}")
 
 
 class AzureHttpTTSService(AzureBaseTTSService):

src/pipecat/services/base_whisper.py

@@ -0,0 +1,183 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+from typing import AsyncGenerator, Optional
+
+from loguru import logger
+
+from pipecat.frames.frames import ErrorFrame, Frame, TranscriptionFrame
+from pipecat.services.ai_services import SegmentedSTTService
+from pipecat.transcriptions.language import Language
+from pipecat.utils.time import time_now_iso8601
+
+try:
+    from openai import AsyncOpenAI
+    from openai.types.audio import Transcription
+except ModuleNotFoundError as e:
+    logger.error(f"Exception: {e}")
+    logger.error(
+        "In order to use OpenAI, you need to `pip install pipecat-ai[openai]`. Also, set `OPENAI_API_KEY` environment variable."
+    )
+    raise Exception(f"Missing module: {e}")
+
+
+def language_to_whisper_language(language: Language) -> Optional[str]:
+    """Language support for Whisper API.
+
+    Docs: https://platform.openai.com/docs/guides/speech-to-text#supported-languages
+    """
+    BASE_LANGUAGES = {
+        Language.AF: "af",
+        Language.AR: "ar",
+        Language.HY: "hy",
+        Language.AZ: "az",
+        Language.BE: "be",
+        Language.BS: "bs",
+        Language.BG: "bg",
+        Language.CA: "ca",
+        Language.ZH: "zh",
+        Language.HR: "hr",
+        Language.CS: "cs",
+        Language.DA: "da",
+        Language.NL: "nl",
+        Language.EN: "en",
+        Language.ET: "et",
+        Language.FI: "fi",
+        Language.FR: "fr",
+        Language.GL: "gl",
+        Language.DE: "de",
+        Language.EL: "el",
+        Language.HE: "he",
+        Language.HI: "hi",
+        Language.HU: "hu",
+        Language.IS: "is",
+        Language.ID: "id",
+        Language.IT: "it",
+        Language.JA: "ja",
+        Language.KN: "kn",
+        Language.KK: "kk",
+        Language.KO: "ko",
+        Language.LV: "lv",
+        Language.LT: "lt",
+        Language.MK: "mk",
+        Language.MS: "ms",
+        Language.MR: "mr",
+        Language.MI: "mi",
+        Language.NE: "ne",
+        Language.NO: "no",
+        Language.FA: "fa",
+        Language.PL: "pl",
+        Language.PT: "pt",
+        Language.RO: "ro",
+        Language.RU: "ru",
+        Language.SR: "sr",
+        Language.SK: "sk",
+        Language.SL: "sl",
+        Language.ES: "es",
+        Language.SW: "sw",
+        Language.SV: "sv",
+        Language.TL: "tl",
+        Language.TA: "ta",
+        Language.TH: "th",
+        Language.TR: "tr",
+        Language.UK: "uk",
+        Language.UR: "ur",
+        Language.VI: "vi",
+        Language.CY: "cy",
+    }
+
+    result = BASE_LANGUAGES.get(language)
+
+    # If not found in base languages, try to find the base language from a variant
+    if not result:
+        lang_str = str(language.value)
+        base_code = lang_str.split("-")[0].lower()
+        result = base_code if base_code in BASE_LANGUAGES.values() else None
+
+    return result
+
+
+class BaseWhisperSTTService(SegmentedSTTService):
+    """Base class for Whisper-based speech-to-text services.
+
+    Provides common functionality for services implementing the Whisper API interface,
+    including metrics generation and error handling.
+
+    Args:
+        model: Name of the Whisper model to use.
+        api_key: Service API key. Defaults to None.
+        base_url: Service API base URL. Defaults to None.
+        language: Language of the audio input. Defaults to English.
+        prompt: Optional text to guide the model's style or continue a previous segment.
+        temperature: Sampling temperature between 0 and 1. Defaults to 0.0.
+        **kwargs: Additional arguments passed to SegmentedSTTService.
+    """
+
+    def __init__(
+        self,
+        *,
+        model: str,
+        api_key: Optional[str] = None,
+        base_url: Optional[str] = None,
+        language: Optional[Language] = Language.EN,
+        prompt: Optional[str] = None,
+        temperature: Optional[float] = None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.set_model_name(model)
+        self._client = self._create_client(api_key, base_url)
+        self._language = self.language_to_service_language(language or Language.EN)
+        self._prompt = prompt
+        self._temperature = temperature
+
+    def _create_client(self, api_key: Optional[str], base_url: Optional[str]):
+        return AsyncOpenAI(api_key=api_key, base_url=base_url)
+
+    async def set_model(self, model: str):
+        self.set_model_name(model)
+
+    def can_generate_metrics(self) -> bool:
+        return True
+
+    def language_to_service_language(self, language: Language) -> Optional[str]:
+        return language_to_whisper_language(language)
+
+    async def run_stt(self, audio: bytes) -> AsyncGenerator[Frame, None]:
+        try:
+            await self.start_processing_metrics()
+            await self.start_ttfb_metrics()
+
+            response = await self._transcribe(audio)
+
+            await self.stop_ttfb_metrics()
+            await self.stop_processing_metrics()
+
+            text = response.text.strip()
+
+            if text:
+                logger.debug(f"Transcription: [{text}]")
+                yield TranscriptionFrame(text, "", time_now_iso8601())
+            else:
+                logger.warning("Received empty transcription from API")
+
+        except Exception as e:
+            logger.exception(f"Exception during transcription: {e}")
+            yield ErrorFrame(f"Error during transcription: {str(e)}")
+
+    async def _transcribe(self, audio: bytes) -> Transcription:
+        """Transcribe audio data to text.
+
+        Args:
+            audio: Raw audio data in WAV format.
+
+        Returns:
+            Transcription: Object containing the transcribed text.
+
+        Raises:
+            NotImplementedError: Must be implemented by subclasses.
+        """
+        raise NotImplementedError

