sketch for runner as a module

Foundational requirements.txt: add silero, websocket optional dep, re…

.github/workflows/format.yaml

@@ -17,7 +17,7 @@ concurrency:
 
 jobs:
   ruff-format:
-    name: "Formatting checker"
+    name: "Code quality checks"
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repo
@@ -39,8 +39,8 @@ jobs:
         run: |
           source .venv/bin/activate
           ruff format --diff
-      - name: Ruff import linter
+      - name: Ruff linter (all rules)
         id: ruff-check
         run: |
           source .venv/bin/activate
-          ruff check --select I
+          ruff check

.github/workflows/publish.yaml

@@ -5,7 +5,7 @@ on:
     inputs:
       gitref:
         type: string
-        description: "what git ref to build"
+        description: "what git tag to build (e.g. v0.0.74)"
         required: true
 
 jobs:

.pre-commit-config.yaml

@@ -4,5 +4,5 @@ repos:
     hooks:
       - id: ruff
         language_version: python3
-        args: [ --select,  I, ]
+        args: [--fix]
       - id: ruff-format

CHANGELOG.md

@@ -5,6 +5,296 @@ 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 a new field `handle_sigterm` to `PipelineRunner`. It defaults to `False`.
+  This field handles SIGTERM signals. The `handle_sigint` field still defaults
+  to `True`, but now it handles only SIGINT signals.
+
+- Added foundational example `14u-function-calling-ollama.py` for Ollama
+  function calling.
+
+- Added `LocalSmartTurnAnalyzerV2`, which supports local on-device inference
+  with the new `smart-turn-v2` turn detection model.
+
+- Added `set_log_level` to `DailyTransport`, allowing setting the logging level
+  for Daily's internal logging system.
+
+### Changed
+
+- Play delayed messages from `ElevenLabsTTSService` if they still belong to the
+  current context.
+
+- Dependency compatibility improvements: Relaxed version constraints for core
+  dependencies to support broader version ranges while maintaining stability:
+
+  - `aiohttp`, `Markdown`, `nltk`, `numpy`, `Pillow`, `pydantic`, `openai`,
+    `numba`: Now support up to the next major version (e.g. `numpy>=1.26.4,<3`)
+  - `pyht`: Relaxed to `>=0.1.6` to resolve `grpcio` conflicts with
+    `nvidia-riva-client`
+  - `fastapi`: Updated to support versions `>=0.115.6,<0.117.0`
+  - `torch`/`torchaudio`: Changed from exact pinning (`==2.5.0`) to compatible
+    range (`~=2.5.0`)
+  - `aws_sdk_bedrock_runtime`: Added Python 3.12+ constraint via environment
+    marker
+  - `numba`: Reduced minimum version to `0.60.0` for better compatibility
+
+- Changed `NeuphonicHttpTTSService` to use a POST based request instead of the
+  `pyneuphonic` package. This removes a package requirement, allowing Neuphonic
+  to work with more services.
+
+- Updated the `deepgram` optional dependency to 4.7.0, which downgrades the
+  `tasks cancelled error` to a debug log. This removes the log from appearing
+  in Pipecat logs upon leaving.
+
+- Upgraded the `websockets` implementation to the new asyncio implementation.
+  Along with this change, we're updating support for versions >=13.1.0 and
+  <15.0.0. All services have been update to use the asyncio implementation.
+
+- Updated `MiniMaxHttpTTSService` with a `base_url` arg where you can specify
+  the Global endpoint (default) or Mainland China.
+
+- Replaced regex-based sentence detection in `match_endofsentence` with NLTK's
+  punkt_tab tokenizer for more reliable sentence boundary detection.
+
+- Changed the `livekit` optional dependency for `tenacity` to
+  `tenacity>=8.2.3,<10.0.0` in order to support the `google-genai` package.
+
+- For `LmntTTSService`, changed the default `model` to `blizzard`, LMNT's
+  recommended model.
+
+### Fixed
+
+- Fixed a dependency issue for uv users where an `llvmlite` version required python 3.9.
+
+- Fixed an issue in `MiniMaxHttpTTSService` where the `pitch` param was the
+  incorrect type.
+
+- Fixed an issue with OpenTelemetry tracing where the `enable_tracing` flag did
+  not disable the internal tracing decorator functions.
+
+- Fixed an issue in `OLLamaLLMService` where kwargs were not passed correctly
+  to the parent class.
+
+- Fixed an issue in `ElevenLabsTTSService` where the word/timestamp pairs were
+  calculating word boundaries incorrectly.
+
+- Fixed an issue where, in some edge cases, the `EmulateUserStartedSpeakingFrame`
+  could be created even if we didn't have a transcription.
+
+- Fixed an issue in `GoogleLLMContext` where it would inject the
+  `system_message` as a "user" message into cases where it was not meant to;
+  it was only meant to do that when there were no "regular" (non-function-call)
+  messages in the context, to ensure that inference would run properly.
+
+- Fixed an issue in `LiveKitTransport` where the `on_audio_track_subscribed` was never emitted.
+
+## [0.0.76] - 2025-07-11
+
+### Added
+
+- Added `SpeechControlParamsFrame`, a new `SystemFrame` that notifies
+  downstream processors of the VAD and Turn analyzer params. This frame is
+  pushed by the `BaseInputTransport` at Start and any time a
+  `VADParamsUpdateFrame` is received.
+
+### Changed
+
+- Two package dependencies have been updated:
+  - `numpy` now supports 1.26.0 and newer
+  - `transformers` now supports 4.48.0 and newer
+
+### Fixed
+
+- Fixed an issue with RTVI's handling of `append-to-context`.
+
+- Fixed an issue where using audio input with a sample rate requiring resampling
+  could result in empty audio being passed to STT services, causing errors.
+
+- Fixed the VAD analyzer to process the full audio buffer as long as it contains
+  more than the minimum required bytes per iteration, instead of only analyzing
+  the first chunk.
+
+- Fixed an issue in ParallelPipeline that caused errors when attempting to drain
+  the queues.
+
+- Fixed an issue with emulated VAD timeout inconsistency in
+  `LLMUserContextAggregator`. Previously, emulated VAD scenarios (where
+  transcription is received without VAD detection) used a hardcoded
+  `aggregation_timeout` (default 0.5s) instead of matching the VAD's
+  `stop_secs` parameter (default 0.8s). This created different user experiences
+  between real VAD and emulated VAD scenarios. Now, emulated VAD timeouts
+  automatically synchronize with the VAD's `stop_secs` parameter.
+
+- Fix a pipeline freeze when using AWS Nova Sonic, which would occur if the
+  user started early, while the bot was still working through
+  `trigger_assistant_response()`.
+
+## [0.0.75] - 2025-07-08
+
+### Added
+
+- Added an `aggregate_sentences` arg in `CartesiaTTSService`,
+  `ElevenLabsTTSService`, `NeuphonicTTSService` and `RimeTTSService`, where the
+  default value is True. When `aggregate_sentences` is True, the `TTSService`
+  aggregates the LLM streamed tokens into sentences by default. Note: setting
+  the value to False requires a custom processor before the `TTSService` to
+  aggregate LLM tokens.
+
+- Added `kwargs` to the `OLLamaLLMService` to allow for configuration args to
+  be passed to Ollama.
+
+- Added call hang-up error handling in `TwilioFrameSerializer`, which handles
+  the case where the user has hung up before the `TwilioFrameSerializer` hangs
+  up the call.
+
+### Changed
+
+- Updated `RTVIObserver` and `RTVIProcessor` to match the new RTVI 1.0.0 protocol.
+  This includes:
+
+  - Deprecating support for all messages related to service configuaration and
+    actions.
+  - Adding support for obtaining and logging data about client, including its
+    RTVI version and optionally included system information (OS/browser/etc.)
+  - Adding support for handling the new `client-message` RTVI message through
+    either a `on_client_message` event handler or listening for a new
+    `RTVIClientMessageFrame`
+  - Adding support for responding to a `client-message` with a `server-response`
+    via either a direct call on the `RTVIProcessor` or via pushing a new
+    `RTVIServerResponseFrame`
+  - Adding built-in support for handling the new `append-to-context` RTVI message
+    which allows a client to add to the user or assistant llm context. No extra
+    code is required for supporting this behavior.
+  - Updating all JavaScript and React client RTVI examples to use versions 1.0.0
+    of the clients.
+
+  Get started migrating to RTVI protocol 1.0.0 by following the migration guide:
+  https://docs.pipecat.ai/client/migration-guide
+
+- Refactored `AWSBedrockLLMService` and `AWSPollyTTSService` to work
+  asynchronously using `aioboto3` instead of the `boto3` library.
+
+- The `UserIdleProcessor` now handles the scenario where function calls take
+  longer than the idle timeout duration. This allows you to use the
+  `UserIdleProcessor` in conjunction with function calls that take a while to
+  return a result.
+
+### Fixed
+
+- Updated the `NeuphonicTTSService` to work with the updated websocket API.
+
+- Fixed an issue with `RivaSTTService` where the watchdog feature was causing
+  an error on initialization.
+
+### Performance
+
+- Remove unncessary push task in each `FrameProcessor`.
+
+## [0.0.74] - 2025-07-03
+
+### Added
+
+- Added a new STT service, `SpeechmaticsSTTService`. This service provides
+  real-time speech-to-text transcription using the Speechmatics API. It supports
+  partial and final transcriptions, multiple languages, various audio formats,
+  and speaker diarization.
+
+- Added `normalize` and `model_id` to `FishAudioTTSService`.
+
+- Added `http_options` argument to `GoogleLLMService`.
+
+- Added `run_llm` field to `LLMMessagesAppendFrame` and `LLMMessagesUpdateFrame`
+  frames. If true, a context frame will be pushed triggering the LLM to respond.
+
+- Added a new `SOXRStreamAudioResampler` for processing audio in chunks or
+  streams. If you write your own processor and need to use an audio resampler,
+  use the new `create_stream_resampler()`.
+
+- Added new `DailyParams.audio_in_user_tracks` to allow receiving one track per
+  user (default) or a single track from the room (all participants mixed).
+
+- Added support for providing "direct" functions, which don't need an
+  accompanying `FunctionSchema` or function definition dict. Instead, metadata
+  (i.e. `name`, `description`, `properties`, and `required`) are automatically
+  extracted from a combination of the function signature and docstring.
+
+  Usage:
+
+  ```python
+  # "Direct" function
+  # `params` must be the first parameter
+  async def do_something(params: FunctionCallParams, foo: int, bar: str = ""):
+    """
+    Do something interesting.
+
+    Args:
+      foo (int): The foo to do something interesting with.
+      bar (string): The bar to do something interesting with.
+    """
+
+    result = await process(foo, bar)
+    await params.result_callback({"result": result})
+
+  # ...
+
+  llm.register_direct_function(do_something)
+
+  # ...
+
+  tools = ToolsSchema(standard_tools=[do_something])
+  ```
+
+- `user_id` is now populated in the `TranscriptionFrame` and
+  `InterimTranscriptionFrame` when using a transport that provides a `user_id`,
+  like `DailyTransport` or `LiveKitTransport`.
+
+- Added `watchdog_coroutine()`. This is a watchdog helper for couroutines. So,
+  if you have a coroutine that is waiting for a result and that takes a long
+  time, you will need to wrap it with `watchdog_coroutine()` so the watchdog
+  timers are reset regularly.
+
+- Added `session_token` parameter to `AWSNovaSonicLLMService`.
+
+- Added Gemini Multimodal Live File API for uploading, fetching, listing, and
+  deleting files. See `26f-gemini-multimodal-live-files-api.py` for example usage.
+
+### Changed
+
+- Updated all the services to use the new `SOXRStreamAudioResampler`, ensuring smooth
+  transitions and eliminating clicks.
+
+- Upgraded `daily-python` to 0.19.4.
+
+- Updated `google` optional dependency to use `google-genai` version `1.24.0`.
+
+### Fixed
+
+- Fixed an issue where audio would get stuck in the queue when an interrupt occurs
+  during Azure TTS synthesis.
+
+- Fixed a race condition that occurs in Python 3.10+ where the task could miss
+  the `CancelledError` and continue running indefinitely, freezing the pipeline.
+
+- Fixed a `AWSNovaSonicLLMService` issue introduced in 0.0.72.
+
+### Deprecated
+
+- In `FishAudioTTSService`, deprecated `model` and replaced with
+  `reference_id`. This change is to better align with Fish Audio's variable
+  naming and to reduce confusion about what functionality the variable
+  controls.
+
+## [0.0.73] - 2025-06-26
+
+### Fixed
+
+- Fixed an issue introduced in 0.0.72 that would cause `ElevenLabsTTSService`,
+  `GladiaSTTService`, `NeuphonicTTSService` and `OpenAIRealtimeBetaLLMService`
+  to throw an error.
+
 ## [0.0.72] - 2025-06-26
 
 ### Added

CONTRIBUTING.md

@@ -43,8 +43,8 @@ We follow Google-style docstrings with these specific conventions:
 
 **Regular Classes:**
 
-- Class docstring describes the class purpose and documents all `__init__` parameters in an `Args:` section
-- No separate `__init__` docstring needed
+- Class docstring describes the class purpose and key functionality
+- `__init__` method has its own docstring with complete `Args:` section documenting all parameters
 - All public methods must have docstrings with `Args:` and `Returns:` sections as appropriate
 
 **Dataclasses:**
@@ -60,6 +60,39 @@ We follow Google-style docstrings with these specific conventions:
 
 - Must have docstrings explaining what subclasses should implement
 
+**`__init__.py` Files:**
+
+- **Skip docstrings** for pure import/re-export modules
+- **Add brief docstrings** for top-level packages or those with initialization logic
+
+**Enums:**
+
+- Class docstring describes the enumeration purpose
+- Use `Parameters:` section to document each enum value and its meaning
+- No `__init__` docstring (Enums don't have custom constructors)
+
+**Code Examples in Docstrings:**
+
+- Use `Examples:` as a section header for multiple examples
+- Use descriptive text followed by double colons (`::`) for each example
+- **Always include a blank line after the `::"`**
+- Indent all code consistently within each block
+- Separate multiple examples with blank lines for readability
+
+**Lists and Bullets in Docstrings:**
+
+- Use dashes (`-`) for bullet points, not asterisks (`*`)
+- **Add a blank line before bullet lists** when they follow a colon
+- Use section headers like "Supported features:" or "Behavior:" before lists
+- For complex nested information, consider using paragraph format instead
+
+**Deprecations:**
+
+- Use `warnings.warn()` in code for runtime deprecation warnings
+- Add `.. deprecated::` directive in docstrings for documentation visibility
+- Include version information and describe current status
+- Describe parameters in present tense, use directive to indicate deprecation status
+
 #### Examples:
 
 ```python
@@ -67,14 +100,34 @@ We follow Google-style docstrings with these specific conventions:
 class MyService(BaseService):
     """Description of what the service does.
 
-    Args:
-        param1: Description of param1.
-        param2: Description of param2. Defaults to True.
-        **kwargs: Additional arguments passed to parent.
+    Provides detailed explanation of the service's functionality,
+    key features, and usage patterns.
+
+    Supported features:
+
+    - Feature one with detailed explanation
+    - Feature two with additional context
+    - Feature three for advanced use cases
     """
 
-    def __init__(self, param1: str, param2: bool = True, **kwargs):
-        # No docstring - parameters documented above
+    def __init__(self, param1: str, old_param: str = None, **kwargs):
+        """Initialize the service.
+
+        Args:
+            param1: Description of param1.
+            old_param: Controls legacy behavior.
+
+                .. deprecated:: 1.2.0
+                    This parameter no longer has any effect and will be removed in version 2.0.
+
+            **kwargs: Additional arguments passed to parent.
+        """
+        if old_param is not None:
+            import warnings
+            warnings.warn(
+                "Parameter 'old_param' is deprecated and will be removed in version 2.0.",
+                DeprecationWarning,
+            )
         super().__init__(**kwargs)
 
     @property
@@ -97,20 +150,41 @@ class MyService(BaseService):
         """
         pass
 
-# Dataclass
+# Dataclass with code examples
 @dataclass
-class ConfigParams:
-    """Configuration parameters for the service.
+class MessageFrame:
+    """Frame containing messages in OpenAI format.
+
+    Supports both simple and content list message formats.
+
+    Example::
+
+        [
+            {"role": "user", "content": "Hello"},
+            {"role": "assistant", "content": "Hi there!"}
+        ]
 
     Parameters:
-        host: The host address.
-        port: The port number. Defaults to 8080.
-        timeout: Connection timeout in seconds.
+        messages: List of messages in OpenAI format.
     """
 
-    host: str
-    port: int = 8080
-    timeout: float = 30.0
+    messages: List[dict]
+
+# Enum class
+class Status(Enum):
+    """Status codes for processing operations.
+
+    Parameters:
+        PENDING: Operation is queued but not started.
+        RUNNING: Operation is currently in progress.
+        COMPLETED: Operation finished successfully.
+        FAILED: Operation encountered an error.
+    """
+
+    PENDING = "pending"
+    RUNNING = "running"
+    COMPLETED = "completed"
+    FAILED = "failed"
 ```
 
 # Contributor Covenant Code of Conduct

README.md

@@ -51,19 +51,19 @@ You can connect to Pipecat from any platform using our official SDKs:
 
 ## 🧩 Available services
 
-| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
-| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Parakeet (NVIDIA)](https://docs.pipecat.ai/server/services/stt/parakeet), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova) [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                          |
-| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                 |
-| Text-to-Speech      | [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), [FastPitch (NVIDIA)](https://docs.pipecat.ai/server/services/tts/fastpitch), [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), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
-| Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
-| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Serializers         | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
-| Video               | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
-| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
-| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Parakeet (NVIDIA)](https://docs.pipecat.ai/server/services/stt/parakeet), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                       |
+| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
+| Text-to-Speech      | [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), [FastPitch (NVIDIA)](https://docs.pipecat.ai/server/services/tts/fastpitch), [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), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                    |
+| Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+| Serializers         | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+| Video               | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 

dev-requirements.txt

@@ -1,13 +1,20 @@
 build~=1.2.2
-coverage~=7.6.12
+coverage~=7.9.1
 grpcio-tools~=1.67.1
 pip-tools~=7.4.1
-pre-commit~=4.0.1
-pyright~=1.1.400
-pytest~=8.3.4
-pytest-asyncio~=0.25.3
+pre-commit~=4.2.0
+pyright~=1.1.402
+pytest~=8.4.1
+pytest-asyncio~=1.0.0
 pytest-aiohttp==1.1.0
-ruff~=0.11.13
-setuptools~=70.0.0
-setuptools_scm~=8.1.0
-python-dotenv~=1.0.1
+ruff~=0.12.1
+setuptools~=78.1.1
+setuptools_scm~=8.3.1
+python-dotenv~=1.1.1
+
+# For running examples
+uvicorn
+python-dotenv
+fastapi
+aiohttp
+aiortc

docs/api/conf.py

@@ -26,18 +26,20 @@ extensions = [
     "sphinx.ext.intersphinx",
 ]
 
+suppress_warnings = [
+    "autodoc.mocked_object",
+]
+
 # Napoleon settings
 napoleon_google_docstring = True
-napoleon_numpy_docstring = False
-napoleon_include_init_with_doc = False
+napoleon_include_init_with_doc = True
 
 # AutoDoc settings
 autodoc_default_options = {
     "members": True,
     "member-order": "bysource",
-    "undoc-members": True,
-    "exclude-members": "__weakref__,__init__",
-    "no-index": True,
+    "undoc-members": False,
+    "exclude-members": "__weakref__,model_config",
     "show-inheritance": True,
 }
 
@@ -72,20 +74,16 @@ autodoc_mock_imports = [
     "langchain",
     "lmnt",
     "noisereduce",
-    "openai",
     "openpipe",
     "simli",
     "soundfile",
+    "soniox",
     "pipecat_ai_krisp",
     "pyaudio",
     "_tkinter",
     "tkinter",
     "daily",
     "daily_python",
-    "pydantic.BaseModel",
-    "pydantic.Field",
-    "pydantic._internal._model_construction",
-    "pydantic._internal._fields",
     # Moondream dependencies
     "torch",
     "transformers",
@@ -168,85 +166,54 @@ autodoc_mock_imports = [
     "mcp.client.stdio",
     "mcp.ClientSession",
     "mcp.StdioServerParameters",
+    # gstreamer
+    "gi",
+    "gi.require_version",
+    "gi.repository",
+    # Protobuf mocks
+    "pipecat.frames.protobufs.frames_pb2",
+    "pipecat.serializers.protobuf",
+    "google.protobuf",
+    "google.protobuf.descriptor",
+    "google.protobuf.descriptor_pool",
+    "google.protobuf.runtime_version",
+    "google.protobuf.symbol_database",
+    "google.protobuf.internal.builder",
 ]
 
 # HTML output settings
 html_theme = "sphinx_rtd_theme"
 html_static_path = ["_static"]
-autodoc_typehints = "description"
+autodoc_typehints = "signature"  # Show type hints in the signature only, not in the docstring
 html_show_sphinx = False
 
 
-def verify_modules():
-    """Verify that required modules are available."""
-    required_modules = {
-        "services": [
-            "assemblyai",
-            "aws",
-            "cartesia",
-            "deepgram",
-            "google",
-            "lmnt",
-            "riva",
-            "simli",
-        ],
-        "serializers": ["livekit"],
-        "vad": ["silero", "vad_analyzer"],
-        "transports": {
-            "services": ["daily", "livekit"],
-            "local": ["audio", "tk"],
-            "network": ["fastapi_websocket", "websocket_server"],
-        },
-    }
+def import_core_modules():
+    """Import core pipecat modules for autodoc to discover."""
+    core_modules = [
+        "pipecat",
+        "pipecat.frames",
+        "pipecat.pipeline",
+        "pipecat.processors",
+        "pipecat.services",
+        "pipecat.transports",
+        "pipecat.audio",
+        "pipecat.adapters",
+        "pipecat.clocks",
+        "pipecat.metrics",
+        "pipecat.observers",
+        "pipecat.serializers",
+        "pipecat.sync",
+        "pipecat.transcriptions",
+        "pipecat.utils",
+    ]
 
-    # Skip importing modules that are in autodoc_mock_imports
-    skipped_modules = set(autodoc_mock_imports)
-
-    missing = []
-    for category, modules in required_modules.items():
-        if isinstance(modules, dict):
-            # Handle nested structure
-            for subcategory, submodules in modules.items():
-                for module in submodules:
-                    # Check if module is in autodoc_mock_imports
-                    if (
-                        f"pipecat.{category}.{subcategory}.{module}" in skipped_modules
-                        or module in skipped_modules
-                    ):
-                        logger.info(
-                            f"Skipping import of mocked module: pipecat.{category}.{subcategory}.{module}"
-                        )
-                        continue
-
-                    try:
-                        __import__(f"pipecat.{category}.{subcategory}.{module}")
-                        logger.info(
-                            f"Successfully imported pipecat.{category}.{subcategory}.{module}"
-                        )
-                    except (ImportError, TypeError, NameError) as e:
-                        missing.append(f"pipecat.{category}.{subcategory}.{module}")
-                        logger.warning(
-                            f"Optional module not available: pipecat.{category}.{subcategory}.{module} - {str(e)}"
-                        )
-        else:
-            # Handle flat structure
-            for module in modules:
-                # Check if module is in autodoc_mock_imports
-                if f"pipecat.{category}.{module}" in skipped_modules or module in skipped_modules:
-                    logger.info(f"Skipping import of mocked module: pipecat.{category}.{module}")
-                    continue
-
-                try:
-                    __import__(f"pipecat.{category}.{module}")
-                    logger.info(f"Successfully imported pipecat.{category}.{module}")
-                except (ImportError, TypeError, NameError) as e:
-                    missing.append(f"pipecat.{category}.{module}")
-                    logger.warning(
-                        f"Optional module not available: pipecat.{category}.{module} - {str(e)}"
-                    )
-
-    if missing:
-        logger.warning(f"Some optional modules are not available: {missing}")
+    for module_name in core_modules:
+        try:
+            __import__(module_name)
+            logger.info(f"Successfully imported {module_name}")
+        except ImportError as e:
+            logger.warning(f"Failed to import {module_name}: {e}")
 
 
 def clean_title(title: str) -> str:
@@ -258,39 +225,7 @@ def clean_title(title: str) -> str:
     parts = title.split(".")
     title = parts[-1]
 
-    # Special cases for service names and common acronyms
-    special_cases = {
-        "ai": "AI",
-        "aws": "AWS",
-        "api": "API",
-        "vad": "VAD",
-        "assemblyai": "AssemblyAI",
-        "deepgram": "Deepgram",
-        "elevenlabs": "ElevenLabs",
-        "openai": "OpenAI",
-        "openpipe": "OpenPipe",
-        "playht": "PlayHT",
-        "xtts": "XTTS",
-        "lmnt": "LMNT",
-        "stt": "STT",
-        "tts": "TTS",
-        "llm": "LLM",
-    }
-
-    # Check if the entire title is a special case
-    if title.lower() in special_cases:
-        return special_cases[title.lower()]
-
-    # Otherwise, capitalize each word
-    words = title.split("_")
-    cleaned_words = []
-    for word in words:
-        if word.lower() in special_cases:
-            cleaned_words.append(special_cases[word.lower()])
-        else:
-            cleaned_words.append(word.capitalize())
-
-    return " ".join(cleaned_words)
+    return title
 
 
 def setup(app):
@@ -315,9 +250,8 @@ def setup(app):
 
     excludes = [
         str(project_root / "src/pipecat/pipeline/to_be_updated"),
-        str(project_root / "src/pipecat/processors/gstreamer"),
-        str(project_root / "src/pipecat/services/to_be_updated"),
-        str(project_root / "src/pipecat/vad"),  # deprecated
+        str(project_root / "src/pipecat/examples"),
+        str(project_root / "src/pipecat/tests"),
         "**/test_*.py",
         "**/tests/*.py",
     ]
@@ -358,5 +292,4 @@ def setup(app):
         logger.error(f"Error generating API documentation: {e}", exc_info=True)
 
 
-# Run module verification
-verify_modules()
+import_core_modules()

docs/api/index.rst

@@ -1,57 +1,17 @@
-Pipecat API Reference Docs
-==========================
+Pipecat API Reference
+=====================
 
-Welcome to Pipecat's API reference documentation!
+Welcome to the Pipecat API reference.
 
-Pipecat is an open source framework for building voice and multimodal assistants.
-It provides a flexible pipeline architecture for connecting various AI services,
-audio processing, and transport layers.
+Use the navigation on the left to browse modules, or search using the search box.
+
+**New to Pipecat?** Check out the `main documentation <https://docs.pipecat.ai>`_ for tutorials, guides, and client SDK information.
 
 Quick Links
 -----------
 
 * `GitHub Repository <https://github.com/pipecat-ai/pipecat>`_
-* `Website <https://pipecat.ai>`_
-
-API Reference
--------------
-
-Core Components
-~~~~~~~~~~~~~~~
-
-* :mod:`Frames <pipecat.frames>`
-* :mod:`Processors <pipecat.processors>`
-* :mod:`Pipeline <pipecat.pipeline>`
-
-Audio Processing
-~~~~~~~~~~~~~~~~
-
-* :mod:`Audio <pipecat.audio>`
-
-Services
-~~~~~~~~
-
-* :mod:`Services <pipecat.services>`
-
-Transport & Serialization
-~~~~~~~~~~~~~~~~~~~~~~~~~
-
-* :mod:`Transports <pipecat.transports>`
-   * :mod:`Local <pipecat.transports.local>`
-   * :mod:`Network <pipecat.transports.network>`
-   * :mod:`Services <pipecat.transports.services>`
-* :mod:`Serializers <pipecat.serializers>`
-
-Utilities
-~~~~~~~~~
-
-* :mod:`Adapters <pipecat.adapters>`
-* :mod:`Clocks <pipecat.clocks>`
-* :mod:`Metrics <pipecat.metrics>`
-* :mod:`Observers <pipecat.observers>`
-* :mod:`Sync <pipecat.sync>`
-* :mod:`Transcriptions <pipecat.transcriptions>`
-* :mod:`Utils <pipecat.utils>`
+* `Join our Community <https://discord.gg/pipecat>`_
 
 .. toctree::
    :maxdepth: 3
@@ -71,11 +31,4 @@ Utilities
    Sync <api/pipecat.sync>
    Transcriptions <api/pipecat.transcriptions>
    Transports <api/pipecat.transports>
-   Utils <api/pipecat.utils>
-
-Indices and tables
-==================
-
-* :ref:`genindex`
-* :ref:`modindex`
-* :ref:`search`
+   Utils <api/pipecat.utils>

docs/api/requirements.txt

@@ -46,6 +46,8 @@ pipecat-ai[sambanova]
 pipecat-ai[silero]
 pipecat-ai[simli]
 pipecat-ai[soundfile]
+pipecat-ai[soniox]
+pipecat-ai[speechmatics]
 pipecat-ai[tavus]
 pipecat-ai[together]
 # pipecat-ai[ultravox] # Mocked

dot-env.template

@@ -109,6 +109,13 @@ MINIMAX_GROUP_ID=...
 # Sarvam AI
 SARVAM_API_KEY=...
 
+# Soniox
+SONIOX_API_KEY=
+
+# Speechmatics
+SPEECHMATICS_API_KEY=...
+
+
 # SambaNova
 SAMBANOVA_API_KEY=...
 

examples/aws-strands/README.md

@@ -0,0 +1,60 @@
+# AWS Strands Examples
+
+This folder contains two Python examples demonstrating how to use Pipecat with the AWS Strands agent.
+
+## Overview
+
+These examples show how to delegate complex, multi-step tasks to a Strands agent, which can reason step-by-step and call tools to accomplish user requests.
+
+These examples are intentionally simplified for demonstration, using mock API calls. They work best if you ask it:
+
+> What's the weather where the Golden Gate Bridge is?
+
+## Example Scripts
+
+### `black-box.py`
+
+A minimal example that demonstrates how to use the Strands agent with Pipecat. The agent can handle multi-step queries by calling tools, but does not explain its reasoning out loud.
+
+### `explain-thinking.py`
+
+An enhanced example where the Strands agent explains each step of its reasoning in clear, simple language as it works through a multi-step task.
+
+## Quick Start
+
+1. **Clone the repository and navigate to this example:**
+
+   ```bash
+   git clone https://github.com/pipecat-ai/pipecat.git
+   cd pipecat/examples/aws-strands
+   ```
+
+2. **Set up a virtual environment:**
+
+   ```bash
+   python -m venv venv
+   source venv/bin/activate  # On Windows: venv\Scripts\activate
+   ```
+
+3. **Install dependencies:**
+
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+4. **Configure environment variables:**
+
+   Copy the provided `env.example` file to `.env` and fill in the necessary credentials:
+
+   ```bash
+   cp env.example .env
+   # Then edit .env with your preferred editor
+   ```
+
+5. **Run an example:**
+
+   ```bash
+   python black-box.py
+   # or
+   python explain-thinking.py
+   ```

examples/aws-strands/black-box.py

@@ -0,0 +1,206 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import asyncio
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+from strands import Agent, tool
+from strands.models import BedrockModel
+
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+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.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+"""This example demonstrates how to use the Strands agent with Pipecat.
+
+You can delegate complex, multi-step tasks to the Strands agent, which can cycle through LLM-based reasoning and tool calls to accomplish the task.
+
+Try asking: "What's the weather where the Golden Gate Bridge is?"
+"""
+
+# Strands agent tools
+
+
+@tool
+def get_location_name_from_landmark(landmark: str) -> str:
+    """
+    Get the location name from a landmark.
+
+    Args:
+        landmark (str): The name of the landmark, e.g. "Golden Gate Bridge".
+    """
+    # Simulate fetching location
+    return "San Francisco, CA"
+
+
+@tool
+def get_lat_long_from_location_name(location: str) -> dict:
+    """
+    Get the latitude and longitude for a location name.
+
+    Args:
+        location (str): The city and state, e.g. "San Francisco, CA".
+    """
+    # Simulate fetching lat/long from a geocoding service
+    return {"lat": 37.7749, "long": -122.4194}
+
+
+@tool
+def get_current_weather_from_lat_long(lat: float, long: float) -> dict:
+    """
+    Get the current weather for a specific latitude and longitude.
+
+    Args:
+        lat (float): The latitude of the location.
+        long (float): The longitude of the location.
+    """
+    # Simulate fetching weather data from a weather service
+    return {"conditions": "nice", "temperature": "75"}
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    logger.info(f"Starting bot")
+
+    strands_agent = Agent(
+        model=BedrockModel(
+            model_id="us.anthropic.claude-3-7-sonnet-20250219-v1:0", max_tokens=64000
+        ),
+        tools=[
+            get_location_name_from_landmark,
+            get_lat_long_from_location_name,
+            get_current_weather_from_lat_long,
+        ],
+        system_prompt="""
+        You are a helpful personal assistant who can look up information about places and weather.
+
+        Your key capabilities:
+        1. Look up where landmarks are located.
+        2. Find latitude and longitude for a location.
+        3. Look up the current weather for a specific latitude and longitude.
+
+        Explain each step of your reasoning in clear, simple, and concise language. Your responses will be converted to audio, so avoid special characters and numbered lists.
+        """,
+    )
+
+    async def handle_location_or_weather_related_queries(params: FunctionCallParams, query: str):
+        """
+        Handle location or weather related queries.
+
+        Args:
+            query (str): The user's query, e.g. "What's the weather where the Golden Gate Bridge is?".
+        """
+        # Run in a background thread
+        # (Otherwise the agent blocks the event loop; one effect of that is that we don't hear
+        # "let me check on that" until the agent finishes)
+        loop = asyncio.get_running_loop()
+        result = await loop.run_in_executor(None, strands_agent, query)
+        await params.result_callback(result.message)
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    llm.register_direct_function(handle_location_or_weather_related_queries)
+
+    @llm.event_handler("on_function_calls_started")
+    async def on_function_calls_started(service, function_calls):
+        await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
+
+    tools = ToolsSchema(standard_tools=[handle_location_or_weather_related_queries])
+
+    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. Start by suggesting that the user ask about the weather where the Golden Gate Bridge is.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=handle_sigint)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    main(run_example, transport_params=transport_params)

examples/aws-strands/env.example

@@ -0,0 +1,8 @@
+OPENAI_API_KEY=
+CARTESIA_API_KEY=
+DEEPGRAM_API_KEY=
+DAILY_API_KEY=
+DAILY_SAMPLE_ROOM_URL=
+AWS_SECRET_ACCESS_KEY=
+AWS_ACCESS_KEY_ID=
+AWS_REGION=

examples/aws-strands/explain-thinking.py

@@ -0,0 +1,249 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import asyncio
+import os
+import threading
+import time
+
+from dotenv import load_dotenv
+from loguru import logger
+from strands import Agent, tool
+from strands.models import BedrockModel
+
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+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.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+"""This example demonstrates how to use the Strands agent with Pipecat in a way where the agent explains its reasoning step-by-step.
+
+You can delegate complex, multi-step tasks to the Strands agent, which can cycle through LLM-based reasoning and tool calls to accomplish the task.
+
+Try asking: "What's the weather where the Golden Gate Bridge is?"
+"""
+
+
+# Strands agent tools
+
+
+@tool
+def get_location_name_from_landmark(landmark: str) -> str:
+    """
+    Get the location name from a landmark.
+
+    Args:
+        landmark (str): The name of the landmark, e.g. "Golden Gate Bridge".
+    """
+    # Simulate fetching location (slowly)
+    time.sleep(3)
+    return "San Francisco, CA"
+
+
+@tool
+def get_lat_long_from_location_name(location: str) -> dict:
+    """
+    Get the latitude and longitude for a location name.
+
+    Args:
+        location (str): The city and state, e.g. "San Francisco, CA".
+    """
+    # Simulate fetching lat/long from a geocoding service (slowly)
+    time.sleep(3)
+    return {"lat": 37.7749, "long": -122.4194}
+
+
+@tool
+def get_current_weather_from_lat_long(lat: float, long: float) -> dict:
+    """
+    Get the current weather for a specific latitude and longitude.
+
+    Args:
+        lat (float): The latitude of the location.
+        long (float): The longitude of the location.
+    """
+    # Simulate fetching weather data from a weather service (slowly)
+    time.sleep(3)
+    return {"conditions": "nice", "temperature": "75"}
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    next_strands_message_is_last = False
+    strands_messages_queue = asyncio.Queue()
+
+    def strands_callback_handler(**kwargs):
+        """
+        Handle events from the Strands agent.
+        """
+        nonlocal next_strands_message_is_last
+        if "event" in kwargs:
+            event_obj = kwargs["event"]
+            if event_obj and "messageStop" in event_obj:
+                message_stop = event_obj["messageStop"]
+                if message_stop and "stopReason" in message_stop:
+                    stop_reason = message_stop["stopReason"]
+                    if stop_reason == "end_turn":
+                        next_strands_message_is_last = True
+        elif "message" in kwargs:
+            message_obj = kwargs["message"]
+            if message_obj and "content" in message_obj and "role" in message_obj:
+                role = message_obj["role"]
+                content = message_obj["content"]
+                if role == "assistant" and isinstance(content, list):
+                    for content_obj in content:
+                        if isinstance(content_obj, dict) and "text" in content_obj:
+                            message = content_obj["text"]
+                            if not next_strands_message_is_last:
+                                strands_messages_queue.put_nowait(message)
+
+    async def process_strands_messages():
+        while True:
+            message = await strands_messages_queue.get()
+            await tts.queue_frame(TTSSpeakFrame(message))
+            strands_messages_queue.task_done()
+
+    asyncio.create_task(process_strands_messages())
+
+    strands_agent = Agent(
+        model=BedrockModel(
+            model_id="us.anthropic.claude-3-7-sonnet-20250219-v1:0", max_tokens=64000
+        ),
+        tools=[
+            get_location_name_from_landmark,
+            get_lat_long_from_location_name,
+            get_current_weather_from_lat_long,
+        ],
+        system_prompt="""
+        You are a helpful personal assistant who can look up information about places and weather.
+
+        Your key capabilities:
+        1. Look up where landmarks are located.
+        2. Find latitude and longitude for a location.
+        3. Look up the current weather for a specific latitude and longitude.
+
+        Explain each step of your reasoning in clear, simple, and concise language. Your responses will be converted to audio, so avoid special characters and numbered lists.
+        """,
+        callback_handler=strands_callback_handler,
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    async def handle_location_or_weather_related_queries(params: FunctionCallParams, query: str):
+        """
+        Handle location or weather related queries.
+
+        Args:
+            query (str): The user's query, e.g. "What's the weather where the Golden Gate Bridge is?".
+        """
+        # Run in a background thread
+        # (Otherwise the agent blocks the event loop; one effect of that is that we don't hear
+        # the agent's "thinking" messages until the agent finishes)
+        loop = asyncio.get_running_loop()
+        result = await loop.run_in_executor(None, strands_agent, query)
+        await params.result_callback(result.message)
+
+    llm.register_direct_function(handle_location_or_weather_related_queries)
+
+    @llm.event_handler("on_function_calls_started")
+    async def on_function_calls_started(service, function_calls):
+        await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
+
+    tools = ToolsSchema(standard_tools=[handle_location_or_weather_related_queries])
+
+    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. Start by suggesting that the user ask about the weather where the Golden Gate Bridge is.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=handle_sigint)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    main(run_example, transport_params=transport_params)

examples/aws-strands/requirements.txt

@@ -2,4 +2,5 @@ fastapi
 uvicorn
 python-dotenv
 pipecat-ai[webrtc,daily,deepgram,cartesia]
-pipecat-ai-small-webrtc-prebuilt
+pipecat-ai-small-webrtc-prebuilt
+strands-agents

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

@@ -4364,9 +4364,9 @@
       }
     },
     "node_modules/brace-expansion": {
-      "version": "1.1.11",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
-      "integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
+      "version": "1.1.12",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
+      "integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
       "dependencies": {
         "balanced-match": "^1.0.0",
         "concat-map": "0.0.1"
@@ -6081,9 +6081,9 @@
       }
     },
     "node_modules/glob/node_modules/brace-expansion": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
-      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
+      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
       "dependencies": {
         "balanced-match": "^1.0.0"
       }

examples/daily-multi-translation/requirements.txt

@@ -2,4 +2,4 @@ aiofiles
 python-dotenv
 fastapi[all]
 uvicorn
-pipecat-ai[daily,deepgram,openai,silero,cartesia]
+pipecat-ai[daily,deepgram,openai,silero,cartesia,soundfile]

examples/deployment/modal-example/client/javascript/package.json

@@ -15,7 +15,7 @@
     "vite": "^6.3.5"
   },
   "dependencies": {
-    "@pipecat-ai/client-js": "^0.3.5",
-    "@pipecat-ai/daily-transport": "^0.3.10"
+    "@pipecat-ai/client-js": "^1.0.0",
+    "@pipecat-ai/daily-transport": "^1.0.0"
   }
 }

examples/deployment/modal-example/client/javascript/src/app.js

@@ -5,7 +5,7 @@
  */
 
 /**
- * RTVI Client Implementation
+ * Pipecat 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.
@@ -16,7 +16,7 @@
  * - Browser with WebRTC support
  */
 
-import { RTVIClient, RTVIEvent } from '@pipecat-ai/client-js';
+import { PipecatClient, RTVIEvent } from '@pipecat-ai/client-js';
 import { DailyTransport } from '@pipecat-ai/daily-transport';
 
 /**
@@ -26,7 +26,7 @@ import { DailyTransport } from '@pipecat-ai/daily-transport';
 class ChatbotClient {
   constructor() {
     // Initialize client state
-    this.rtviClient = null;
+    this.pcClient = null;
     this.setupDOMElements();
     this.initializeClientAndTransport();
     this.setupEventListeners();
@@ -59,7 +59,7 @@ class ChatbotClient {
     this.disconnectBtn.addEventListener('click', () => this.disconnect());
 
     // Populate device selector
-    this.rtviClient.getAllMics().then((mics) => {
+    this.pcClient.getAllMics().then((mics) => {
       console.log('Available mics:', mics);
       mics.forEach((device) => {
         const option = document.createElement('option');
@@ -71,16 +71,16 @@ class ChatbotClient {
     this.deviceSelector.addEventListener('change', (event) => {
       const selectedDeviceId = event.target.value;
       console.log('Selected device ID:', selectedDeviceId);
-      this.rtviClient.updateMic(selectedDeviceId);
+      this.pcClient.updateMic(selectedDeviceId);
     });
 
     // Handle mic mute/unmute toggle
     const micToggleBtn = document.getElementById('mic-toggle-btn');
 
     micToggleBtn.addEventListener('click', () => {
-      let micEnabled = this.rtviClient.isMicEnabled;
+      let micEnabled = this.pcClient.isMicEnabled;
       micToggleBtn.textContent = micEnabled ? 'Unmute Mic' : 'Mute Mic';
-      this.rtviClient.enableMic(!micEnabled);
+      this.pcClient.enableMic(!micEnabled);
       // Add logic to mute/unmute the mic
       if (micEnabled) {
         console.log('Mic muted');
@@ -93,23 +93,12 @@ class ChatbotClient {
   }
 