src/pipecat/services/cartesia.py

@@ -27,7 +27,7 @@ from pipecat.frames.frames import (
     TTSStoppedFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
-from pipecat.services.ai_services import TTSService, WordTTSService
+from pipecat.services.ai_services import AudioContextWordTTSService, TTSService
 from pipecat.services.websocket_service import WebsocketService
 from pipecat.transcriptions.language import Language
 
@@ -75,7 +75,7 @@ def language_to_cartesia_language(language: Language) -> Optional[str]:
     return result
 
 
-class CartesiaTTSService(WordTTSService, WebsocketService):
+class CartesiaTTSService(AudioContextWordTTSService, WebsocketService):
     class InputParams(BaseModel):
         language: Optional[Language] = Language.EN
         speed: Optional[Union[str, float]] = ""
@@ -105,10 +105,11 @@ class CartesiaTTSService(WordTTSService, WebsocketService):
         # if we're interrupted. Cartesia gives us word-by-word timestamps. We
         # can use those to generate text frames ourselves aligned with the
         # playout timing of the audio!
-        WordTTSService.__init__(
+        AudioContextWordTTSService.__init__(
             self,
             aggregate_sentences=True,
             push_text_frames=False,
+            pause_frame_processing=True,
             sample_rate=sample_rate,
             **kwargs,
         )
@@ -191,12 +192,12 @@ class CartesiaTTSService(WordTTSService, WebsocketService):
         self._receive_task = self.create_task(self._receive_task_handler(self.push_error))
 
     async def _disconnect(self):
-        await self._disconnect_websocket()
-
         if self._receive_task:
             await self.cancel_task(self._receive_task)
             self._receive_task = None
 
+        await self._disconnect_websocket()
+
     async def _connect_websocket(self):
         try:
             logger.debug("Connecting to Cartesia")
@@ -239,21 +240,19 @@ class CartesiaTTSService(WordTTSService, WebsocketService):
         logger.trace(f"{self}: flushing audio")
         msg = self._build_msg(text="", continue_transcript=False)
         await self._websocket.send(msg)
+        self._context_id = None
 
     async def _receive_messages(self):
         async for message in self._get_websocket():
             msg = json.loads(message)
-            if not msg or msg["context_id"] != self._context_id:
+            if not msg or not self.audio_context_available(msg["context_id"]):
                 continue
             if msg["type"] == "done":
                 await self.stop_ttfb_metrics()
-                # Unset _context_id but not the _context_id_start_timestamp
-                # because we are likely still playing out audio and need the
-                # timestamp to set send context frames.
-                self._context_id = None
                 await self.add_word_timestamps(
                     [("TTSStoppedFrame", 0), ("LLMFullResponseEndFrame", 0), ("Reset", 0)]
                 )
+                await self.remove_audio_context(msg["context_id"])
             elif msg["type"] == "timestamps":
                 await self.add_word_timestamps(
                     list(zip(msg["word_timestamps"]["words"], msg["word_timestamps"]["start"]))
@@ -266,28 +265,16 @@ class CartesiaTTSService(WordTTSService, WebsocketService):
                     sample_rate=self.sample_rate,
                     num_channels=1,
                 )
-                await self.push_frame(frame)
+                await self.append_to_audio_context(msg["context_id"], frame)
             elif msg["type"] == "error":
                 logger.error(f"{self} error: {msg}")
                 await self.push_frame(TTSStoppedFrame())
                 await self.stop_all_metrics()
                 await self.push_error(ErrorFrame(f"{self} error: {msg['error']}"))
+                self._context_id = None
             else:
                 logger.error(f"{self} error, unknown message type: {msg}")
 