   /**
-   * Set up the RTVI client and Daily transport
+   * Set up the Pipecat client and Daily transport
    */
   async initializeClientAndTransport() {
-    // Initialize the RTVI client with a DailyTransport and our configuration
-    this.rtviClient = new RTVIClient({
+    // Initialize the Pipecat client with a DailyTransport and our configuration
+    this.pcClient = new PipecatClient({
       transport: new DailyTransport(),
-      params: {
-        // REPLACE WITH YOUR MODAL URL ENDPOINT
-        baseUrl:
-          'https://<Modal workspace>--pipecat-modal-bot-launcher.modal.run',
-        endpoints: {
-          connect: '/connect',
-        },
-        requestData: {
-          bot_name: 'openai',
-        },
-      },
       enableMic: true, // Enable microphone for user input
       enableCam: false,
       callbacks: {
@@ -176,8 +165,8 @@ class ChatbotClient {
     // Set up listeners for media track events
     this.setupTrackListeners();
 
-    await this.rtviClient.initDevices();
-    window.client = this.rtviClient;
+    await this.pcClient.initDevices();
+    window.client = this.pcClient;
   }
 
   /**
@@ -212,10 +201,10 @@ class ChatbotClient {
    * This is called when the bot is ready or when the transport state changes to ready
    */
   setupMediaTracks() {
-    if (!this.rtviClient) return;
+    if (!this.pcClient) return;
 
     // Get current tracks from the client
-    const tracks = this.rtviClient.tracks();
+    const tracks = this.pcClient.tracks();
 
     // Set up any available bot tracks
     if (tracks.bot?.audio) {
@@ -231,10 +220,10 @@ class ChatbotClient {
    * This handles new tracks being added during the session
    */
   setupTrackListeners() {
-    if (!this.rtviClient) return;
+    if (!this.pcClient) return;
 
     // Listen for new tracks starting
-    this.rtviClient.on(RTVIEvent.TrackStarted, (track, participant) => {
+    this.pcClient.on(RTVIEvent.TrackStarted, (track, participant) => {
       // Only handle non-local (bot) tracks
       if (!participant?.local) {
         if (track.kind === 'audio') {
@@ -253,7 +242,7 @@ class ChatbotClient {
     });
 
     // Listen for tracks stopping
-    this.rtviClient.on(RTVIEvent.TrackStopped, (track, participant) => {
+    this.pcClient.on(RTVIEvent.TrackStopped, (track, participant) => {
       if (participant.local) {
         this.log('Local mic muted');
         return;
@@ -311,21 +300,27 @@ class ChatbotClient {
 
   /**
    * Initialize and connect to the bot
-   * This sets up the RTVI client, initializes devices, and establishes the connection
+   * This sets up the Pipecat client, initializes devices, and establishes the connection
    */
   async connect() {
     try {
       const botSelector = document.getElementById('bot-selector');
       const selectedBot = botSelector.value;
-      this.rtviClient.params.requestData.bot_name = selectedBot;
 
       // Initialize audio/video devices
       this.log('Initializing devices...');
-      await this.rtviClient.initDevices();
+      await this.pcClient.initDevices();
 
       // Connect to the bot
       this.log(`Connecting to bot: ${selectedBot}`);
-      await this.rtviClient.connect();
+      await this.pcClient.connect({
+        // REPLACE WITH YOUR MODAL URL ENDPOINT
+        endpoint:
+          'https://<your-workspace>--pipecat-modal-fastapi-app.modal.run/connect',
+        requestData: {
+          bot_name: selectedBot,
+        },
+      });
 
       this.log('Connection complete');
     } catch (error) {
@@ -336,9 +331,9 @@ class ChatbotClient {
       this.updateStatus('Error');
 
       // Clean up if there's an error
-      if (this.rtviClient) {
+      if (this.pcClient) {
         try {
-          await this.rtviClient.disconnect();
+          await this.pcClient.disconnect();
         } catch (disconnectError) {
           this.log(`Error during disconnect: ${disconnectError.message}`);
         }
@@ -350,10 +345,10 @@ class ChatbotClient {
    * Disconnect from the bot and clean up media resources
    */
   async disconnect() {
-    if (this.rtviClient) {
+    if (this.pcClient) {
       try {
-        // Disconnect the RTVI client
-        await this.rtviClient.disconnect();
+        // Disconnect the Pipecat client
+        await this.pcClient.disconnect();
 
         // Clean up audio
         if (this.botAudio.srcObject) {

examples/deployment/modal-example/server/app.py

@@ -301,7 +301,7 @@ def fastapi_app():
         allow_headers=["*"],
     )
 
-    # Include the endpoints from endpoints.py
+    # Include the endpoints from this file
     web_app.include_router(router)
 
     return web_app

examples/deployment/modal-example/server/requirements.txt

@@ -1,2 +1,3 @@
 python-dotenv==1.0.1
-modal==0.71.3
+modal==1.0.5
+fastapi[all]

examples/deployment/pipecat-cloud-daily-pstn-server/nextjs-webhook-server/package-lock.json

@@ -8,7 +8,7 @@
       "name": "my-daily-app",
       "version": "0.1.0",
       "dependencies": {
-        "axios": "^1.6.0",
+        "axios": "^1.11.0",
         "next": "^14.0.0",
         "pino": "^8.15.0",
         "react": "^18.2.0",
@@ -215,10 +215,9 @@
       }
     },
     "node_modules/@next/env": {
-      "version": "14.2.26",
-      "resolved": "https://registry.npmjs.org/@next/env/-/env-14.2.26.tgz",
-      "integrity": "sha512-vO//GJ/YBco+H7xdQhzJxF7ub3SUwft76jwaeOyVVQFHCi5DCnkP16WHB+JBylo4vOKPoZBlR94Z8xBxNBdNJA==",
-      "license": "MIT"
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/env/-/env-14.2.30.tgz",
+      "integrity": "sha512-KBiBKrDY6kxTQWGzKjQB7QirL3PiiOkV7KW98leHFjtVRKtft76Ra5qSA/SL75xT44dp6hOcqiiJ6iievLOYug=="
     },
     "node_modules/@next/eslint-plugin-next": {
       "version": "14.2.25",
@@ -231,13 +230,12 @@
       }
     },
     "node_modules/@next/swc-darwin-arm64": {
-      "version": "14.2.26",
-      "resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-14.2.26.tgz",
-      "integrity": "sha512-zDJY8gsKEseGAxG+C2hTMT0w9Nk9N1Sk1qV7vXYz9MEiyRoF5ogQX2+vplyUMIfygnjn9/A04I6yrUTRTuRiyQ==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-14.2.30.tgz",
+      "integrity": "sha512-EAqfOTb3bTGh9+ewpO/jC59uACadRHM6TSA9DdxJB/6gxOpyV+zrbqeXiFTDy9uV6bmipFDkfpAskeaDcO+7/g==",
       "cpu": [
         "arm64"
       ],
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
@@ -247,13 +245,12 @@
       }
     },
     "node_modules/@next/swc-darwin-x64": {
-      "version": "14.2.26",
-      "resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-14.2.26.tgz",
-      "integrity": "sha512-U0adH5ryLfmTDkahLwG9sUQG2L0a9rYux8crQeC92rPhi3jGQEY47nByQHrVrt3prZigadwj/2HZ1LUUimuSbg==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-14.2.30.tgz",
+      "integrity": "sha512-TyO7Wz1IKE2kGv8dwQ0bmPL3s44EKVencOqwIY69myoS3rdpO1NPg5xPM5ymKu7nfX4oYJrpMxv8G9iqLsnL4A==",
       "cpu": [
         "x64"
       ],
-      "license": "MIT",
       "optional": true,
       "os": [
         "darwin"
@@ -263,13 +260,12 @@
       }
     },
     "node_modules/@next/swc-linux-arm64-gnu": {
-      "version": "14.2.26",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-14.2.26.tgz",
-      "integrity": "sha512-SINMl1I7UhfHGM7SoRiw0AbwnLEMUnJ/3XXVmhyptzriHbWvPPbbm0OEVG24uUKhuS1t0nvN/DBvm5kz6ZIqpg==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-14.2.30.tgz",
+      "integrity": "sha512-I5lg1fgPJ7I5dk6mr3qCH1hJYKJu1FsfKSiTKoYwcuUf53HWTrEkwmMI0t5ojFKeA6Vu+SfT2zVy5NS0QLXV4Q==",
       "cpu": [
         "arm64"
       ],
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -279,13 +275,12 @@
       }
     },
     "node_modules/@next/swc-linux-arm64-musl": {
-      "version": "14.2.26",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-14.2.26.tgz",
-      "integrity": "sha512-s6JaezoyJK2DxrwHWxLWtJKlqKqTdi/zaYigDXUJ/gmx/72CrzdVZfMvUc6VqnZ7YEvRijvYo+0o4Z9DencduA==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-14.2.30.tgz",
+      "integrity": "sha512-8GkNA+sLclQyxgzCDs2/2GSwBc92QLMrmYAmoP2xehe5MUKBLB2cgo34Yu242L1siSkwQkiV4YLdCnjwc/Micw==",
       "cpu": [
         "arm64"
       ],
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -295,13 +290,12 @@
       }
     },
     "node_modules/@next/swc-linux-x64-gnu": {
-      "version": "14.2.26",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-14.2.26.tgz",
-      "integrity": "sha512-FEXeUQi8/pLr/XI0hKbe0tgbLmHFRhgXOUiPScz2hk0hSmbGiU8aUqVslj/6C6KA38RzXnWoJXo4FMo6aBxjzg==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-14.2.30.tgz",
+      "integrity": "sha512-8Ly7okjssLuBoe8qaRCcjGtcMsv79hwzn/63wNeIkzJVFVX06h5S737XNr7DZwlsbTBDOyI6qbL2BJB5n6TV/w==",
       "cpu": [
         "x64"
       ],
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -311,13 +305,12 @@
       }
     },
     "node_modules/@next/swc-linux-x64-musl": {
-      "version": "14.2.26",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-14.2.26.tgz",
-      "integrity": "sha512-BUsomaO4d2DuXhXhgQCVt2jjX4B4/Thts8nDoIruEJkhE5ifeQFtvW5c9JkdOtYvE5p2G0hcwQ0UbRaQmQwaVg==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-14.2.30.tgz",
+      "integrity": "sha512-dBmV1lLNeX4mR7uI7KNVHsGQU+OgTG5RGFPi3tBJpsKPvOPtg9poyav/BYWrB3GPQL4dW5YGGgalwZ79WukbKQ==",
       "cpu": [
         "x64"
       ],
-      "license": "MIT",
       "optional": true,
       "os": [
         "linux"
@@ -327,13 +320,12 @@
       }
     },
     "node_modules/@next/swc-win32-arm64-msvc": {
-      "version": "14.2.26",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-14.2.26.tgz",
-      "integrity": "sha512-5auwsMVzT7wbB2CZXQxDctpWbdEnEW/e66DyXO1DcgHxIyhP06awu+rHKshZE+lPLIGiwtjo7bsyeuubewwxMw==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-14.2.30.tgz",
+      "integrity": "sha512-6MMHi2Qc1Gkq+4YLXAgbYslE1f9zMGBikKMdmQRHXjkGPot1JY3n5/Qrbg40Uvbi8//wYnydPnyvNhI1DMUW1g==",
       "cpu": [
         "arm64"
       ],
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -343,13 +335,12 @@
       }
     },
     "node_modules/@next/swc-win32-ia32-msvc": {
-      "version": "14.2.26",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-ia32-msvc/-/swc-win32-ia32-msvc-14.2.26.tgz",
-      "integrity": "sha512-GQWg/Vbz9zUGi9X80lOeGsz1rMH/MtFO/XqigDznhhhTfDlDoynCM6982mPCbSlxJ/aveZcKtTlwfAjwhyxDpg==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-ia32-msvc/-/swc-win32-ia32-msvc-14.2.30.tgz",
+      "integrity": "sha512-pVZMnFok5qEX4RT59mK2hEVtJX+XFfak+/rjHpyFh7juiT52r177bfFKhnlafm0UOSldhXjj32b+LZIOdswGTg==",
       "cpu": [
         "ia32"
       ],
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -359,13 +350,12 @@
       }
     },
     "node_modules/@next/swc-win32-x64-msvc": {
-      "version": "14.2.26",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-14.2.26.tgz",
-      "integrity": "sha512-2rdB3T1/Gp7bv1eQTTm9d1Y1sv9UuJ2LAwOE0Pe2prHKe32UNscj7YS13fRB37d0GAiGNR+Y7ZcW8YjDI8Ns0w==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-14.2.30.tgz",
+      "integrity": "sha512-4KCo8hMZXMjpTzs3HOqOGYYwAXymXIy7PEPAXNEcEOyKqkjiDlECumrWziy+JEF0Oi4ILHGxzgQ3YiMGG2t/Lg==",
       "cpu": [
         "x64"
       ],
-      "license": "MIT",
       "optional": true,
       "os": [
         "win32"
@@ -620,11 +610,10 @@
       }
     },
     "node_modules/@typescript-eslint/typescript-estree/node_modules/brace-expansion": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
-      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
+      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0"
       }
@@ -1176,13 +1165,13 @@
       }
     },
     "node_modules/axios": {
-      "version": "1.8.4",
-      "resolved": "https://registry.npmjs.org/axios/-/axios-1.8.4.tgz",
-      "integrity": "sha512-eBSYY4Y68NNlHbHBMdeDmKNtDgXWhQsJcGqzO3iLUM0GraQFSS9cVgPX5I9b3lbdFKyYoAEGAZF1DwhTaljNAw==",
+      "version": "1.11.0",
+      "resolved": "https://registry.npmjs.org/axios/-/axios-1.11.0.tgz",
+      "integrity": "sha512-1Lx3WLFQWm3ooKDYZD1eXmoGO9fxYQjrycfHFC8P0sCfQVXyROp0p9PFWBehewBOdCwHc+f/b8I0fMto5eSfwA==",
       "license": "MIT",
       "dependencies": {
         "follow-redirects": "^1.15.6",
-        "form-data": "^4.0.0",
+        "form-data": "^4.0.4",
         "proxy-from-env": "^1.1.0"
       }
     },
@@ -1224,11 +1213,10 @@
       "license": "MIT"
     },
     "node_modules/brace-expansion": {
-      "version": "1.1.11",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
-      "integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
+      "version": "1.1.12",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
+      "integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0",
         "concat-map": "0.0.1"
@@ -2448,14 +2436,15 @@
       }
     },
     "node_modules/form-data": {
-      "version": "4.0.2",
-      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.2.tgz",
-      "integrity": "sha512-hGfm/slu0ZabnNt4oaRZ6uREyfCj6P4fT/n6A1rGV+Z0VdGXjfOhVUpkn6qVQONHGIFwmveGXyDs75+nr6FM8w==",
+      "version": "4.0.4",
+      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.4.tgz",
+      "integrity": "sha512-KrGhL9Q4zjj0kiUt5OO4Mr/A/jlI2jDYs5eHBpYHPcBEVSiipAvn2Ko2HnPe20rmcuuvMHNdZFp+4IlGTMF0Ow==",
       "license": "MIT",
       "dependencies": {
         "asynckit": "^0.4.0",
         "combined-stream": "^1.0.8",
         "es-set-tostringtag": "^2.1.0",
+        "hasown": "^2.0.2",
         "mime-types": "^2.1.12"
       },
       "engines": {
@@ -2614,11 +2603,10 @@
       }
     },
     "node_modules/glob/node_modules/brace-expansion": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
-      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
+      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
       "dev": true,
-      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0"
       }
@@ -3613,12 +3601,11 @@
       "license": "MIT"
     },
     "node_modules/next": {
-      "version": "14.2.26",
-      "resolved": "https://registry.npmjs.org/next/-/next-14.2.26.tgz",
-      "integrity": "sha512-b81XSLihMwCfwiUVRRja3LphLo4uBBMZEzBBWMaISbKTwOmq3wPknIETy/8000tr7Gq4WmbuFYPS7jOYIf+ZJw==",
-      "license": "MIT",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/next/-/next-14.2.30.tgz",
+      "integrity": "sha512-+COdu6HQrHHFQ1S/8BBsCag61jZacmvbuL2avHvQFbWa2Ox7bE+d8FyNgxRLjXQ5wtPyQwEmk85js/AuaG2Sbg==",
       "dependencies": {
-        "@next/env": "14.2.26",
+        "@next/env": "14.2.30",
         "@swc/helpers": "0.5.5",
         "busboy": "1.6.0",
         "caniuse-lite": "^1.0.30001579",
@@ -3633,15 +3620,15 @@
         "node": ">=18.17.0"
       },
       "optionalDependencies": {
-        "@next/swc-darwin-arm64": "14.2.26",
-        "@next/swc-darwin-x64": "14.2.26",
-        "@next/swc-linux-arm64-gnu": "14.2.26",
-        "@next/swc-linux-arm64-musl": "14.2.26",
-        "@next/swc-linux-x64-gnu": "14.2.26",
-        "@next/swc-linux-x64-musl": "14.2.26",
-        "@next/swc-win32-arm64-msvc": "14.2.26",
-        "@next/swc-win32-ia32-msvc": "14.2.26",
-        "@next/swc-win32-x64-msvc": "14.2.26"
+        "@next/swc-darwin-arm64": "14.2.30",
+        "@next/swc-darwin-x64": "14.2.30",
+        "@next/swc-linux-arm64-gnu": "14.2.30",
+        "@next/swc-linux-arm64-musl": "14.2.30",
+        "@next/swc-linux-x64-gnu": "14.2.30",
+        "@next/swc-linux-x64-musl": "14.2.30",
+        "@next/swc-win32-arm64-msvc": "14.2.30",
+        "@next/swc-win32-ia32-msvc": "14.2.30",
+        "@next/swc-win32-x64-msvc": "14.2.30"
       },
       "peerDependencies": {
         "@opentelemetry/api": "^1.1.0",

examples/deployment/pipecat-cloud-daily-pstn-server/nextjs-webhook-server/package.json

@@ -9,7 +9,7 @@
     "lint": "next lint"
   },
   "dependencies": {
-    "axios": "^1.6.0",
+    "axios": "^1.11.0",
     "next": "^14.0.0",
     "pino": "^8.15.0",
     "react": "^18.2.0",

examples/deployment/pipecat-cloud-daily-pstn-server/nextjs-webhook-server/pages/api/dial.js

@@ -103,7 +103,7 @@ export default async function handler(req, res) {
       const sip_config = {
         display_name: From,
         sip_mode: 'dial-in',
-        num_endpoints: call_transfer !== null ? 2 : 1,
+        num_endpoints: (call_transfer !== undefined && call_transfer !== null) ? 2 : 1,
         codecs: {"audio": ["OPUS"]},
       };
       daily_room_properties.sip = sip_config;

examples/deployment/pipecat-cloud-example/bot.py

@@ -90,7 +90,7 @@ async def main(transport: DailyTransport):
         logger.info("Participant left: {}", participant)
         await task.cancel()
 
-    runner = PipelineRunner()
+    runner = PipelineRunner(handle_sigint=False, force_gc=True)
 
     await runner.run(task)
 

examples/fal-smart-turn/README.md

@@ -44,7 +44,7 @@ Try the hosted version of the demo here: https://pcc-smart-turn.vercel.app/.
 4. Run the server:
 
    ```bash
-   LOCAL=1 python server.py
+   LOCAL_RUN=1 python server.py
    ```
 
 ### Run the client

examples/fal-smart-turn/client/package.json

@@ -9,9 +9,9 @@
     "lint": "next lint"
   },
   "dependencies": {
-    "@pipecat-ai/client-js": "^0.3.5",
-    "@pipecat-ai/client-react": "^0.3.5",
-    "@pipecat-ai/daily-transport": "^0.3.10",
+    "@pipecat-ai/client-js": "^1.0.0",
+    "@pipecat-ai/client-react": "^1.0.0",
+    "@pipecat-ai/daily-transport": "^1.0.0",
     "next": "15.3.1",
     "react": "^19.0.0",
     "react-dom": "^19.0.0"

examples/fal-smart-turn/client/src/app/layout.tsx

@@ -1,5 +1,5 @@
 import './globals.css';
-import { RTVIProvider } from '@/providers/RTVIProvider';
+import { PipecatProvider } from '@/providers/PipecatProvider';
 
 export const metadata = {
   title: 'Pipecat React Client',
@@ -20,7 +20,7 @@ export default function RootLayout({
         <link rel="icon" href="/favicon.svg" type="image/svg+xml" />
       </head>
       <body>
-        <RTVIProvider>{children}</RTVIProvider>
+        <PipecatProvider>{children}</PipecatProvider>
       </body>
     </html>
   );

examples/fal-smart-turn/client/src/app/page.tsx

@@ -1,22 +1,22 @@
 'use client';
 
 import {
-  RTVIClientAudio,
-  RTVIClientVideo,
-  useRTVIClientTransportState,
+  PipecatClientAudio,
+  PipecatClientVideo,
+  usePipecatClientTransportState,
 } from '@pipecat-ai/client-react';
 import { ConnectButton } from '../components/ConnectButton';
 import { StatusDisplay } from '../components/StatusDisplay';
 import { DebugDisplay } from '../components/DebugDisplay';
 
 function BotVideo() {
-  const transportState = useRTVIClientTransportState();
+  const transportState = usePipecatClientTransportState();
   const isConnected = transportState !== 'disconnected';
 
   return (
     <div className="bot-container">
       <div className="video-container">
-        {isConnected && <RTVIClientVideo participant="bot" fit="cover" />}
+        {isConnected && <PipecatClientVideo participant="bot" fit="cover" />}
       </div>
     </div>
   );
@@ -35,7 +35,7 @@ export default function Home() {
       </div>
 
       <DebugDisplay />
-      <RTVIClientAudio />
+      <PipecatClientAudio />
     </div>
   );
 }

examples/fal-smart-turn/client/src/components/ConnectButton.tsx

@@ -1,11 +1,17 @@
 import {
-  useRTVIClient,
-  useRTVIClientTransportState,
+  usePipecatClient,
+  usePipecatClientTransportState,
 } from '@pipecat-ai/client-react';
 
+// Get the API base URL from environment variables
+// Default to "/api" if not specified
+// "/api" is the default for Next.js API routes and used
+// for the Pipecat Cloud deployed agent
+const API_BASE_URL = process.env.NEXT_PUBLIC_API_BASE_URL || '/api';
+
 export function ConnectButton() {
-  const client = useRTVIClient();
-  const transportState = useRTVIClientTransportState();
+  const client = usePipecatClient();
+  const transportState = usePipecatClientTransportState();
   const isConnected = ['connected', 'ready'].includes(transportState);
 
   const handleClick = async () => {
@@ -18,7 +24,10 @@ export function ConnectButton() {
       if (isConnected) {
         await client.disconnect();
       } else {
-        await client.connect();
+        await client.connect({
+          endpoint: `${API_BASE_URL}/connect`,
+          requestData: { foo: 'bar' },
+        });
       }
     } catch (error) {
       console.error('Connection error:', error);

examples/fal-smart-turn/client/src/components/DebugDisplay.tsx

@@ -6,7 +6,7 @@ import {
   TranscriptData,
   BotLLMTextData,
 } from '@pipecat-ai/client-js';
-import { useRTVIClient, useRTVIClientEvent } from '@pipecat-ai/client-react';
+import { usePipecatClient, useRTVIClientEvent } from '@pipecat-ai/client-react';
 import './DebugDisplay.css';
 
 interface SmartTurnResultData {
@@ -20,7 +20,7 @@ interface SmartTurnResultData {
 
 export function DebugDisplay() {
   const debugLogRef = useRef<HTMLDivElement>(null);
-  const client = useRTVIClient();
+  const client = usePipecatClient();
 
   const log = useCallback((message: string) => {
     if (!debugLogRef.current) return;

examples/fal-smart-turn/client/src/components/StatusDisplay.tsx

@@ -1,7 +1,7 @@
-import { useRTVIClientTransportState } from '@pipecat-ai/client-react';
+import { usePipecatClientTransportState } from '@pipecat-ai/client-react';
 
 export function StatusDisplay() {
-  const transportState = useRTVIClientTransportState();
+  const transportState = usePipecatClientTransportState();
 
   return (
     <div className="status">

examples/fal-smart-turn/client/src/providers/PipecatProvider.tsx

@@ -0,0 +1,28 @@
+'use client';
+
+import { PipecatClient } from '@pipecat-ai/client-js';
+import { DailyTransport } from '@pipecat-ai/daily-transport';
+import { PipecatClientProvider } from '@pipecat-ai/client-react';
+import { PropsWithChildren, useEffect, useState } from 'react';
+
+export function PipecatProvider({ children }: PropsWithChildren) {
+  const [client, setClient] = useState<PipecatClient | null>(null);
+
+  useEffect(() => {
+    const pcClient = new PipecatClient({
+      transport: new DailyTransport(),
+      enableMic: true,
+      enableCam: false,
+    });
+
+    setClient(pcClient);
+  }, []);
+
+  if (!client) {
+    return null;
+  }
+
+  return (
+    <PipecatClientProvider client={client}>{children}</PipecatClientProvider>
+  );
+}

examples/fal-smart-turn/client/src/providers/RTVIProvider.tsx

@@ -1,43 +0,0 @@
-'use client';
-
-import { RTVIClient } from '@pipecat-ai/client-js';
-import { DailyTransport } from '@pipecat-ai/daily-transport';
-import { RTVIClientProvider } from '@pipecat-ai/client-react';
-import { PropsWithChildren, useEffect, useState } from 'react';
-
-// Get the API base URL from environment variables
-// Default to "/api" if not specified
-// "/api" is the default for Next.js API routes and used
-// for the Pipecat Cloud deployed agent
-const API_BASE_URL = process.env.NEXT_PUBLIC_API_BASE_URL || '/api';
-
-console.log('Using API base URL:', API_BASE_URL);
-
-export function RTVIProvider({ children }: PropsWithChildren) {
-  const [client, setClient] = useState<RTVIClient | null>(null);
-
-  useEffect(() => {
-    const transport = new DailyTransport();
-
-    const rtviClient = new RTVIClient({
-      transport,
-      params: {
-        baseUrl: API_BASE_URL,
-        endpoints: {
-          connect: '/connect',
-        },
-        requestData: { foo: 'bar' },
-      },
-      enableMic: true,
-      enableCam: false,
-    });
-
-    setClient(rtviClient);
-  }, []);
-
-  if (!client) {
-    return null;
-  }
-
-  return <RTVIClientProvider client={client}>{children}</RTVIClientProvider>;
-}

examples/fal-smart-turn/server/bot.py

@@ -45,7 +45,7 @@ from pipecat.transports.services.daily import DailyParams, DailyTransport
 load_dotenv(override=True)
 
 # Check if we're in local development mode
-LOCAL = os.getenv("LOCAL")
+LOCAL = os.getenv("LOCAL_RUN")
 
 logger.remove()
 logger.add(sys.stderr, level="DEBUG")

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

@@ -20,7 +20,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.services.daily import DailyLogLevel, DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -43,6 +43,7 @@ async def main():
                 vad_analyzer=SileroVADAnalyzer(),
             ),
         )
+        transport.set_log_level(DailyLogLevel.Info)
 
         tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),

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

@@ -0,0 +1,153 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import os
+
+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.llm_response import (
+    LLMUserAggregatorParams,
+)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
+from pipecat.services.openai.base_llm import BaseOpenAILLMService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    """Run example using Speechmatics STT.
+
+    This example will use diarization within our STT service and output the words spoken by
+    each individual speaker and wrap them with XML tags for the LLM to process. Note the
+    instructions in the system context for the LLM. This greatly improves the conversation
+    experience by allowing the LLM to understand who is speaking in a multi-party call.
+
+    If you do not wish to use diarization, then set the `enable_speaker_diarization` parameter
+    to `False` or omit it altogether. The `text_format` will only be used if diarization is enabled.
+
+    By default, this example will use our ENHANCED operating point, which is optimized for
+    high accuracy. You can change this by setting the `operating_point` parameter to a different
+    value.
+
+    For more information on operating points, see the Speechmatics documentation:
+    https://docs.speechmatics.com/rt-api-ref
+    """
+    logger.info(f"Starting bot")
+
+    stt = SpeechmaticsSTTService(
+        api_key=os.getenv("SPEECHMATICS_API_KEY"),
+        language=Language.EN,
+        enable_speaker_diarization=True,
+        text_format="<{speaker_id}>{text}</{speaker_id}>",
+    )
+
+    tts = ElevenLabsTTSService(
+        api_key=os.getenv("ELEVENLABS_API_KEY", ""),
+        voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
+        model="eleven_turbo_v2_5",
+    )
+
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        params=BaseOpenAILLMService.InputParams(temperature=0.75),
+    )
+
+    messages = [
+        {
+            "role": "system",
+            "content": (
+                "You are a helpful British assistant called Alfred. "
+                "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. "
+                "Always include punctuation in your responses. "
+                "Give very short replies - do not give longer replies unless strictly necessary. "
+                "Respond to what the user said in a concise, funny, creative and helpful way. "
+                "Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
+            ),
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(
+        context,
+        user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Say a short hello to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=handle_sigint)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    main(run_example, transport_params=transport_params)

examples/foundational/07aa-interruptible-soniox.py

@@ -0,0 +1,109 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import os
+
+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.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.soniox.stt import SonioxSTTService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    logger.info(f"Starting bot")
+
+    stt = SonioxSTTService(
+        api_key=os.getenv("SONIOX_API_KEY"),
+    )
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=handle_sigint)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    main(run_example, transport_params=transport_params)

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

@@ -35,7 +35,7 @@ transport_params = {
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(),
     ),
-    "twilio": lambda: TransportParams(
+    "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(),

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

@@ -61,7 +61,12 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
     )
 
-    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
+    llm = GoogleLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        model="gemini-2.5-flash",
+        # turn on thinking if you want it
+        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),)
+    )
 
     messages = [
         {

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

@@ -214,7 +214,12 @@ transport_params = {
 async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
     logger.info(f"Starting bot")
 
-    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
+    llm = GoogleLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        model="gemini-2.5-flash",
+        # turn on thinking if you want it
+        # params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),
+    )
 
     tts = GoogleTTSService(
         voice_id="en-US-Chirp3-HD-Charon",

examples/foundational/07v-interruptible-neuphonic-http.py

@@ -7,6 +7,7 @@
 import argparse
 import os
 
+import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
@@ -50,60 +51,63 @@ transport_params = {
 async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
     logger.info(f"Starting bot")
 
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    # Create an HTTP session
+    async with aiohttp.ClientSession() as session:
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = NeuphonicHttpTTSService(
-        api_key=os.getenv("NEUPHONIC_API_KEY"),
-        voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
-    )
+        tts = NeuphonicHttpTTSService(
+            api_key=os.getenv("NEUPHONIC_API_KEY"),
+            voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
+            aiohttp_session=session,
+        )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-    messages = [
-        {
-            "role": "system",
-            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-        },
-    ]
-
-    context = OpenAILLMContext(messages)
-    context_aggregator = llm.create_context_aggregator(context)
-
-    pipeline = Pipeline(
-        [
-            transport.input(),  # Transport user input
-            stt,
-            context_aggregator.user(),  # User responses
-            llm,  # LLM
-            tts,  # TTS
-            transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+        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.",
+            },
         ]
-    )
 
-    task = PipelineTask(
-        pipeline,
-        params=PipelineParams(
-            enable_metrics=True,
-            enable_usage_metrics=True,
-        ),
-    )
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
-    @transport.event_handler("on_client_connected")
-    async def on_client_connected(transport, client):
-        logger.info(f"Client connected")
-        # Kick off the conversation.
-        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
 
-    @transport.event_handler("on_client_disconnected")
-    async def on_client_disconnected(transport, client):
-        logger.info(f"Client disconnected")
-        await task.cancel()
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+        )
 
-    runner = PipelineRunner(handle_sigint=handle_sigint)
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info(f"Client connected")
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-    await runner.run(task)
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+            await task.cancel()
+
+        runner = PipelineRunner(handle_sigint=handle_sigint)
+
+        await runner.run(task)
 
 
 if __name__ == "__main__":

examples/foundational/13h-speechmatics-transcription.py

@@ -0,0 +1,89 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.frames.frames import Frame, TranscriptionFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+
+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}")
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(audio_in_enabled=True),
+    "twilio": lambda: FastAPIWebsocketParams(audio_in_enabled=True),
+    "webrtc": lambda: TransportParams(audio_in_enabled=True),
+}
+
+
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    """Run example using Speechmatics STT.
+
+    This example will use diarization within our STT service and output the words spoken by
+    each individual speaker and wrap them with XML tags.
+
+    If you do not wish to use diarization, then set the `enable_speaker_diarization` parameter
+    to `False` or omit it altogether. The `text_format` will only be used if diarization is enabled.
+
+    By default, this example will use our ENHANCED operating point, which is optimized for
+    high accuracy. You can change this by setting the `operating_point` parameter to a different
+    value.
+
+    For more information on operating points, see the Speechmatics documentation:
+    https://docs.speechmatics.com/rt-api-ref
+    """
+    logger.info(f"Starting bot")
+
+    stt = SpeechmaticsSTTService(
+        api_key=os.getenv("SPEECHMATICS_API_KEY"),
+        language=Language.EN,
+        enable_speaker_diarization=True,
+        text_format="<{speaker_id}>{text}</{speaker_id}>",
+    )
+
+    tl = TranscriptionLogger()
+
+    pipeline = Pipeline([transport.input(), stt, tl])
+
+    task = PipelineTask(pipeline)
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=handle_sigint)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    main(run_example, transport_params=transport_params)

examples/foundational/13i-soniox-transcription.py

@@ -0,0 +1,81 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+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.soniox.stt import SonioxSTTService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+
+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}")
+
+
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    logger.info(f"Starting bot")
+
+    stt = SonioxSTTService(
+        api_key=os.getenv("SONIOX_API_KEY"),
+    )
+
+    tl = TranscriptionLogger()
+
+    pipeline = Pipeline([transport.input(), stt, tl])
+
+    task = PipelineTask(pipeline)
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    main(run_example, transport_params=transport_params)

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

@@ -42,7 +42,7 @@ transport_params = {
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(),
     ),
-    "twilio": lambda: TransportParams(
+    "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(),

examples/foundational/14t-function-calling-direct.py

@@ -0,0 +1,146 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+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.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+
+async def get_current_weather(params: FunctionCallParams, location: str, format: str):
+    """
+    Get the current weather.
+
+    Args:
+        location (str): The city and state, e.g. "San Francisco, CA".
+        format (str): The temperature unit to use. Must be either "celsius" or "fahrenheit". Infer this from the user's location.
+    """
+    await params.result_callback({"conditions": "nice", "temperature": "75"})
+
+
+async def get_restaurant_recommendation(params: FunctionCallParams, location: str):
+    """
+    Get a restaurant recommendation.
+
+    Args:
+        location (str): The city and state, e.g. "San Francisco, CA".
+    """
+    await params.result_callback({"name": "The Golden Dragon"})
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    # You can also register a function_name of None to get all functions
+    # sent to the same callback with an additional function_name parameter.
+    llm.register_direct_function(get_current_weather)
+    llm.register_direct_function(get_restaurant_recommendation)
+
+    @llm.event_handler("on_function_calls_started")
+    async def on_function_calls_started(service, function_calls):
+        await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
+
+    tools = ToolsSchema(standard_tools=[get_current_weather, get_restaurant_recommendation])
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=handle_sigint)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    main(run_example, transport_params=transport_params)

examples/foundational/14u-function-calling-ollama.py

@@ -0,0 +1,162 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.adapters.schemas.function_schema import FunctionSchema
+from pipecat.adapters.schemas.tools_schema import ToolsSchema
+from pipecat.audio.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.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.llm_service import FunctionCallParams
+from pipecat.services.ollama.llm import OLLamaLLMService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+
+async def fetch_weather_from_api(params: FunctionCallParams):
+    await params.result_callback({"conditions": "nice", "temperature": "75"})
+
+
+async def fetch_restaurant_recommendation(params: FunctionCallParams):
+    await params.result_callback({"name": "The Golden Dragon"})
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = OLLamaLLMService(model="llama3.2")  # Update to the model you're running locally
+
+    # You can also register a function_name of None to get all functions
+    # sent to the same callback with an additional function_name parameter.
+    llm.register_function("get_current_weather", fetch_weather_from_api)
+    llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
+
+    @llm.event_handler("on_function_calls_started")
+    async def on_function_calls_started(service, function_calls):
+        await tts.queue_frame(TTSSpeakFrame("Let me check on that."))
+
+    weather_function = FunctionSchema(
+        name="get_current_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
+            },
+        },
+        required=["location", "format"],
+    )
+    restaurant_function = FunctionSchema(
+        name="get_restaurant_recommendation",
+        description="Get a restaurant recommendation",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
+            },
+        },
+        required=["location"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=handle_sigint)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    main(run_example, transport_params=transport_params)

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

@@ -33,7 +33,7 @@ transport_params = {
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(),
     ),
-    "twilio": lambda: TransportParams(
+    "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(),

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

@@ -55,7 +55,7 @@ transport_params = {
         # endpointing, for now.
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
     ),
-    "twilio": lambda: TransportParams(
+    "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         # set stop_secs to something roughly similar to the internal setting

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

@@ -0,0 +1,242 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import os
+import tempfile
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.gemini_multimodal_live.gemini import (
+    GeminiMultimodalLiveLLMService,
+)
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=False,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=False,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=False,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+}
+
+
+sample_file_path = ""
+
+
+async def create_sample_file():
+    if sample_file_path:
+        return sample_file_path
+    else:
+        """Create a sample text file for testing the File API."""
+        content = """# Sample Document for Gemini File API Test
+
+    This is a test document to demonstrate the Gemini File API functionality.
+
+    ## Key Information:
+    - This document was created for testing purposes
+    - It contains information about AI assistants
+    - The document should be analyzed by Gemini
+    - The secret phrase for the test is "Pineapple Pizza"
+
+    ## AI Assistant Capabilities:
+    1. Natural language processing
+    2. File analysis and understanding
+    3. Context-aware conversations
+    4. Multi-modal interactions
+
+    ## Conclusion:
+    This document serves as a test case for the Gemini File API integration with Pipecat.
+    The AI should be able to reference and discuss the contents of this file.
+    """
+
+        # Create a temporary file
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
+            f.write(content)
+            return f.name
+
+
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    logger.info(f"Starting File API bot")
+
+    # Create a sample file to upload
+    sample_file_path = await create_sample_file()
+    logger.info(f"Created sample file: {sample_file_path}")
+
+    system_instruction = """
+    You are a helpful AI assistant with access to a document that has been uploaded for analysis.
+    
+    The document contains test information.
+    You should be able to:
+    - Reference and discuss the contents of the uploaded document
+    - Answer questions about what's in the document
+    - Use the information from the document in our conversation
+    
+    Your output will be converted to audio so don't include special characters in your answers.
+    Be friendly and demonstrate your ability to work with the uploaded file.
+    """
+
+    # Initialize Gemini service with File API support
+    llm = GeminiMultimodalLiveLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        system_instruction=system_instruction,
+        voice_id="Charon",  # Aoede, Charon, Fenrir, Kore, Puck
+        transcribe_user_audio=True,
+    )
+
+    # Upload the sample file to Gemini File API
+    logger.info("Uploading file to Gemini File API...")
+    file_info = None
+    try:
+        file_info = await llm.file_api.upload_file(
+            sample_file_path, display_name="Sample Test Document"
+        )
+        logger.info(f"File uploaded successfully: {file_info['file']['name']}")
+
+        # Get file URI and mime type
+        file_uri = file_info["file"]["uri"]
+        mime_type = "text/plain"
+
+        # Create context with file reference
+        context = OpenAILLMContext(
+            [
+                {
+                    "role": "user",
+                    "content": [
+                        {
+                            "type": "text",
+                            "text": "Greet the user and let them know you have access to a document they can ask you about. Mention that you can discuss its contents.",
+                        },
+                        {
+                            "type": "file_data",
+                            "file_data": {"mime_type": mime_type, "file_uri": file_uri},
+                        },
+                    ],
+                }
+            ]
+        )
+
+        logger.info("File reference added to conversation context")
+
+    except Exception as e:
+        logger.error(f"Error uploading file: {e}")
+        # Continue with a basic context if file upload fails
+        context = OpenAILLMContext(
+            [
+                {
+                    "role": "user",
+                    "content": "Greet the user and explain that there was an issue with file upload, but you're ready to help with other tasks.",
+                }
+            ]
+        )
+
+    # Create context aggregator
+    context_aggregator = llm.create_context_aggregator(context)
+
+    # Build the pipeline
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            context_aggregator.user(),
+            llm,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    # Configure the pipeline task
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
+
+    # Handle client connection event
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation using standard context frame
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    # Handle client disconnection events
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    # Run the pipeline
+    runner = PipelineRunner(handle_sigint=False)
+    await runner.run(task)
+
+    # Clean up: delete the uploaded file and temporary file
+    if file_info:
+        try:
+            await llm.file_api.delete_file(file_info["file"]["name"])
+            logger.info("Cleaned up uploaded file from Gemini")
+        except Exception as e:
+            logger.error(f"Error cleaning up file: {e}")
+
+    # Remove temporary file
+    try:
+        os.unlink(sample_file_path)
+        logger.info("Cleaned up temporary file")
+    except Exception as e:
+        logger.error(f"Error removing temporary file: {e}")
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    upload_example_file = input("""
+
+        Please pass in a TEXT filepath to test upload.
+        NOTE: Files are stored on Google's servers for 48 hours.
+
+        Press Enter to use a default test file.
+
+        text filepath : """)
+    if upload_example_file:
+        print(f"Uploading file: {upload_example_file}")
+        sample_file_path = upload_example_file.strip()
+    else:
+        print(f"Using default file")
+
+    main(run_example, transport_params=transport_params)