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        # If we received a TTSSpeakFrame and the LLM response included text (it
-        # might be that it's only a function calling response) we pause
-        # processing more frames until we receive a BotStoppedSpeakingFrame.
-        if isinstance(frame, TTSSpeakFrame):
-            await self.pause_processing_frames()
-        elif isinstance(frame, LLMFullResponseEndFrame) and self._context_id:
-            await self.pause_processing_frames()
-        elif isinstance(frame, BotStoppedSpeakingFrame):
-            await self.resume_processing_frames()
-
     async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
         logger.debug(f"Generating TTS: [{text}]")
 
@@ -299,6 +286,7 @@ class CartesiaTTSService(WordTTSService, WebsocketService):
                 await self.start_ttfb_metrics()
                 yield TTSStartedFrame()
                 self._context_id = str(uuid.uuid4())
+                await self.create_audio_context(self._context_id)
 
             msg = self._build_msg(text=text or " ")  # Text must contain at least one character
 

src/pipecat/services/deepgram.py

@@ -5,7 +5,7 @@
 #
 
 import asyncio
-from typing import AsyncGenerator, Optional
+from typing import AsyncGenerator, Dict, Optional
 
 from loguru import logger
 
@@ -34,6 +34,7 @@ try:
         AsyncListenWebSocketClient,
         DeepgramClient,
         DeepgramClientOptions,
+        ErrorResponse,
         LiveOptions,
         LiveResultResponse,
         LiveTranscriptionEvents,
@@ -120,6 +121,7 @@ class DeepgramSTTService(STTService):
         url: str = "",
         sample_rate: Optional[int] = None,
         live_options: Optional[LiveOptions] = None,
+        addons: Optional[Dict] = None,
         **kwargs,
     ):
         super().__init__(sample_rate=sample_rate, **kwargs)
@@ -127,7 +129,7 @@ class DeepgramSTTService(STTService):
         default_options = LiveOptions(
             encoding="linear16",
             language=Language.EN,
-            model="nova-2-general",
+            model="nova-3-general",
             channels=1,
             interim_results=True,
             smart_format=True,
@@ -147,6 +149,7 @@ class DeepgramSTTService(STTService):
             merged_options.language = merged_options.language.value
 
         self._settings = merged_options.to_dict()
+        self._addons = addons
 
         self._client = DeepgramClient(
             api_key,
@@ -155,13 +158,10 @@ class DeepgramSTTService(STTService):
                 options={"keepalive": "true"},  # verbose=logging.DEBUG
             ),
         )
-        self._connection: AsyncListenWebSocketClient = self._client.listen.asyncwebsocket.v("1")
-        self._connection.on(LiveTranscriptionEvents.Transcript, self._on_message)
+
         if self.vad_enabled:
             self._register_event_handler("on_speech_started")
             self._register_event_handler("on_utterance_end")
-            self._connection.on(LiveTranscriptionEvents.SpeechStarted, self._on_speech_started)
-            self._connection.on(LiveTranscriptionEvents.UtteranceEnd, self._on_utterance_end)
 
     @property
     def vad_enabled(self):
@@ -202,7 +202,25 @@ class DeepgramSTTService(STTService):
 
     async def _connect(self):
         logger.debug("Connecting to Deepgram")
-        if not await self._connection.start(self._settings):
+
+        self._connection: AsyncListenWebSocketClient = self._client.listen.asyncwebsocket.v("1")
+
+        self._connection.on(
+            LiveTranscriptionEvents(LiveTranscriptionEvents.Transcript), self._on_message
+        )
+        self._connection.on(LiveTranscriptionEvents(LiveTranscriptionEvents.Error), self._on_error)
+
+        if self.vad_enabled:
+            self._connection.on(
+                LiveTranscriptionEvents(LiveTranscriptionEvents.SpeechStarted),
+                self._on_speech_started,
+            )
+            self._connection.on(
+                LiveTranscriptionEvents(LiveTranscriptionEvents.UtteranceEnd),
+                self._on_utterance_end,
+            )
+
+        if not await self._connection.start(options=self._settings, addons=self._addons):
             logger.error(f"{self}: unable to connect to Deepgram")
 
     async def _disconnect(self):
@@ -214,6 +232,15 @@ class DeepgramSTTService(STTService):
         await self.start_ttfb_metrics()
         await self.start_processing_metrics()
 