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

@@ -0,0 +1,165 @@
+import argparse
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.adapters.schemas.tools_schema import AdapterType, ToolsSchema
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.frames.frames import Frame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
+from pipecat.services.google.frames import LLMSearchResponseFrame
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=False,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=False,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=False,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+}
+
+SYSTEM_INSTRUCTION = """
+You are a helpful AI assistant that actively uses Google Search to provide up-to-date, accurate information.
+
+IMPORTANT: For ANY question about current events, news, recent developments, real-time information, or anything that might have changed recently, you MUST use the google_search tool to get the latest information.
+
+You should use Google Search for:
+- Current news and events
+- Recent developments in any field
+- Today's weather, stock prices, or other real-time data
+- Any question that starts with "what's happening", "latest", "recent", "current", "today", etc.
+- When you're not certain about recent information
+
+Always be proactive about using search when the user asks about anything that could benefit from real-time information.
+
+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, always using search for current information.
+"""
+
+
+class GroundingMetadataProcessor(FrameProcessor):
+    """Processor to capture and display grounding metadata from Gemini Live API."""
+
+    def __init__(self):
+        super().__init__()
+        self._grounding_count = 0
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, LLMSearchResponseFrame):
+            self._grounding_count += 1
+            logger.info(f"\n\n🔍 GROUNDING METADATA RECEIVED #{self._grounding_count}\n")
+            logger.info(f"📝 Search Result Text: {frame.search_result[:200]}...")
+
+            if frame.rendered_content:
+                logger.info(f"🔗 Rendered Content: {frame.rendered_content}")
+
+            if frame.origins:
+                logger.info(f"📍 Number of Origins: {len(frame.origins)}")
+                for i, origin in enumerate(frame.origins):
+                    logger.info(f"  Origin {i + 1}: {origin.site_title} - {origin.site_uri}")
+                    if origin.results:
+                        logger.info(f"    Results: {len(origin.results)} items")
+
+        # Always push the frame downstream
+        await self.push_frame(frame, direction)
+
+
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    logger.info(f"Starting Gemini Live Grounding Metadata Test Bot")
+
+    # Create tools using ToolsSchema with custom tools for Gemini
+    tools = ToolsSchema(
+        standard_tools=[],  # No standard function declarations needed
+        custom_tools={AdapterType.GEMINI: [{"google_search": {}}, {"code_execution": {}}]},
+    )
+
+    llm = GeminiMultimodalLiveLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        system_instruction=SYSTEM_INSTRUCTION,
+        voice_id="Charon",  # Aoede, Charon, Fenrir, Kore, Puck
+        transcribe_user_audio=True,
+        tools=tools,
+    )
+
+    # Create a processor to capture grounding metadata
+    grounding_processor = GroundingMetadataProcessor()
+
+    messages = [
+        {
+            "role": "user",
+            "content": "Please introduce yourself and let me know that you can help with current information by searching the web. Ask me what current information I'd like to know about.",
+        },
+    ]
+
+    # Set up conversation context and management
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            context_aggregator.user(),
+            llm,
+            grounding_processor,  # Add our grounding processor here
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(pipeline)
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    main(run_example, transport_params=transport_params)

examples/foundational/38b-smart-turn-local.py

@@ -11,7 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
-from pipecat.audio.turn.smart_turn.local_smart_turn import LocalSmartTurnAnalyzer
+from pipecat.audio.turn.smart_turn.local_smart_turn_v2 import LocalSmartTurnAnalyzerV2
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.pipeline.pipeline import Pipeline
@@ -37,7 +37,7 @@ load_dotenv(override=True)
 #   # Hugging Face uses LFS to store large model files, including .mlpackage
 #   git lfs install
 #   # Clone the repo with the smart_turn_classifier.mlpackage
-#   git clone https://huggingface.co/pipecat-ai/smart-turn
+#   git clone https://huggingface.co/pipecat-ai/smart-turn-v2
 #
 # Then set the env variable:
 #   export LOCAL_SMART_TURN_MODEL_PATH=./smart-turn
@@ -52,7 +52,7 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzer(
+        turn_analyzer=LocalSmartTurnAnalyzerV2(
             smart_turn_model_path=smart_turn_model_path, params=SmartTurnParams()
         ),
     ),
@@ -60,7 +60,7 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzer(
+        turn_analyzer=LocalSmartTurnAnalyzerV2(
             smart_turn_model_path=smart_turn_model_path, params=SmartTurnParams()
         ),
     ),
@@ -68,7 +68,7 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzer(
+        turn_analyzer=LocalSmartTurnAnalyzerV2(
             smart_turn_model_path=smart_turn_model_path, params=SmartTurnParams()
         ),
     ),

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

@@ -0,0 +1,133 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+from mcp.client.session_group import StreamableHttpParameters
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.google.llm import GoogleLLMService
+from pipecat.services.mcp_service import MCPClient
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
+from pipecat.transports.services.daily import DailyParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash")
+
+    try:
+        # Github MCP docs: https://github.com/github/github-mcp-server
+        # Enable Github Copilot on your GitHub account. Free tier is ok. (https://github.com/settings/copilot)
+        # Generate a personal access token. It must be a Fine-grained token, classic tokens are not supported. (https://github.com/settings/personal-access-tokens)
+        # Set permissions you want to use (eg. "all repositories", "profile: read/write", etc)
+        mcp = MCPClient(
+            server_params=StreamableHttpParameters(
+                url="https://api.githubcopilot.com/mcp/",
+                headers={"Authorization": f"Bearer {os.getenv('GITHUB_PERSONAL_ACCESS_TOKEN')}"},
+            )
+        )
+    except Exception as e:
+        logger.error(f"error setting up mcp")
+        logger.exception("error trace:")
+
+    tools = await mcp.register_tools(llm)
+
+    system = f"""
+    You are a helpful LLM in a WebRTC call.
+    Your goal is to answer questions about the user's GitHub repositories and account.
+    You have access to a number of tools provided by Github. Use any and all tools to help users.
+    Your output will be converted to audio so don't include special characters in your answers.
+    Don't overexplain what you are doing.
+    Just respond with short sentences when you are carrying out tool calls.
+    """
+
+    messages = [{"role": "system", "content": system}]
+
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User spoken responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses and tool context
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=handle_sigint)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from pipecat.examples.run import main
+
+    main(run_example, transport_params=transport_params)

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

@@ -102,6 +102,7 @@ async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_si
         secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
         access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
         region=os.getenv("AWS_REGION"),  # as of 2025-05-06, us-east-1 is the only supported region
+        session_token=os.getenv("AWS_SESSION_TOKEN"),
         voice_id="tiffany",  # matthew, tiffany, amy
         # you could choose to pass instruction here rather than via context
         # system_instruction=system_instruction

examples/foundational/42-interruption-config.py

@@ -10,8 +10,8 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+from pipecat.audio.interruptions.min_words_interruption_strategy import MinWordsInterruptionStrategy
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import MinWordsInterruptionStrategy
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask

examples/freeze-test/client/src/app.ts

@@ -20,11 +20,10 @@ import {
 } from '@pipecat-ai/client-js';
 import {
   ProtobufFrameSerializer,
-  WebSocketTransport
-} from "@pipecat-ai/websocket-transport";
+  WebSocketTransport,
+} from '@pipecat-ai/websocket-transport';
 
 class RecordingSerializer extends ProtobufFrameSerializer {
-
   private lastTimestamp: number | null = null;
   private recordingAudioToSend: boolean = false;
   private _recordedAudio: { data: ArrayBuffer; delay: number }[] = [];
@@ -40,7 +39,11 @@ class RecordingSerializer extends ProtobufFrameSerializer {
   }
 
   // @ts-ignore
-  serializeAudio(data: ArrayBuffer, sampleRate: number, numChannels: number): Uint8Array | null {
+  serializeAudio(
+    data: ArrayBuffer,
+    sampleRate: number,
+    numChannels: number
+  ): Uint8Array | null {
     if (this.recordingAudioToSend) {
       const now = Date.now();
       // Compute delay since last packet
@@ -55,13 +58,13 @@ class RecordingSerializer extends ProtobufFrameSerializer {
   }
 
   public get recordedAudio() {
-    return this._recordedAudio
+    return this._recordedAudio;
   }
 }
 
 class WebsocketClientApp {
-  private ENABLE_RECORDING_MODE = false
-  private RECORDING_TIME_MS = 10000
+  private ENABLE_RECORDING_MODE = false;
+  private RECORDING_TIME_MS = 10000;
 
   private rtviClient: RTVIClient | null = null;
   private connectBtn: HTMLButtonElement | null = null;
@@ -71,7 +74,7 @@ class WebsocketClientApp {
   private botAudio: HTMLAudioElement;
 
   private declare websocketTransport: WebSocketTransport;
-  private sendRecordedAudio: boolean = false
+  private sendRecordedAudio: boolean = false;
   private declare recordingSerializer: RecordingSerializer;
 
   private playBtn: HTMLButtonElement | null = null;
@@ -91,8 +94,12 @@ class WebsocketClientApp {
    * 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.connectBtn = document.getElementById(
+      'connect-btn'
+    ) as HTMLButtonElement;
+    this.disconnectBtn = document.getElementById(
+      'disconnect-btn'
+    ) as HTMLButtonElement;
     this.statusSpan = document.getElementById('connection-status');
     this.debugLog = document.getElementById('debug-log');
     this.playBtn = document.getElementById('play-btn') as HTMLButtonElement;
@@ -105,8 +112,12 @@ class WebsocketClientApp {
   private setupEventListeners(): void {
     this.connectBtn?.addEventListener('click', () => this.connect());
     this.disconnectBtn?.addEventListener('click', () => this.disconnect());
-    this.playBtn?.addEventListener('click', () => this.startSendingRecordedAudio());
-    this.stopBtn?.addEventListener('click', () => this.stopSendingRecordedAudio());
+    this.playBtn?.addEventListener('click', () =>
+      this.startSendingRecordedAudio()
+    );
+    this.stopBtn?.addEventListener('click', () =>
+      this.stopSendingRecordedAudio()
+    );
   }
 
   /**
@@ -165,7 +176,9 @@ class WebsocketClientApp {
 
     // Listen for tracks stopping
     this.rtviClient.on(RTVIEvent.TrackStopped, (track, participant) => {
-      this.log(`Track stopped: ${track.kind} from ${participant?.name || 'unknown'}`);
+      this.log(
+        `Track stopped: ${track.kind} from ${participant?.name || 'unknown'}`
+      );
     });
   }
 
@@ -175,7 +188,10 @@ class WebsocketClientApp {
    */
   private setupAudioTrack(track: MediaStreamTrack): void {
     this.log('Setting up audio track');
-    if (this.botAudio.srcObject && "getAudioTracks" in this.botAudio.srcObject) {
+    if (
+      this.botAudio.srcObject &&
+      'getAudioTracks' in this.botAudio.srcObject
+    ) {
       const oldTrack = this.botAudio.srcObject.getAudioTracks()[0];
       if (oldTrack?.id === track.id) return;
     }
@@ -190,17 +206,17 @@ class WebsocketClientApp {
     try {
       const startTime = Date.now();
 
-      this.recordingSerializer = new RecordingSerializer()
-      const transport = this.ENABLE_RECORDING_MODE ? new WebSocketTransport({serializer: this.recordingSerializer}) : new WebSocketTransport();
-      this.websocketTransport = transport
+      this.recordingSerializer = new RecordingSerializer();
+      const ws_opts = {
+        serializer: this.ENABLE_RECORDING_MODE
+          ? this.recordingSerializer
+          : new ProtobufFrameSerializer(),
+        recorderSampleRate: 8000,
+        playerSampleRate: 8000,
+      };
 
       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' },
-        },
+        transport: new WebSocketTransport(ws_opts),
         enableMic: true,
         enableCam: false,
         callbacks: {
@@ -228,27 +244,34 @@ class WebsocketClientApp {
           onMessageError: (error) => console.error('Message error:', error),
           onError: (error) => console.error('Error:', error),
         },
-      }
+      };
       this.rtviClient = new RTVIClient(RTVIConfig);
+      this.websocketTransport = this.rtviClient.transport;
       this.setupTrackListeners();
 
       this.log('Initializing devices...');
       await this.rtviClient.initDevices();
 
       this.log('Connecting to bot...');
-      await this.rtviClient.connect();
+      await this.rtviClient.connect({
+        endpoint: 'http://localhost:7860/connect',
+      });
 
       const timeTaken = Date.now() - startTime;
       this.log(`Connection complete, timeTaken: ${timeTaken}`);
 
       if (this.ENABLE_RECORDING_MODE) {
-        this.log(`Starting to recording the next ${(this.RECORDING_TIME_MS/1000)}s of audio`);
-        this.recordingSerializer.startRecording()
-        await this.sleep(this.RECORDING_TIME_MS)
-        this.recordingSerializer.stopRecording()
-        this.log("Recording stopped");
-        this.rtviClient.enableMic(false)
-        this.startSendingRecordedAudio()
+        this.log(
+          `Starting to recording the next ${
+            this.RECORDING_TIME_MS / 1000
+          }s of audio`
+        );
+        this.recordingSerializer.startRecording();
+        await this.sleep(this.RECORDING_TIME_MS);
+        this.recordingSerializer.stopRecording();
+        this.log('Recording stopped');
+        this.rtviClient.enableMic(false);
+        this.startSendingRecordedAudio();
       }
     } catch (error) {
       this.log(`Error connecting: ${(error as Error).message}`);
@@ -270,11 +293,16 @@ class WebsocketClientApp {
   public async disconnect(): Promise<void> {
     if (this.rtviClient) {
       try {
-        this.stopSendingRecordedAudio()
+        this.stopSendingRecordedAudio();
         await this.rtviClient.disconnect();
         this.rtviClient = null;
-        if (this.botAudio.srcObject && "getAudioTracks" in this.botAudio.srcObject) {
-          this.botAudio.srcObject.getAudioTracks().forEach((track) => track.stop());
+        if (
+          this.botAudio.srcObject &&
+          'getAudioTracks' in this.botAudio.srcObject
+        ) {
+          this.botAudio.srcObject
+            .getAudioTracks()
+            .forEach((track) => track.stop());
           this.botAudio.srcObject = null;
         }
       } catch (error) {
@@ -284,21 +312,21 @@ class WebsocketClientApp {
   }
 
   private startSendingRecordedAudio() {
-    this.sendRecordedAudio = true
+    this.sendRecordedAudio = true;
     if (this.playBtn) this.playBtn.disabled = true;
     if (this.stopBtn) this.stopBtn.disabled = false;
-    void this.replayAudio()
+    void this.replayAudio();
   }
 
   private stopSendingRecordedAudio() {
     if (this.stopBtn) this.stopBtn.disabled = true;
     if (this.playBtn) this.playBtn.disabled = false;
-    this.sendRecordedAudio = false
+    this.sendRecordedAudio = false;
   }
 
   private async replayAudio() {
     if (this.sendRecordedAudio) {
-      this.log("Sending recorded audio")
+      this.log('Sending recorded audio');
       for (const chunk of this.recordingSerializer.recordedAudio) {
         await this.sleep(chunk.delay);
         this.websocketTransport.handleUserAudioStream(chunk.data);
@@ -306,14 +334,13 @@ class WebsocketClientApp {
       const randomDelay = 1000 + Math.random() * (10000 - 500);
       await this.sleep(randomDelay);
 
-      void this.replayAudio()
+      void this.replayAudio();
     }
   }
 
   private sleep(ms: number): Promise<void> {
-    return new Promise(resolve => setTimeout(resolve, ms));
+    return new Promise((resolve) => setTimeout(resolve, ms));
   }
-
 }
 
 declare global {

examples/freeze-test/env.example

@@ -0,0 +1,4 @@
+SENTRY_DSN=
+DEEPGRAM_API_KEY=
+CARTESIA_API_KEY=
+OPENAI_API_KEY=

examples/freeze-test/freeze_test_bot.py

@@ -18,7 +18,6 @@ from fastapi import FastAPI, Request, WebSocket
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import RedirectResponse
 from loguru import logger
-from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import (
@@ -27,11 +26,13 @@ from pipecat.frames.frames import (
     Frame,
     InterimTranscriptionFrame,
     LLMFullResponseEndFrame,
+    LLMMessagesFrame,
     StartFrame,
     StartInterruptionFrame,
     StopFrame,
     StopInterruptionFrame,
     TranscriptionFrame,
+    TTSSpeakFrame,
     UserStartedSpeakingFrame,
     UserStoppedSpeakingFrame,
 )
@@ -47,6 +48,7 @@ from pipecat.processors.aggregators.openai_llm_context import (
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIProcessor
 from pipecat.processors.metrics.sentry import SentryMetrics
+from pipecat.processors.user_idle_processor import UserIdleProcessor
 from pipecat.serializers.protobuf import ProtobufFrameSerializer
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -78,9 +80,6 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-# Mount the frontend at /
-app.mount("/client", SmallWebRTCPrebuiltUI)
-
 
 class SimulateFreezeInput(FrameProcessor):
     def __init__(
@@ -188,6 +187,37 @@ async def run_example(websocket_client):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
+    async def handle_user_idle(user_idle: UserIdleProcessor, retry_count: int) -> bool:
+        if retry_count == 1:
+            # First attempt: Add a gentle prompt to the conversation
+            messages.append(
+                {
+                    "role": "system",
+                    "content": "The user has been quiet. Politely and briefly ask if they're still there.",
+                }
+            )
+            await user_idle.push_frame(LLMMessagesFrame(messages))
+            return True
+        elif retry_count == 2:
+            # Second attempt: More direct prompt
+            messages.append(
+                {
+                    "role": "system",
+                    "content": "The user is still inactive. Ask if they'd like to continue our conversation.",
+                }
+            )
+            await user_idle.push_frame(LLMMessagesFrame(messages))
+            return True
+        else:
+            # Third attempt: End the conversation
+            await user_idle.push_frame(
+                TTSSpeakFrame("It seems like you're busy right now. Have a nice day!")
+            )
+            await task.queue_frame(EndFrame())
+            return False
+
+    user_idle = UserIdleProcessor(callback=handle_user_idle, timeout=10.0)
+
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
@@ -222,6 +252,7 @@ async def run_example(websocket_client):
                     stt,
                 ],
             ),
+            user_idle,
             rtvi,
             context_aggregator.user(),  # User responses
             llm,  # LLM
@@ -238,6 +269,8 @@ async def run_example(websocket_client):
             enable_metrics=True,
             enable_usage_metrics=True,
             report_only_initial_ttfb=True,
+            audio_in_sample_rate=8000,
+            audio_out_sample_rate=8000,
         ),
         idle_timeout_secs=120,
         observers=[
@@ -249,6 +282,10 @@ async def run_example(websocket_client):
                     # LLMTextFrame: None,
                     OpenAILLMContextFrame: None,
                     LLMFullResponseEndFrame: None,
+                    UserStartedSpeakingFrame: None,
+                    UserStoppedSpeakingFrame: None,
+                    StartInterruptionFrame: None,
+                    StopInterruptionFrame: None,
                 },
                 exclude_fields={
                     "result",

examples/freeze-test/requirements.txt

@@ -0,0 +1,4 @@
+python-dotenv
+fastapi[all]
+uvicorn
+pipecat-ai[silero,websocket,openai, deepgram, cartesia, sentry]

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

@@ -18,7 +18,7 @@
     "vite": "^6.3.5"
   },
   "dependencies": {
-    "@pipecat-ai/client-js": "^0.3.5",
-    "@pipecat-ai/daily-transport": "^0.3.8"
+    "@pipecat-ai/client-js": "^1.0.0",
+    "@pipecat-ai/daily-transport": "^1.0.0"
   }
 }

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

@@ -5,7 +5,7 @@
  */
 
 /**
- * RTVI Client Implementation
+ * Pipecat 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.
@@ -18,20 +18,22 @@
 
 import {
   Participant,
-  RTVIClient,
-  RTVIClientOptions,
+  PipecatClient,
+  PipecatClientOptions,
   RTVIEvent,
 } from '@pipecat-ai/client-js';
-import { DailyTransport } from '@pipecat-ai/daily-transport';
+import {
+  DailyEventCallbacks,
+  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 declare pcClient: PipecatClient;
   private connectBtn: HTMLButtonElement | null = null;
   private disconnectBtn: HTMLButtonElement | null = null;
   private statusSpan: HTMLElement | null = null;
@@ -46,7 +48,7 @@ class InstantVoiceClient {
     document.body.appendChild(this.botAudio);
     this.setupDOMElements();
     this.setupEventListeners();
-    this.initializeRTVIClient();
+    this.initializePipecatClient();
   }
 
   /**
@@ -72,16 +74,11 @@ class InstantVoiceClient {
     this.disconnectBtn?.addEventListener('click', () => this.disconnect());
   }
 
-  private initializeRTVIClient(): void {
-    const RTVIConfig: RTVIClientOptions = {
+  private initializePipecatClient(): void {
+    const PipecatConfig: PipecatClientOptions = {
       transport: new DailyTransport({
         bufferLocalAudioUntilBotReady: true,
       }),
-      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: {
@@ -113,30 +110,23 @@ class InstantVoiceClient {
         onBotTranscript: (data) => this.log(`Bot: ${data.text}`),
         onMessageError: (error) => console.error('Message error:', error),
         onError: (error) => console.error('Error:', error),
-      },
+        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}`
+          );
+        },
+      } as DailyEventCallbacks,
     };
 
-    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.pcClient = new PipecatClient(PipecatConfig);
     this.setupTrackListeners();
   }
 
@@ -182,8 +172,8 @@ class InstantVoiceClient {
    * 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 (!this.pcClient) return;
+    const tracks = this.pcClient.tracks();
     if (tracks.bot?.audio) {
       this.setupAudioTrack(tracks.bot.audio);
     }
@@ -194,10 +184,10 @@ class InstantVoiceClient {
    * This handles new tracks being added during the session
    */
   setupTrackListeners() {
-    if (!this.rtviClient) return;
+    if (!this.pcClient) return;
 
     // Listen for new tracks starting
-    this.rtviClient.on(RTVIEvent.TrackStarted, (track, participant) => {
+    this.pcClient.on(RTVIEvent.TrackStarted, (track, participant) => {
       // Only handle non-local (bot) tracks
       if (!participant?.local && track.kind === 'audio') {
         this.setupAudioTrack(track);
@@ -205,7 +195,7 @@ class InstantVoiceClient {
     });
 
     // Listen for tracks stopping
-    this.rtviClient.on(RTVIEvent.TrackStopped, (track, participant) => {
+    this.pcClient.on(RTVIEvent.TrackStopped, (track, participant) => {
       this.log(
         `Track stopped: ${track.kind} from ${participant?.name || 'unknown'}`
       );
@@ -230,22 +220,25 @@ class InstantVoiceClient {
 
   /**
    * Initialize and connect to the bot
-   * This sets up the RTVI client, initializes devices, and establishes the connection
+   * This sets up the Pipecat 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();
+      await this.pcClient.connect({
+        // The baseURL and endpoint of your bot server that the client will connect to
+        endpoint: 'http://localhost:7860/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) {
+      if (this.pcClient) {
         try {
-          await this.rtviClient.disconnect();
+          await this.pcClient.disconnect();
         } catch (disconnectError) {
           this.log(`Error during disconnect: ${disconnectError}`);
         }
@@ -258,7 +251,7 @@ class InstantVoiceClient {
    */
   public async disconnect(): Promise<void> {
     try {
-      await this.rtviClient.disconnect();
+      await this.pcClient.disconnect();
       if (
         this.botAudio.srcObject &&
         'getAudioTracks' in this.botAudio.srcObject

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

@@ -1,39 +0,0 @@
-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/news-chatbot/client/javascript/package.json

@@ -15,7 +15,7 @@
     "vite": "^6.3.5"
   },
   "dependencies": {
-    "@pipecat-ai/client-js": "^0.3.5",
-    "@pipecat-ai/daily-transport": "^0.3.8"
+    "@pipecat-ai/client-js": "^1.0.0",
+    "@pipecat-ai/daily-transport": "^1.0.0"
   }
 }

examples/news-chatbot/client/javascript/src/app.js

@@ -5,7 +5,7 @@
  */
 
 /**
- * RTVI Client Implementation
+ * Pipecat 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.
@@ -16,78 +16,9 @@
  * - Browser with WebRTC support
  */
 
-import {
-  LogLevel,
-  RTVIClient,
-  RTVIClientHelper,
-  RTVIEvent,
-} from '@pipecat-ai/client-js';
+import { LogLevel, PipecatClient, RTVIEvent } from '@pipecat-ai/client-js';
 import { DailyTransport } from '@pipecat-ai/daily-transport';
 
-class SearchResponseHelper extends RTVIClientHelper {
-  constructor(contentPanel) {
-    super();
-    this.contentPanel = contentPanel;
-  }
-
-  handleMessage(rtviMessage) {
-    console.log('SearchResponseHelper, received message:', rtviMessage);
-    if (rtviMessage.data) {
-      // Clear existing content
-      this.contentPanel.innerHTML = '';
-
-      // Create a container for all content
-      const contentContainer = document.createElement('div');
-      contentContainer.className = 'content-container';
-
-      // Add the search_result
-      if (rtviMessage.data.search_result) {
-        const searchResultDiv = document.createElement('div');
-        searchResultDiv.className = 'search-result';
-        searchResultDiv.textContent = rtviMessage.data.search_result;
-        contentContainer.appendChild(searchResultDiv);
-      }
-
-      // Add the sources
-      if (rtviMessage.data.origins) {
-        const sourcesDiv = document.createElement('div');
-        sourcesDiv.className = 'sources';
-
-        const sourcesTitle = document.createElement('h3');
-        sourcesTitle.className = 'sources-title';
-        sourcesTitle.textContent = 'Sources:';
-        sourcesDiv.appendChild(sourcesTitle);
-
-        rtviMessage.data.origins.forEach((origin) => {
-          const sourceLink = document.createElement('a');
-          sourceLink.className = 'source-link';
-          sourceLink.href = origin.site_uri;
-          sourceLink.target = '_blank';
-          sourceLink.textContent = origin.site_title;
-          sourcesDiv.appendChild(sourceLink);
-        });
-
-        contentContainer.appendChild(sourcesDiv);
-      }
-
-      // Add the rendered_content in an iframe
-      if (rtviMessage.data.rendered_content) {
-        const iframe = document.createElement('iframe');
-        iframe.className = 'iframe-container';
-        iframe.srcdoc = rtviMessage.data.rendered_content;
-        contentContainer.appendChild(iframe);
-      }
-
-      // Append the content container to the content panel
-      this.contentPanel.appendChild(contentContainer);
-    }
-  }
-
-  getMessageTypes() {
-    return ['bot-llm-search-response'];
-  }
-}
-
 /**
  * ChatbotClient handles the connection and media management for a real-time
  * voice and video interaction with an AI bot.
@@ -95,7 +26,7 @@ class SearchResponseHelper extends RTVIClientHelper {
 class ChatbotClient {
   constructor() {
     // Initialize client state
-    this.rtviClient = null;
+    this.pcClient = null;
     this.setupDOMElements();
     this.setupEventListeners();
   }
@@ -160,10 +91,10 @@ class ChatbotClient {
    * This is called when the bot is ready or when the transport state changes to ready
    */
   setupMediaTracks() {
-    if (!this.rtviClient) return;
+    if (!this.pcClient) return;
 
     // Get current tracks from the client
-    const tracks = this.rtviClient.tracks();
+    const tracks = this.pcClient.tracks();
 
     // Set up any available bot tracks
     if (tracks.bot?.audio) {
@@ -176,10 +107,10 @@ class ChatbotClient {
    * This handles new tracks being added during the session
    */
   setupTrackListeners() {
-    if (!this.rtviClient) return;
+    if (!this.pcClient) return;
 
     // Listen for new tracks starting
-    this.rtviClient.on(RTVIEvent.TrackStarted, (track, participant) => {
+    this.pcClient.on(RTVIEvent.TrackStarted, (track, participant) => {
       // Only handle non-local (bot) tracks
       if (!participant?.local && track.kind === 'audio') {
         this.setupAudioTrack(track);
@@ -187,7 +118,7 @@ class ChatbotClient {
     });
 
     // Listen for tracks stopping
-    this.rtviClient.on(RTVIEvent.TrackStopped, (track, participant) => {
+    this.pcClient.on(RTVIEvent.TrackStopped, (track, participant) => {
       this.log(
         `Track stopped event: ${track.kind} from ${
           participant?.name || 'unknown'
@@ -213,20 +144,13 @@ class ChatbotClient {
 
   /**
    * Initialize and connect to the bot
-   * This sets up the RTVI client, initializes devices, and establishes the connection
+   * This sets up the Pipecat client, initializes devices, and establishes the connection
    */
   async connect() {
     try {
-      // Initialize the RTVI client with a Daily WebRTC transport and our configuration
-      this.rtviClient = new RTVIClient({
+      // Initialize the Pipecat client with a Daily WebRTC transport and our configuration
+      this.pcClient = new PipecatClient({
         transport: new DailyTransport(),
-        params: {
-          // The baseURL and endpoint of your bot server that the client will connect to
-          baseUrl: 'http://localhost:7860',
-          endpoints: {
-            connect: '/connect',
-          },
-        },
         enableMic: true, // Enable microphone for user input
         enableCam: false,
         callbacks: {
@@ -251,6 +175,8 @@ class ChatbotClient {
               this.setupMediaTracks();
             }
           },
+          // Handle search response events
+          onBotLlmSearchResponse: this.handleSearchResponse.bind(this),
           // Handle bot connection events
           onBotConnected: (participant) => {
             this.log(`Bot connected: ${JSON.stringify(participant)}`);
@@ -281,22 +207,22 @@ class ChatbotClient {
           },
         },
       });
-      //this.rtviClient.setLogLevel(LogLevel.DEBUG)
-      this.rtviClient.registerHelper(
-        'llm',
-        new SearchResponseHelper(this.searchResultContainer)
-      );
+
+      //this.pcClient.setLogLevel(LogLevel.DEBUG)
 
       // Set up listeners for media track events
       this.setupTrackListeners();
 
       // Initialize audio devices
       this.log('Initializing devices...');
-      await this.rtviClient.initDevices();
+      await this.pcClient.initDevices();
 
       // Connect to the bot
       this.log('Connecting to bot...');
-      await this.rtviClient.connect();
+      await this.pcClient.connect({
+        // The baseURL and endpoint of your bot server that the client will connect to
+        endpoint: 'http://localhost:7860/connect',
+      });
 
       this.log('Connection complete');
     } catch (error) {
@@ -306,9 +232,9 @@ class ChatbotClient {
       this.updateStatus('Error');
 
       // Clean up if there's an error
-      if (this.rtviClient) {
+      if (this.pcClient) {
         try {
-          await this.rtviClient.disconnect();
+          await this.pcClient.disconnect();
         } catch (disconnectError) {
           this.log(`Error during disconnect: ${disconnectError.message}`);
         }
@@ -320,11 +246,11 @@ class ChatbotClient {
    * Disconnect from the bot and clean up media resources
    */
   async disconnect() {
-    if (this.rtviClient) {
+    if (this.pcClient) {
       try {
-        // Disconnect the RTVI client
-        await this.rtviClient.disconnect();
-        this.rtviClient = null;
+        // Disconnect the Pipecat client
+        await this.pcClient.disconnect();
+        this.pcClient = null;
 
         // Clean up audio
         if (this.botAudio.srcObject) {
@@ -339,6 +265,57 @@ class ChatbotClient {
       }
     }
   }
+
+  handleSearchResponse(response) {
+    console.log('SearchResponseHelper, received message:', response);
+    // Clear existing content
+    this.searchResultContainer.innerHTML = '';
+
+    // Create a container for all content
+    const contentContainer = document.createElement('div');
+    contentContainer.className = 'content-container';
+
+    // Add the search_result
+    if (response.search_result) {
+      const searchResultDiv = document.createElement('div');
+      searchResultDiv.className = 'search-result';
+      searchResultDiv.textContent = response.search_result;
+      contentContainer.appendChild(searchResultDiv);
+    }
+
+    // Add the sources
+    if (response.origins) {
+      const sourcesDiv = document.createElement('div');
+      sourcesDiv.className = 'sources';
+
+      const sourcesTitle = document.createElement('h3');
+      sourcesTitle.className = 'sources-title';
+      sourcesTitle.textContent = 'Sources:';
+      sourcesDiv.appendChild(sourcesTitle);
+
+      response.origins.forEach((origin) => {
+        const sourceLink = document.createElement('a');
+        sourceLink.className = 'source-link';
+        sourceLink.href = origin.site_uri;
+        sourceLink.target = '_blank';
+        sourceLink.textContent = origin.site_title;
+        sourcesDiv.appendChild(sourceLink);
+      });
+
+      contentContainer.appendChild(sourcesDiv);
+    }
+
+    // Add the rendered_content in an iframe
+    if (response.rendered_content) {
+      const iframe = document.createElement('iframe');
+      iframe.className = 'iframe-container';
+      iframe.srcdoc = response.rendered_content;
+      contentContainer.appendChild(iframe);
+    }
+
+    // Append the content container to the content panel
+    this.searchResultContainer.appendChild(contentContainer);
+  }
 }
 
 // Initialize the client when the page loads

examples/open-telemetry/jaeger/bot.py

@@ -24,6 +24,7 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.llm_service import FunctionCallParams
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
 from pipecat.transports.services.daily import DailyParams
 from pipecat.utils.tracing.setup import setup_tracing
 
@@ -61,7 +62,7 @@ transport_params = {
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(),
     ),
-    "twilio": lambda: TransportParams(
+    "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(),

examples/open-telemetry/jaeger/requirements.txt

@@ -1,6 +1,6 @@
 fastapi
 uvicorn
 python-dotenv
-pipecat-ai[webrtc,silero,cartesia,deepgram,openai,tracing]
+pipecat-ai[daily,webrtc,silero,cartesia,deepgram,openai,tracing]
 pipecat-ai-small-webrtc-prebuilt
 opentelemetry-exporter-otlp-proto-grpc