+    async def _on_error(self, *args, **kwargs):
+        error: ErrorResponse = kwargs["error"]
+        logger.warning(f"{self} connection error, will retry: {error}")
+        await self.stop_all_metrics()
+        # NOTE(aleix): we don't disconnect (i.e. call finish on the connection)
+        # because this triggers more errors internally in the Deepgram SDK. So,
+        # we just forget about the previous connection and create a new one.
+        await self._connect()
+
     async def _on_speech_started(self, *args, **kwargs):
         await self.start_metrics()
         await self._call_event_handler("on_speech_started", *args, **kwargs)

src/pipecat/services/elevenlabs.py

@@ -192,6 +192,7 @@ class ElevenLabsTTSService(WordTTSService, WebsocketService):
             push_text_frames=False,
             push_stop_frames=True,
             stop_frame_timeout_s=2.0,
+            pause_frame_processing=True,
             sample_rate=sample_rate,
             **kwargs,
         )
@@ -289,19 +290,6 @@ class ElevenLabsTTSService(WordTTSService, WebsocketService):
             if isinstance(frame, TTSStoppedFrame):
                 await self.add_word_timestamps([("LLMFullResponseEndFrame", 0), ("Reset", 0)])
 
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        # If we received a TTSSpeakFrame and the LLM response included text (it
-        # might be that it's only a function calling response) we pause
-        # processing more frames until we receive a BotStoppedSpeakingFrame.
-        if isinstance(frame, TTSSpeakFrame):
-            await self.pause_processing_frames()
-        elif isinstance(frame, LLMFullResponseEndFrame) and self._started:
-            await self.pause_processing_frames()
-        elif isinstance(frame, BotStoppedSpeakingFrame):
-            await self.resume_processing_frames()
-
     async def _connect(self):
         await self._connect_websocket()
 
@@ -370,8 +358,13 @@ class ElevenLabsTTSService(WordTTSService, WebsocketService):
         except Exception as e:
             logger.error(f"{self} error closing websocket: {e}")
 
+    def _get_websocket(self):
+        if self._websocket:
+            return self._websocket
+        raise Exception("Websocket not connected")
+
     async def _receive_messages(self):
-        async for message in self._websocket:
+        async for message in self._get_websocket():
             msg = json.loads(message)
             if msg.get("audio"):
                 await self.stop_ttfb_metrics()
@@ -388,7 +381,11 @@ class ElevenLabsTTSService(WordTTSService, WebsocketService):
     async def _keepalive_task_handler(self):
         while True:
             await asyncio.sleep(10)
-            await self._send_text("")
+            try:
+                await self._send_text("")
+            except websockets.ConnectionClosed as e:
+                logger.warning(f"{self} keepalive error: {e}")
+                break
 
     async def _send_text(self, text: str):
         if self._websocket:

src/pipecat/services/fal.py

@@ -4,6 +4,7 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
+import asyncio
 import io
 import os
 from typing import AsyncGenerator, Dict, Optional, Union
@@ -53,6 +54,11 @@ class FalImageGenService(ImageGenService):
             os.environ["FAL_KEY"] = key
 
     async def run_image_gen(self, prompt: str) -> AsyncGenerator[Frame, None]:
+        def load_image_bytes(encoded_image: bytes):
+            buffer = io.BytesIO(encoded_image)
+            image = Image.open(buffer)
+            return (image.tobytes(), image.size, image.format)
+
         logger.debug(f"Generating image from prompt: {prompt}")
 
         response = await fal_client.run_async(
@@ -73,10 +79,8 @@ class FalImageGenService(ImageGenService):
         logger.debug(f"Downloading image {image_url} ...")
         async with self._aiohttp_session.get(image_url) as response:
             logger.debug(f"Downloaded image {image_url}")
-            image_stream = io.BytesIO(await response.content.read())
-            image = Image.open(image_stream)
+            encoded_image = await response.content.read()
+            (image_bytes, size, format) = await asyncio.to_thread(load_image_bytes, encoded_image)
 
-            frame = URLImageRawFrame(
-                url=image_url, image=image.tobytes(), size=image.size, format=image.format
-            )
+            frame = URLImageRawFrame(url=image_url, image=image_bytes, size=size, format=format)
             yield frame

src/pipecat/services/fish.py

@@ -60,7 +60,7 @@ class FishAudioTTSService(TTSService, WebsocketService):
         params: InputParams = InputParams(),
         **kwargs,
     ):
-        super().__init__(sample_rate=sample_rate, **kwargs)
+        super().__init__(pause_frame_processing=True, sample_rate=sample_rate, **kwargs)
 
         self._api_key = api_key
         self._base_url = "wss://api.fish.audio/v1/tts/live"
@@ -166,16 +166,6 @@ class FishAudioTTSService(TTSService, WebsocketService):
             except Exception as e:
                 logger.error(f"Error processing message: {e}")
 
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        await super().process_frame(frame, direction)
-
-        if isinstance(frame, TTSSpeakFrame):
-            await self.pause_processing_frames()
-        elif isinstance(frame, LLMFullResponseEndFrame) and self._request_id:
-            await self.pause_processing_frames()
-        elif isinstance(frame, BotStoppedSpeakingFrame):
-            await self.resume_processing_frames()
-
     async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
         await super()._handle_interruption(frame, direction)
         await self.stop_all_metrics()