examples/open-telemetry/langfuse/README.md

@@ -26,7 +26,7 @@ Create a `.env` file with your API keys to enable tracing:
 ```
 ENABLE_TRACING=true
 # OTLP endpoint for Langfuse
-OTEL_EXPORTER_OTLP_ENDPOINT=http://cloud.langfuse.com/api/public/otel
+OTEL_EXPORTER_OTLP_ENDPOINT=https://cloud.langfuse.com/api/public/otel
 OTEL_EXPORTER_OTLP_HEADERS=Authorization=Basic%20<base64_encoded_api_key>
 # Set to any value to enable console output for debugging
 # OTEL_CONSOLE_EXPORT=true

examples/open-telemetry/langfuse/bot.py

@@ -24,6 +24,7 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.llm_service import FunctionCallParams
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
 from pipecat.transports.services.daily import DailyParams
 from pipecat.utils.tracing.setup import setup_tracing
 
@@ -58,7 +59,7 @@ transport_params = {
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(),
     ),
-    "twilio": lambda: TransportParams(
+    "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(),

examples/open-telemetry/langfuse/requirements.txt

@@ -1,6 +1,6 @@
 fastapi
 uvicorn
 python-dotenv
-pipecat-ai[webrtc,silero,cartesia,deepgram,openai,tracing]
+pipecat-ai[daily,webrtc,silero,cartesia,deepgram,openai,tracing]
 pipecat-ai-small-webrtc-prebuilt
 opentelemetry-exporter-otlp-proto-http

examples/p2p-webrtc/video-transform/client/typescript/package.json

@@ -18,7 +18,7 @@
     "vite": "^6.3.5"
   },
   "dependencies": {
-    "@pipecat-ai/client-js": "^0.3.2",
-    "@pipecat-ai/small-webrtc-transport": "^0.0.2"
+    "@pipecat-ai/client-js": "^1.0.0",
+    "@pipecat-ai/small-webrtc-transport": "^1.0.0"
   }
 }

examples/p2p-webrtc/video-transform/client/typescript/src/app.ts

@@ -1,217 +1,236 @@
+import { SmallWebRTCTransport } from '@pipecat-ai/small-webrtc-transport';
 import {
-    SmallWebRTCTransport
-} from "@pipecat-ai/small-webrtc-transport";
-import {Participant, RTVIClient, RTVIClientOptions, Transport} from "@pipecat-ai/client-js";
+  BotLLMTextData,
+  Participant,
+  PipecatClient,
+  PipecatClientOptions,
+  TranscriptData,
+  TransportState,
+} from '@pipecat-ai/client-js';
 
 class WebRTCApp {
+  private declare connectBtn: HTMLButtonElement;
+  private declare disconnectBtn: HTMLButtonElement;
+  private declare muteBtn: HTMLButtonElement;
 
-    private declare connectBtn: HTMLButtonElement;
-    private declare disconnectBtn: HTMLButtonElement;
-    private declare muteBtn: HTMLButtonElement;
+  private declare audioInput: HTMLSelectElement;
+  private declare videoInput: HTMLSelectElement;
+  private declare audioCodec: HTMLSelectElement;
+  private declare videoCodec: HTMLSelectElement;
 
-    private declare audioInput: HTMLSelectElement;
-    private declare videoInput: HTMLSelectElement;
-    private declare audioCodec: HTMLSelectElement;
-    private declare videoCodec: HTMLSelectElement;
+  private declare videoElement: HTMLVideoElement;
+  private declare audioElement: HTMLAudioElement;
 
-    private declare videoElement: HTMLVideoElement;
-    private declare audioElement: HTMLAudioElement;
+  private debugLog: HTMLElement | null = null;
+  private statusSpan: HTMLElement | null = null;
 
-    private debugLog: HTMLElement | null = null;
-    private statusSpan: HTMLElement | null = null;
+  private declare smallWebRTCTransport: SmallWebRTCTransport;
+  private declare pcClient: PipecatClient;
 
-    private declare smallWebRTCTransport: SmallWebRTCTransport;
-    private declare rtviClient: RTVIClient;
+  constructor() {
+    this.setupDOMElements();
+    this.setupDOMEventListeners();
+    this.initializePipecatClient();
+    void this.populateDevices();
+  }
 
-    constructor() {
-        this.setupDOMElements();
-        this.setupDOMEventListeners();
-        this.initializeRTVIClient()
-        void this.populateDevices();
+  private initializePipecatClient(): void {
+    const opts: PipecatClientOptions = {
+      transport: new SmallWebRTCTransport({ connectionUrl: '/api/offer' }),
+      enableMic: true,
+      enableCam: true,
+      callbacks: {
+        onTransportStateChanged: (state: TransportState) => {
+          this.log(`Transport state: ${state}`);
+        },
+        onConnected: () => {
+          this.onConnectedHandler();
+        },
+        onBotReady: () => {
+          this.log('Bot is ready.');
+        },
+        onDisconnected: () => {
+          this.onDisconnectedHandler();
+        },
+        onUserStartedSpeaking: () => {
+          this.log('User started speaking.');
+        },
+        onUserStoppedSpeaking: () => {
+          this.log('User stopped speaking.');
+        },
+        onBotStartedSpeaking: () => {
+          this.log('Bot started speaking.');
+        },
+        onBotStoppedSpeaking: () => {
+          this.log('Bot stopped speaking.');
+        },
+        onUserTranscript: (transcript: TranscriptData) => {
+          if (transcript.final) {
+            this.log(`User transcript: ${transcript.text}`);
+          }
+        },
+        onBotTranscript: (data: BotLLMTextData) => {
+          this.log(`Bot transcript: ${data.text}`);
+        },
+        onTrackStarted: (
+          track: MediaStreamTrack,
+          participant?: Participant
+        ) => {
+          if (participant?.local) {
+            return;
+          }
+          this.onBotTrackStarted(track);
+        },
+        onServerMessage: (msg: unknown) => {
+          this.log(`Server message: ${msg}`);
+        },
+      },
+    };
+    this.pcClient = new PipecatClient(opts);
+    this.smallWebRTCTransport = this.pcClient.transport as SmallWebRTCTransport;
+  }
+
+  private setupDOMElements(): void {
+    this.connectBtn = document.getElementById(
+      'connect-btn'
+    ) as HTMLButtonElement;
+    this.disconnectBtn = document.getElementById(
+      'disconnect-btn'
+    ) as HTMLButtonElement;
+    this.muteBtn = document.getElementById('mute-btn') as HTMLButtonElement;
+
+    this.audioInput = document.getElementById(
+      'audio-input'
+    ) as HTMLSelectElement;
+    this.videoInput = document.getElementById(
+      'video-input'
+    ) as HTMLSelectElement;
+    this.audioCodec = document.getElementById(
+      'audio-codec'
+    ) as HTMLSelectElement;
+    this.videoCodec = document.getElementById(
+      'video-codec'
+    ) as HTMLSelectElement;
+
+    this.videoElement = document.getElementById(
+      'bot-video'
+    ) as HTMLVideoElement;
+    this.audioElement = document.getElementById(
+      'bot-audio'
+    ) as HTMLAudioElement;
+
+    this.debugLog = document.getElementById('debug-log');
+    this.statusSpan = document.getElementById('connection-status');
+  }
+
+  private setupDOMEventListeners(): void {
+    this.connectBtn.addEventListener('click', () => this.start());
+    this.disconnectBtn.addEventListener('click', () => this.stop());
+    this.audioInput.addEventListener('change', (e) => {
+      // @ts-ignore
+      let audioDevice = e.target?.value;
+      this.pcClient.updateMic(audioDevice);
+    });
+    this.videoInput.addEventListener('change', (e) => {
+      // @ts-ignore
+      let videoDevice = e.target?.value;
+      this.pcClient.updateCam(videoDevice);
+    });
+    this.muteBtn.addEventListener('click', () => {
+      let isCamEnabled = this.pcClient.isCamEnabled;
+      this.pcClient.enableCam(!isCamEnabled);
+      this.muteBtn.textContent = isCamEnabled ? '📵' : '📷';
+    });
+  }
+
+  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;
+  }
 
-    private initializeRTVIClient(): void {
-        const transport = new SmallWebRTCTransport();
-        const RTVIConfig: RTVIClientOptions = {
-            params: {
-                baseUrl: "/api/offer"
-            },
-            transport: transport as Transport,
-            enableMic: true,
-            enableCam: true,
-            callbacks: {
-                onTransportStateChanged: (state) => {
-                    this.log(`Transport state: ${state}`)
-                },
-                onConnected: () => {
-                    this.onConnectedHandler()
-                },
-                onBotReady: () => {
-                    this.log("Bot is ready.")
-                },
-                onDisconnected: () => {
-                    this.onDisconnectedHandler()
-                },
-                onUserStartedSpeaking: () => {
-                    this.log("User started speaking.")
-                },
-                onUserStoppedSpeaking: () => {
-                    this.log("User stopped speaking.")
-                },
-                onBotStartedSpeaking: () => {
-                    this.log("Bot started speaking.")
-                },
-                onBotStoppedSpeaking: () => {
-                    this.log("Bot stopped speaking.")
-                },
-                onUserTranscript: (transcript) => {
-                    if (transcript.final) {
-                        this.log(`User transcript: ${transcript.text}`)
-                    }
-                },
-                onBotTranscript: (transcript) => {
-                    this.log(`Bot transcript: ${transcript.text}`)
-                },
-                onTrackStarted: (track: MediaStreamTrack, participant?: Participant) => {
-                    if (participant?.local) {
-                        return
-                    }
-                    this.onBotTrackStarted(track)
-                },
-                onServerMessage: (msg) => {
-                    this.log(`Server message: ${msg}`)
-                }
-            },
-        }
-        RTVIConfig.customConnectHandler = () => Promise.resolve();
-        this.rtviClient = new RTVIClient(RTVIConfig);
-        this.smallWebRTCTransport = transport
+  private clearAllLogs() {
+    this.debugLog!.innerText = '';
+  }
+
+  private updateStatus(status: string): void {
+    if (this.statusSpan) {
+      this.statusSpan.textContent = status;
     }
+    this.log(`Status: ${status}`);
+  }
 
-    private setupDOMElements(): void {
-        this.connectBtn = document.getElementById('connect-btn') as HTMLButtonElement;
-        this.disconnectBtn = document.getElementById('disconnect-btn') as HTMLButtonElement;
-        this.muteBtn = document.getElementById('mute-btn') as HTMLButtonElement;
+  private onConnectedHandler() {
+    this.updateStatus('Connected');
+    if (this.connectBtn) this.connectBtn.disabled = true;
+    if (this.disconnectBtn) this.disconnectBtn.disabled = false;
+  }
 
-        this.audioInput = document.getElementById('audio-input') as HTMLSelectElement;
-        this.videoInput = document.getElementById('video-input') as HTMLSelectElement;
-        this.audioCodec = document.getElementById('audio-codec') as HTMLSelectElement;
-        this.videoCodec = document.getElementById('video-codec') as HTMLSelectElement;
+  private onDisconnectedHandler() {
+    this.updateStatus('Disconnected');
+    if (this.connectBtn) this.connectBtn.disabled = false;
+    if (this.disconnectBtn) this.disconnectBtn.disabled = true;
+  }
 
-        this.videoElement = document.getElementById('bot-video') as HTMLVideoElement;
-        this.audioElement = document.getElementById('bot-audio') as HTMLAudioElement;
-
-        this.debugLog = document.getElementById('debug-log');
-        this.statusSpan = document.getElementById('connection-status');
+  private onBotTrackStarted(track: MediaStreamTrack) {
+    if (track.kind === 'video') {
+      this.videoElement.srcObject = new MediaStream([track]);
+    } else {
+      this.audioElement.srcObject = new MediaStream([track]);
     }
+  }
 
-    private setupDOMEventListeners(): void {
-        this.connectBtn.addEventListener("click", () => this.start());
-        this.disconnectBtn.addEventListener("click", () => this.stop());
-        this.audioInput.addEventListener("change", (e) => {
-            // @ts-ignore
-            let audioDevice = e.target?.value
-            this.rtviClient.updateMic(audioDevice)
-        })
-        this.videoInput.addEventListener("change", (e) => {
-            // @ts-ignore
-            let videoDevice = e.target?.value
-            this.rtviClient.updateCam(videoDevice)
-        })
-        this.muteBtn.addEventListener('click', () => {
-            let isCamEnabled = this.rtviClient.isCamEnabled
-            this.rtviClient.enableCam(!isCamEnabled)
-            this.muteBtn.textContent = isCamEnabled ? '📵' : '📷';
-        });
+  private async populateDevices(): Promise<void> {
+    const populateSelect = (
+      select: HTMLSelectElement,
+      devices: MediaDeviceInfo[]
+    ): void => {
+      let counter = 1;
+      devices.forEach((device) => {
+        const option = document.createElement('option');
+        option.value = device.deviceId;
+        option.text = device.label || 'Device #' + counter;
+        select.appendChild(option);
+        counter += 1;
+      });
+    };
 
+    try {
+      const audioDevices = await this.pcClient.getAllMics();
+      populateSelect(this.audioInput, audioDevices);
+      const videoDevices = await this.pcClient.getAllCams();
+      populateSelect(this.videoInput, videoDevices);
+    } catch (e) {
+      alert(e);
     }
+  }
 
-    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;
+  private async start(): Promise<void> {
+    this.clearAllLogs();
+
+    this.connectBtn.disabled = true;
+    this.updateStatus('Connecting');
+
+    this.smallWebRTCTransport.setAudioCodec(this.audioCodec.value);
+    this.smallWebRTCTransport.setVideoCodec(this.videoCodec.value);
+    try {
+      await this.pcClient.connect();
+    } catch (e) {
+      console.log(`Failed to connect ${e}`);
+      this.stop();
     }
+  }
 
-    private clearAllLogs() {
-        this.debugLog!.innerText = ''
-    }
-
-    private updateStatus(status: string): void {
-        if (this.statusSpan) {
-            this.statusSpan.textContent = status;
-        }
-        this.log(`Status: ${status}`);
-   }
-
-    private onConnectedHandler() {
-        this.updateStatus('Connected');
-        if (this.connectBtn) this.connectBtn.disabled = true;
-        if (this.disconnectBtn) this.disconnectBtn.disabled = false;
-    }
-
-    private onDisconnectedHandler() {
-        this.updateStatus('Disconnected');
-        if (this.connectBtn) this.connectBtn.disabled = false;
-        if (this.disconnectBtn) this.disconnectBtn.disabled = true;
-    }
-
-    private onBotTrackStarted(track: MediaStreamTrack) {
-        if (track.kind === 'video') {
-            this.videoElement.srcObject = new MediaStream([track]);
-        } else {
-            this.audioElement.srcObject = new MediaStream([track]);
-        }
-    }
-
-    private async populateDevices(): Promise<void> {
-        const populateSelect = (select: HTMLSelectElement, devices: MediaDeviceInfo[]): void => {
-            let counter = 1;
-            devices.forEach((device) => {
-                const option = document.createElement('option');
-                option.value = device.deviceId;
-                option.text = device.label || ('Device #' + counter);
-                select.appendChild(option);
-                counter += 1;
-            });
-        };
-
-        try {
-            const audioDevices = await this.rtviClient.getAllMics();
-            populateSelect(this.audioInput, audioDevices);
-            const videoDevices = await this.rtviClient.getAllCams();
-            populateSelect(this.videoInput, videoDevices);
-        } catch (e) {
-            alert(e);
-        }
-    }
-
-    private async start(): Promise<void> {
-        this.clearAllLogs()
-
-        this.connectBtn.disabled = true;
-        this.updateStatus("Connecting")
-
-        this.smallWebRTCTransport.setAudioCodec(this.audioCodec.value)
-        this.smallWebRTCTransport.setVideoCodec(this.videoCodec.value)
-        try {
-            await this.rtviClient.connect()
-        } catch (e) {
-            console.log(`Failed to connect ${e}`)
-            this.stop()
-        }
-
-    }
-
-    private stop(): void {
-        void this.rtviClient.disconnect()
-    }
+  private stop(): void {
+    void this.pcClient.disconnect();
+  }
 }
 
 // Create the WebRTCConnection instance

examples/phone-chatbot/daily-twilio-sip-dial-in/requirements.txt

@@ -1,4 +1,4 @@
-pipecat-ai[daily,elevenlabs,openai,silero]
+pipecat-ai[daily,cartesia,openai,silero]
 fastapi==0.115.6
 uvicorn
 python-dotenv

examples/simple-chatbot/client/ios/SimpleChatbot.xcodeproj/project.pbxproj

@@ -15,7 +15,6 @@
 		90031FC22C616EE900408370 /* SimpleChatbotUITests.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90031FC12C616EE900408370 /* SimpleChatbotUITests.swift */; };
 		90031FC42C616EE900408370 /* SimpleChatbotUITestsLaunchTests.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90031FC32C616EE900408370 /* SimpleChatbotUITestsLaunchTests.swift */; };
 		90031FDC2C6D5DD700408370 /* ToastModifier.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90031FDB2C6D5DD700408370 /* ToastModifier.swift */; };
-		907C98842D37E6AF0079441F /* PipecatClientIOSDaily in Frameworks */ = {isa = PBXBuildFile; productRef = 907C98832D37E6AF0079441F /* PipecatClientIOSDaily */; };
 		90ABB98E2C735ED6000D9CC7 /* MeetingView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB98D2C735ED6000D9CC7 /* MeetingView.swift */; };
 		90ABB9902C736A8B000D9CC7 /* WaveformView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB98F2C736A8B000D9CC7 /* WaveformView.swift */; };
 		90ABB9932C73820D000D9CC7 /* MicrophoneView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB9922C73820D000D9CC7 /* MicrophoneView.swift */; };
@@ -25,6 +24,8 @@
 		90ABB9A32C74E1CE000D9CC7 /* SettingsView.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB9A22C74E1CE000D9CC7 /* SettingsView.swift */; };
 		90ABB9A62C74EA8A000D9CC7 /* SettingsPreference.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB9A52C74EA8A000D9CC7 /* SettingsPreference.swift */; };
 		90ABB9A82C74EAB1000D9CC7 /* SettingsManager.swift in Sources */ = {isa = PBXBuildFile; fileRef = 90ABB9A72C74EAB1000D9CC7 /* SettingsManager.swift */; };
+		90CC98B02E158093003C2706 /* PipecatClientIOSDaily in Frameworks */ = {isa = PBXBuildFile; productRef = 90CC98AF2E158093003C2706 /* PipecatClientIOSDaily */; };
+		90CC98B62E15820B003C2706 /* PipecatClientIOSDaily in Frameworks */ = {isa = PBXBuildFile; productRef = 90CC98B52E15820B003C2706 /* PipecatClientIOSDaily */; };
 /* End PBXBuildFile section */
 
 /* Begin PBXContainerItemProxy section */
@@ -73,7 +74,8 @@
 			isa = PBXFrameworksBuildPhase;
 			buildActionMask = 2147483647;
 			files = (
-				907C98842D37E6AF0079441F /* PipecatClientIOSDaily in Frameworks */,
+				90CC98B62E15820B003C2706 /* PipecatClientIOSDaily in Frameworks */,
+				90CC98B02E158093003C2706 /* PipecatClientIOSDaily in Frameworks */,
 			);
 			runOnlyForDeploymentPostprocessing = 0;
 		};
@@ -218,7 +220,8 @@
 			);
 			name = SimpleChatbot;
 			packageProductDependencies = (
-				907C98832D37E6AF0079441F /* PipecatClientIOSDaily */,
+				90CC98AF2E158093003C2706 /* PipecatClientIOSDaily */,
+				90CC98B52E15820B003C2706 /* PipecatClientIOSDaily */,
 			);
 			productName = SimpleChatbot;
 			productReference = 90031FA32C616EE700408370 /* SimpleChatbot.app */;
@@ -293,7 +296,7 @@
 			);
 			mainGroup = 90031F9A2C616EE700408370;
 			packageReferences = (
-				907C98822D37E6AF0079441F /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */,
+				90CC98B42E15820B003C2706 /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */,
 			);
 			productRefGroup = 90031FA42C616EE700408370 /* Products */;
 			projectDirPath = "";
@@ -682,20 +685,24 @@
 /* End XCConfigurationList section */
 
 /* Begin XCRemoteSwiftPackageReference section */
-		907C98822D37E6AF0079441F /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */ = {
+		90CC98B42E15820B003C2706 /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */ = {
 			isa = XCRemoteSwiftPackageReference;
 			repositoryURL = "https://github.com/pipecat-ai/pipecat-client-ios-daily/";
 			requirement = {
 				kind = upToNextMajorVersion;
-				minimumVersion = 0.3.2;
+				minimumVersion = 0.3.6;
 			};
 		};
 /* End XCRemoteSwiftPackageReference section */
 
 /* Begin XCSwiftPackageProductDependency section */
-		907C98832D37E6AF0079441F /* PipecatClientIOSDaily */ = {
+		90CC98AF2E158093003C2706 /* PipecatClientIOSDaily */ = {
 			isa = XCSwiftPackageProductDependency;
-			package = 907C98822D37E6AF0079441F /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */;
+			productName = PipecatClientIOSDaily;
+		};
+		90CC98B52E15820B003C2706 /* PipecatClientIOSDaily */ = {
+			isa = XCSwiftPackageProductDependency;
+			package = 90CC98B42E15820B003C2706 /* XCRemoteSwiftPackageReference "pipecat-client-ios-daily" */;
 			productName = PipecatClientIOSDaily;
 		};
 /* End XCSwiftPackageProductDependency section */

examples/simple-chatbot/client/ios/SimpleChatbot.xcodeproj/project.xcworkspace/xcshareddata/swiftpm/Package.resolved

@@ -1,12 +1,13 @@
 {
+  "originHash" : "cc17f08b06def9570d775e9c6f7a8dc10d1588b98127e977c47d052abac659b7",
   "pins" : [
     {
       "identity" : "daily-client-ios",
       "kind" : "remoteSourceControl",
       "location" : "https://github.com/daily-co/daily-client-ios.git",
       "state" : {
-        "revision" : "15804ce495780da3ec2d05ab99736315f7bfbd24",
-        "version" : "0.28.0"
+        "revision" : "431938db25e5807120e89e2dc5bab1c076729f59",
+        "version" : "0.31.0"
       }
     },
     {
@@ -14,8 +15,8 @@
       "kind" : "remoteSourceControl",
       "location" : "https://github.com/pipecat-ai/pipecat-client-ios.git",
       "state" : {
-        "revision" : "c679512e367002a1a67da85d503fec72d9b17191",
-        "version" : "0.3.2"
+        "revision" : "f92b5e68e56a8311f7d8ead68a7a5674843cbc40",
+        "version" : "0.3.6"
       }
     },
     {
@@ -23,10 +24,10 @@
       "kind" : "remoteSourceControl",
       "location" : "https://github.com/pipecat-ai/pipecat-client-ios-daily/",
       "state" : {
-        "revision" : "a337fe6642c52376d2f90eafcb965f5be772ce72",
-        "version" : "0.3.2"
+        "revision" : "8f494da903192c22c367ecf9e51248c9b651fbc6",
+        "version" : "0.3.6"
       }
     }
   ],
-  "version" : 2
+  "version" : 3
 }

examples/simple-chatbot/client/ios/SimpleChatbot/model/CallContainerModel.swift

@@ -78,10 +78,11 @@ class CallContainerModel: ObservableObject {
         self.saveCredentials(backendURL: baseUrl)
     }
     
-    @MainActor
     func disconnect() {
-        self.rtviClientIOS?.disconnect(completion: nil)
-        self.rtviClientIOS?.release()
+        Task { @MainActor in
+            try await self.rtviClientIOS?.disconnect()
+            self.rtviClientIOS?.release()
+        }
     }
     
     func showError(message: String) {

examples/simple-chatbot/client/javascript/index.html

@@ -1,40 +1,51 @@
 <!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>
 
-<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">
-        Status: <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>
-
-    <div class="main-content">
-      <div class="bot-container">
-        <div id="bot-video-container">
+  <body>
+    <div class="container">
+      <div class="status-bar">
+        <div class="status">
+          Status: <span id="connection-status">Disconnected</span>
         </div>
-        <audio id="bot-audio" autoplay></audio>
+        <div class="controls">
+          <button id="connect-btn">Connect</button>
+          <button id="disconnect-btn" disabled>Disconnect</button>
+        </div>
+      </div>
+
+      <div class="main-content">
+        <div class="bot-container">
+          <div id="bot-video-container"></div>
+          <audio id="bot-audio" autoplay></audio>
+        </div>
+      </div>
+
+      <div class="device-bar">
+        <div class="device-controls">
+          <select id="device-selector"></select>
+          <button id="mic-toggle-btn">Unmute Mic</button>
+        </div>
+        <div class="text-input-container">
+          <input
+            type="text"
+            id="text-input"
+            placeholder="Type your message..." />
+          <button id="send-text-btn" disabled>Send</button>
+        </div>
+      </div>
+
+      <div class="debug-panel">
+        <h3>Debug Info</h3>
+        <div id="debug-log"></div>
       </div>
     </div>
 
-    <div class="debug-panel">
-      <h3>Debug Info</h3>
-      <div id="debug-log"></div>
-    </div>
-  </div>
-
-  <script type="module" src="/src/app.js"></script>
-  <link rel="stylesheet" href="/src/style.css">
-</body>
-
-</html>
+    <script type="module" src="/src/app.js"></script>
+    <link rel="stylesheet" href="/src/style.css" />
+  </body>
+</html>

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

@@ -15,7 +15,7 @@
     "vite": "^6.3.5"
   },
   "dependencies": {
-    "@pipecat-ai/client-js": "^0.3.5",
-    "@pipecat-ai/daily-transport": "^0.3.8"
+    "@pipecat-ai/client-js": "^1.0.0",
+    "@pipecat-ai/daily-transport": "^1.0.0"
   }
 }

examples/simple-chatbot/client/javascript/src/app.js

@@ -5,7 +5,7 @@
  */
 
 /**
- * RTVI Client Implementation
+ * Pipecat 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.
@@ -16,7 +16,7 @@
  * - Browser with WebRTC support
  */
 
-import { RTVIClient, RTVIEvent } from '@pipecat-ai/client-js';
+import { PipecatClient, RTVIEvent } from '@pipecat-ai/client-js';
 import { DailyTransport } from '@pipecat-ai/daily-transport';
 
 /**
@@ -26,9 +26,8 @@ import { DailyTransport } from '@pipecat-ai/daily-transport';
 class ChatbotClient {
   constructor() {
     // Initialize client state
-    this.rtviClient = null;
+    this.pcClient = null;
     this.setupDOMElements();
-    this.setupEventListeners();
     this.initializeClientAndTransport();
   }
 
@@ -42,6 +41,9 @@ class ChatbotClient {
     this.statusSpan = document.getElementById('connection-status');
     this.debugLog = document.getElementById('debug-log');
     this.botVideoContainer = document.getElementById('bot-video-container');
+    this.deviceSelector = document.getElementById('device-selector');
+    this.micToggleBtn = document.getElementById('mic-toggle-btn');
+    this.sendTextBtn = document.getElementById('send-text-btn');
 
     // Create an audio element for bot's voice output
     this.botAudio = document.createElement('audio');
@@ -54,25 +56,78 @@ class ChatbotClient {
    * Set up event listeners for connect/disconnect buttons
    */
   setupEventListeners() {
-    this.connectBtn.addEventListener('click', () => this.connect());
+    this.connectBtn.addEventListener('click', () => {
+      console.log('click');
+      this.connect();
+    });
     this.disconnectBtn.addEventListener('click', () => this.disconnect());
+
+    // Populate device selector
+    this.pcClient.getAllMics().then((mics) => {
+      console.log('Available mics:', mics);
+      mics.forEach((device) => {
+        const option = document.createElement('option');
+        option.value = device.deviceId;
+        option.textContent = device.label || `Microphone ${device.deviceId}`;
+        this.deviceSelector.appendChild(option);
+      });
+    });
+    this.deviceSelector.addEventListener('change', (event) => {
+      const selectedDeviceId = event.target.value;
+      console.log('Selected device ID:', selectedDeviceId);
+      this.pcClient.updateMic(selectedDeviceId);
+    });
+
+    // Handle mic mute/unmute toggle
+    const micToggleBtn = document.getElementById('mic-toggle-btn');
+
+    micToggleBtn.addEventListener('click', async () => {
+      if (this.pcClient.state === 'disconnected') {
+        await this.pcClient.initDevices();
+      } else {
+        this.pcClient.enableMic(!this.pcClient.isMicEnabled);
+      }
+    });
+
+    const textInput = document.getElementById('text-input');
+
+    const sendTextToLLM = () => {
+      this.sendTextBtn.disabled = true; // Disable button to prevent multiple clicks
+      const text = textInput.value.trim();
+      if (text) {
+        void this.pcClient.appendToContext({
+          role: 'user',
+          content: text,
+          run_immediately: true,
+        });
+      }
+      textInput.value = ''; // Clear the input
+      this.sendTextBtn.disabled = false; // Re-enable button after sending
+    };
+
+    this.sendTextBtn.addEventListener('click', sendTextToLLM);
+
+    // Also handle Enter key in the input
+    textInput.addEventListener('keypress', (e) => {
+      if (e.key === 'Enter') {
+        sendTextToLLM();
+      }
+    });
   }
 
+  updateMicToggleButton(micEnabled) {
+    console.log('Mic enabled:', micEnabled, this.pcClient?.isMicEnabled);
+    this.micToggleBtn.textContent = micEnabled ? 'Mute Mic' : 'Unmute Mic';
+  }
   /**
-   * Set up the RTVI client and Daily transport
+   * Set up the Pipecat client and Daily transport
    */
-  initializeClientAndTransport() {
-    // Initialize the RTVI client with a DailyTransport and our configuration
-    this.rtviClient = new RTVIClient({
+  async initializeClientAndTransport() {
+    console.log('Initializing Pipecat client and transport...');
+    // Initialize the Pipecat client with a DailyTransport and our configuration
+    this.pcClient = new PipecatClient({
       transport: new DailyTransport(),
-      params: {
-        // The baseURL and endpoint of your bot server that the client will connect to
-        baseUrl: 'http://localhost:7860',
-        endpoints: {
-          connect: '/connect',
-        },
-      },
-      enableMic: true, // Enable microphone for user input
+      enableMic: true,
       enableCam: false,
       callbacks: {
         // Handle connection state changes
@@ -86,7 +141,9 @@ class ChatbotClient {
           this.updateStatus('Disconnected');
           this.connectBtn.disabled = false;
           this.disconnectBtn.disabled = true;
+          this.sendTextBtn.disabled = true;
           this.log('Client disconnected');
+          this.updateMicToggleButton(false);
         },
         // Handle transport state changes
         onTransportStateChanged: (state) => {
@@ -106,6 +163,7 @@ class ChatbotClient {
         onBotReady: (data) => {
           this.log(`Bot ready: ${JSON.stringify(data)}`);
           this.setupMediaTracks();
+          this.sendTextBtn.disabled = false;
         },
         // Transcript events
         onUserTranscript: (data) => {
@@ -121,14 +179,20 @@ class ChatbotClient {
         onMessageError: (error) => {
           console.log('Message error:', error);
         },
+        onMicUpdated: (data) => {
+          console.log('Mic updated:', data);
+          this.deviceSelector.value = data.deviceId;
+        },
         onError: (error) => {
           console.log('Error:', JSON.stringify(error));
         },
       },
     });
+    window.client = this; // Expose client globally for debugging
 
     // Set up listeners for media track events
     this.setupTrackListeners();
+    this.setupEventListeners();
   }
 
   /**
@@ -163,10 +227,10 @@ class ChatbotClient {
    * This is called when the bot is ready or when the transport state changes to ready
    */
   setupMediaTracks() {
-    if (!this.rtviClient) return;
+    if (!this.pcClient) return;
 
     // Get current tracks from the client
-    const tracks = this.rtviClient.tracks();
+    const tracks = this.pcClient.tracks();
 
     // Set up any available bot tracks
     if (tracks.bot?.audio) {
@@ -182,27 +246,34 @@ class ChatbotClient {
    * This handles new tracks being added during the session
    */
   setupTrackListeners() {
-    if (!this.rtviClient) return;
+    if (!this.pcClient) return;
 
     // Listen for new tracks starting
-    this.rtviClient.on(RTVIEvent.TrackStarted, (track, participant) => {
-      // Only handle non-local (bot) tracks
+    this.pcClient.on(RTVIEvent.TrackStarted, (track, participant) => {
       if (!participant?.local) {
         if (track.kind === 'audio') {
           this.setupAudioTrack(track);
         } else if (track.kind === 'video') {
           this.setupVideoTrack(track);
         }
+      } else if (track.kind === 'audio') {
+        console.log(`Local audio track started: `, this.pcClient.tracks());
+        // If local audio track starts, update mic
+        this.updateMicToggleButton(true);
       }
     });
 
     // Listen for tracks stopping
-    this.rtviClient.on(RTVIEvent.TrackStopped, (track, participant) => {
+    this.pcClient.on(RTVIEvent.TrackStopped, (track, participant) => {
       this.log(
         `Track stopped event: ${track.kind} from ${
-          participant?.name || 'unknown'
+          participant ? (participant.local ? 'local' : 'bot') : 'unknown'
         }`
       );
+      if (participant?.local && track.kind === 'audio') {
+        // If local audio track stops, update mic toggle button
+        this.updateMicToggleButton(false);
+      }
     });
   }
 
@@ -251,17 +322,16 @@ class ChatbotClient {
 
   /**
    * Initialize and connect to the bot
-   * This sets up the RTVI client, initializes devices, and establishes the connection
+   * This sets up the Pipecat client, initializes devices, and establishes the connection
    */
   async connect() {
     try {
-      // Initialize audio/video devices
-      this.log('Initializing devices...');
-      await this.rtviClient.initDevices();
-
       // Connect to the bot
       this.log('Connecting to bot...');
-      await this.rtviClient.connect();
+      await this.pcClient.connect({
+        endpoint: 'http://localhost:7860/connect',
+        timeout: 25000,
+      });
 
       this.log('Connection complete');
     } catch (error) {
@@ -271,9 +341,9 @@ class ChatbotClient {
       this.updateStatus('Error');
 
       // Clean up if there's an error
-      if (this.rtviClient) {
+      if (this.pcClient) {
         try {
-          await this.rtviClient.disconnect();
+          await this.pcClient.disconnect();
         } catch (disconnectError) {
           this.log(`Error during disconnect: ${disconnectError.message}`);
         }
@@ -285,10 +355,10 @@ class ChatbotClient {
    * Disconnect from the bot and clean up media resources
    */
   async disconnect() {
-    if (this.rtviClient) {
+    if (this.pcClient) {
       try {
-        // Disconnect the RTVI client
-        await this.rtviClient.disconnect();
+        // Disconnect the Pipecat client
+        await this.pcClient.disconnect();
 
         // Clean up audio
         if (this.botAudio.srcObject) {

examples/simple-chatbot/client/javascript/src/style.css

@@ -10,7 +10,8 @@ body {
   margin: 0 auto;
 }
 
-.status-bar {
+.status-bar,
+.device-bar {
   display: flex;
   justify-content: space-between;
   align-items: center;
@@ -20,7 +21,24 @@ body {
   margin-bottom: 20px;
 }
 
-.controls button {
+.device-bar {
+  flex-direction: column;
+  gap: 10px;
+}
+
+.controls,
+.device-controls {
+  display: flex;
+  align-items: center;
+  gap: 10px; /* Adds spacing between elements */
+}
+
+.device-controls {
+  margin-left: auto;
+}
+
+.controls button,
+.device-controls button {
   padding: 8px 16px;
   margin-left: 10px;
   border: none;
@@ -28,6 +46,56 @@ body {
   cursor: pointer;
 }
 
+#bot-selector,
+#device-selector {
+  padding: 8px 16px;
+  padding-right: 40px;
+  border: none;
+  border-radius: 4px;
+  background-color: #6c757d; /* Gray background */
+  color: white; /* White text */
+  cursor: pointer;
+  appearance: none; /* Removes default browser styling for dropdowns */
+  background-image: url("data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 24 24' fill='white'%3E%3Cpath d='M7 10l5 5 5-5z'/%3E%3C/svg%3E"); /* Custom arrow */
+  background-repeat: no-repeat;
+  background-position: right 8px center; /* Position the arrow */
+}
+
+#bot-selector:focus,
+#device-selector:focus {
+  outline: none;
+  box-shadow: 0 0 4px rgba(0, 0, 0, 0.3); /* Add a subtle focus effect */
+}
+
+.text-input-container {
+  display: flex;
+  gap: 8px;
+  margin-left: 10px;
+  width: 100%;
+  flex: 1;
+}
+
+#text-input {
+  flex: 1;
+  padding: 8px 16px;
+  border: 1px solid #e0e0e0;
+  border-radius: 4px;
+  min-width: 200px;
+}
+
+#send-text-btn {
+  padding: 8px 16px;
+  border: none;
+  border-radius: 4px;
+  background-color: #007bff;
+  color: white;
+  flex-shrink: 0;
+}
+
+#send-text-btn:hover {
+  background-color: #0056b3;
+}
+
 #connect-btn {
   background-color: #4caf50;
   color: white;
@@ -38,6 +106,9 @@ body {
   color: white;
 }
 
+#mic-toggle-btn {
+}
+
 button:disabled {
   opacity: 0.5;
   cursor: not-allowed;

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

@@ -10,9 +10,9 @@
     "preview": "vite preview"
   },
   "dependencies": {
-    "@pipecat-ai/client-js": "^0.3.5",
-    "@pipecat-ai/client-react": "^0.3.5",
-    "@pipecat-ai/daily-transport": "^0.3.8",
+    "@pipecat-ai/client-js": "^1.0.0",
+    "@pipecat-ai/client-react": "^1.0.0",
+    "@pipecat-ai/daily-transport": "^1.0.0",
     "react": "^18.3.1",
     "react-dom": "^18.3.1"
   },

examples/simple-chatbot/client/react/src/App.tsx

@@ -1,22 +1,22 @@
 import {
-  RTVIClientAudio,
-  RTVIClientVideo,
-  useRTVIClientTransportState,
+  PipecatClientAudio,
+  PipecatClientVideo,
+  usePipecatClientTransportState,
 } from '@pipecat-ai/client-react';
-import { RTVIProvider } from './providers/RTVIProvider';
+import { PipecatProvider } from './providers/PipecatProvider';
 import { ConnectButton } from './components/ConnectButton';
 import { StatusDisplay } from './components/StatusDisplay';
 import { DebugDisplay } from './components/DebugDisplay';
 import './App.css';
 
 function BotVideo() {
-  const transportState = useRTVIClientTransportState();
+  const transportState = usePipecatClientTransportState();
   const isConnected = transportState !== 'disconnected';
 
   return (
     <div className="bot-container">
       <div className="video-container">
-        {isConnected && <RTVIClientVideo participant="bot" fit="cover" />}
+        {isConnected && <PipecatClientVideo participant="bot" fit="cover" />}
       </div>
     </div>
   );
@@ -35,16 +35,16 @@ function AppContent() {
       </div>
 
       <DebugDisplay />
-      <RTVIClientAudio />
+      <PipecatClientAudio />
     </div>
   );
 }
 
 function App() {
   return (
-    <RTVIProvider>
+    <PipecatProvider>
       <AppContent />
-    </RTVIProvider>
+    </PipecatProvider>
   );
 }
 

examples/simple-chatbot/client/react/src/components/ConnectButton.tsx

@@ -1,16 +1,16 @@
 import {
-  useRTVIClient,
-  useRTVIClientTransportState,
+  usePipecatClient,
+  usePipecatClientTransportState,
 } from '@pipecat-ai/client-react';
 
 export function ConnectButton() {
-  const client = useRTVIClient();
-  const transportState = useRTVIClientTransportState();
+  const client = usePipecatClient();
+  const transportState = usePipecatClientTransportState();
   const isConnected = ['connected', 'ready'].includes(transportState);
 
   const handleClick = async () => {
     if (!client) {
-      console.error('RTVI client is not initialized');
+      console.error('Pipecat client is not initialized');
       return;
     }
 
@@ -18,7 +18,7 @@ export function ConnectButton() {
       if (isConnected) {
         await client.disconnect();
       } else {
-        await client.connect();
+        await client.connect({ endpoint: 'http://localhost:7860/connect' });
       }
     } catch (error) {
       console.error('Connection error:', error);

examples/simple-chatbot/client/react/src/components/DebugDisplay.tsx

@@ -6,12 +6,12 @@ import {
   TranscriptData,
   BotLLMTextData,
 } from '@pipecat-ai/client-js';
-import { useRTVIClient, useRTVIClientEvent } from '@pipecat-ai/client-react';
+import { usePipecatClient, useRTVIClientEvent } from '@pipecat-ai/client-react';
 import './DebugDisplay.css';
 
 export function DebugDisplay() {
   const debugLogRef = useRef<HTMLDivElement>(null);
-  const client = useRTVIClient();
+  const client = usePipecatClient();
 
   const log = useCallback((message: string) => {
     if (!debugLogRef.current) return;

examples/simple-chatbot/client/react/src/components/StatusDisplay.tsx

@@ -1,7 +1,7 @@
-import { useRTVIClientTransportState } from '@pipecat-ai/client-react';
+import { usePipecatClientTransportState } from '@pipecat-ai/client-react';
 
 export function StatusDisplay() {
-  const transportState = useRTVIClientTransportState();
+  const transportState = usePipecatClientTransportState();
 
   return (
     <div className="status">

examples/simple-chatbot/client/react/src/providers/PipecatProvider.tsx

@@ -0,0 +1,16 @@
+import { type PropsWithChildren } from 'react';
+import { PipecatClient } from '@pipecat-ai/client-js';
+import { DailyTransport } from '@pipecat-ai/daily-transport';
+import { PipecatClientProvider } from '@pipecat-ai/client-react';
+
+const client = new PipecatClient({
+  transport: new DailyTransport(),
+  enableMic: true,
+  enableCam: false,
+});
+
+export function PipecatProvider({ children }: PropsWithChildren) {
+  return (
+    <PipecatClientProvider client={client}>{children}</PipecatClientProvider>
+  );
+}

examples/simple-chatbot/client/react/src/providers/RTVIProvider.tsx

@@ -1,22 +0,0 @@
-import { type PropsWithChildren } from 'react';
-import { RTVIClient } from '@pipecat-ai/client-js';
-import { DailyTransport } from '@pipecat-ai/daily-transport';
-import { RTVIClientProvider } from '@pipecat-ai/client-react';
-
-const transport = new DailyTransport();
-
-const client = new RTVIClient({
-  transport,
-  params: {
-    baseUrl: 'http://localhost:7860',
-    endpoints: {
-      connect: '/connect',
-    },
-  },
-  enableMic: true,
-  enableCam: false,
-});
-
-export function RTVIProvider({ children }: PropsWithChildren) {
-  return <RTVIClientProvider client={client}>{children}</RTVIClientProvider>;
-}

examples/storytelling-chatbot/client/package-lock.json

@@ -345,9 +345,9 @@
       }
     },
     "node_modules/@next/env": {
-      "version": "14.2.28",
-      "resolved": "https://registry.npmjs.org/@next/env/-/env-14.2.28.tgz",
-      "integrity": "sha512-PAmWhJfJQlP+kxZwCjrVd9QnR5x0R3u0mTXTiZDgSd4h5LdXmjxCCWbN9kq6hkZBOax8Rm3xDW5HagWyJuT37g=="
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/env/-/env-14.2.30.tgz",
+      "integrity": "sha512-KBiBKrDY6kxTQWGzKjQB7QirL3PiiOkV7KW98leHFjtVRKtft76Ra5qSA/SL75xT44dp6hOcqiiJ6iievLOYug=="
     },
     "node_modules/@next/eslint-plugin-next": {
       "version": "14.1.4",
@@ -359,9 +359,9 @@
       }
     },
     "node_modules/@next/swc-darwin-arm64": {
-      "version": "14.2.28",
-      "resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-14.2.28.tgz",
-      "integrity": "sha512-kzGChl9setxYWpk3H6fTZXXPFFjg7urptLq5o5ZgYezCrqlemKttwMT5iFyx/p1e/JeglTwDFRtb923gTJ3R1w==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-14.2.30.tgz",
+      "integrity": "sha512-EAqfOTb3bTGh9+ewpO/jC59uACadRHM6TSA9DdxJB/6gxOpyV+zrbqeXiFTDy9uV6bmipFDkfpAskeaDcO+7/g==",
       "cpu": [
         "arm64"
       ],
@@ -374,9 +374,9 @@
       }
     },
     "node_modules/@next/swc-darwin-x64": {
-      "version": "14.2.28",
-      "resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-14.2.28.tgz",
-      "integrity": "sha512-z6FXYHDJlFOzVEOiiJ/4NG8aLCeayZdcRSMjPDysW297Up6r22xw6Ea9AOwQqbNsth8JNgIK8EkWz2IDwaLQcw==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-14.2.30.tgz",
+      "integrity": "sha512-TyO7Wz1IKE2kGv8dwQ0bmPL3s44EKVencOqwIY69myoS3rdpO1NPg5xPM5ymKu7nfX4oYJrpMxv8G9iqLsnL4A==",
       "cpu": [
         "x64"
       ],
@@ -389,9 +389,9 @@
       }
     },
     "node_modules/@next/swc-linux-arm64-gnu": {
-      "version": "14.2.28",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-14.2.28.tgz",
-      "integrity": "sha512-9ARHLEQXhAilNJ7rgQX8xs9aH3yJSj888ssSjJLeldiZKR4D7N08MfMqljk77fAwZsWwsrp8ohHsMvurvv9liQ==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-14.2.30.tgz",
+      "integrity": "sha512-I5lg1fgPJ7I5dk6mr3qCH1hJYKJu1FsfKSiTKoYwcuUf53HWTrEkwmMI0t5ojFKeA6Vu+SfT2zVy5NS0QLXV4Q==",
       "cpu": [
         "arm64"
       ],
@@ -404,9 +404,9 @@
       }
     },
     "node_modules/@next/swc-linux-arm64-musl": {
-      "version": "14.2.28",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-14.2.28.tgz",
-      "integrity": "sha512-p6gvatI1nX41KCizEe6JkF0FS/cEEF0u23vKDpl+WhPe/fCTBeGkEBh7iW2cUM0rvquPVwPWdiUR6Ebr/kQWxQ==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-14.2.30.tgz",
+      "integrity": "sha512-8GkNA+sLclQyxgzCDs2/2GSwBc92QLMrmYAmoP2xehe5MUKBLB2cgo34Yu242L1siSkwQkiV4YLdCnjwc/Micw==",
       "cpu": [
         "arm64"
       ],
@@ -419,9 +419,9 @@
       }
     },
     "node_modules/@next/swc-linux-x64-gnu": {
-      "version": "14.2.28",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-14.2.28.tgz",
-      "integrity": "sha512-nsiSnz2wO6GwMAX2o0iucONlVL7dNgKUqt/mDTATGO2NY59EO/ZKnKEr80BJFhuA5UC1KZOMblJHWZoqIJddpA==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-14.2.30.tgz",
+      "integrity": "sha512-8Ly7okjssLuBoe8qaRCcjGtcMsv79hwzn/63wNeIkzJVFVX06h5S737XNr7DZwlsbTBDOyI6qbL2BJB5n6TV/w==",
       "cpu": [
         "x64"
       ],
@@ -434,9 +434,9 @@
       }
     },
     "node_modules/@next/swc-linux-x64-musl": {
-      "version": "14.2.28",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-14.2.28.tgz",
-      "integrity": "sha512-+IuGQKoI3abrXFqx7GtlvNOpeExUH1mTIqCrh1LGFf8DnlUcTmOOCApEnPJUSLrSbzOdsF2ho2KhnQoO0I1RDw==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-14.2.30.tgz",
+      "integrity": "sha512-dBmV1lLNeX4mR7uI7KNVHsGQU+OgTG5RGFPi3tBJpsKPvOPtg9poyav/BYWrB3GPQL4dW5YGGgalwZ79WukbKQ==",
       "cpu": [
         "x64"
       ],
@@ -449,9 +449,9 @@
       }
     },
     "node_modules/@next/swc-win32-arm64-msvc": {
-      "version": "14.2.28",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-14.2.28.tgz",
-      "integrity": "sha512-l61WZ3nevt4BAnGksUVFKy2uJP5DPz2E0Ma/Oklvo3sGj9sw3q7vBWONFRgz+ICiHpW5mV+mBrkB3XEubMrKaA==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-14.2.30.tgz",
+      "integrity": "sha512-6MMHi2Qc1Gkq+4YLXAgbYslE1f9zMGBikKMdmQRHXjkGPot1JY3n5/Qrbg40Uvbi8//wYnydPnyvNhI1DMUW1g==",
       "cpu": [
         "arm64"
       ],
@@ -464,9 +464,9 @@
       }
     },
     "node_modules/@next/swc-win32-ia32-msvc": {
-      "version": "14.2.28",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-ia32-msvc/-/swc-win32-ia32-msvc-14.2.28.tgz",
-      "integrity": "sha512-+Kcp1T3jHZnJ9v9VTJ/yf1t/xmtFAc/Sge4v7mVc1z+NYfYzisi8kJ9AsY8itbgq+WgEwMtOpiLLJsUy2qnXZw==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-ia32-msvc/-/swc-win32-ia32-msvc-14.2.30.tgz",
+      "integrity": "sha512-pVZMnFok5qEX4RT59mK2hEVtJX+XFfak+/rjHpyFh7juiT52r177bfFKhnlafm0UOSldhXjj32b+LZIOdswGTg==",
       "cpu": [
         "ia32"
       ],
@@ -479,9 +479,9 @@
       }
     },
     "node_modules/@next/swc-win32-x64-msvc": {
-      "version": "14.2.28",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-14.2.28.tgz",
-      "integrity": "sha512-1gCmpvyhz7DkB1srRItJTnmR2UwQPAUXXIg9r0/56g3O8etGmwlX68skKXJOp9EejW3hhv7nSQUJ2raFiz4MoA==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-14.2.30.tgz",
+      "integrity": "sha512-4KCo8hMZXMjpTzs3HOqOGYYwAXymXIy7PEPAXNEcEOyKqkjiDlECumrWziy+JEF0Oi4ILHGxzgQ3YiMGG2t/Lg==",
       "cpu": [
         "x64"
       ],
@@ -1317,9 +1317,9 @@
       }
     },
     "node_modules/@typescript-eslint/typescript-estree/node_modules/brace-expansion": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
-      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
+      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
       "dev": true,
       "dependencies": {
         "balanced-match": "^1.0.0"
@@ -1960,9 +1960,9 @@
       "integrity": "sha512-AlcaJBi/pqqJBIQ8U9Mcpc9i8Aqxn88Skv5d+xBX006BY5u8N3mGLHa5Lgppa7L/HfwgwLgZ6NYs+Ag6uUmJRA=="
     },
     "node_modules/brace-expansion": {
-      "version": "1.1.11",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
-      "integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
+      "version": "1.1.12",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
+      "integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
       "dev": true,
       "dependencies": {
         "balanced-match": "^1.0.0",
@@ -3391,9 +3391,9 @@
       }
     },
     "node_modules/glob/node_modules/brace-expansion": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
-      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
+      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
       "dependencies": {
         "balanced-match": "^1.0.0"
       }
@@ -4389,11 +4389,11 @@
       "dev": true
     },
     "node_modules/next": {
-      "version": "14.2.28",
-      "resolved": "https://registry.npmjs.org/next/-/next-14.2.28.tgz",
-      "integrity": "sha512-QLEIP/kYXynIxtcKB6vNjtWLVs3Y4Sb+EClTC/CSVzdLD1gIuItccpu/n1lhmduffI32iPGEK2cLLxxt28qgYA==",
+      "version": "14.2.30",
+      "resolved": "https://registry.npmjs.org/next/-/next-14.2.30.tgz",
+      "integrity": "sha512-+COdu6HQrHHFQ1S/8BBsCag61jZacmvbuL2avHvQFbWa2Ox7bE+d8FyNgxRLjXQ5wtPyQwEmk85js/AuaG2Sbg==",
       "dependencies": {
-        "@next/env": "14.2.28",
+        "@next/env": "14.2.30",
         "@swc/helpers": "0.5.5",
         "busboy": "1.6.0",
         "caniuse-lite": "^1.0.30001579",
@@ -4408,15 +4408,15 @@
         "node": ">=18.17.0"
       },
       "optionalDependencies": {
-        "@next/swc-darwin-arm64": "14.2.28",
-        "@next/swc-darwin-x64": "14.2.28",
-        "@next/swc-linux-arm64-gnu": "14.2.28",
-        "@next/swc-linux-arm64-musl": "14.2.28",
-        "@next/swc-linux-x64-gnu": "14.2.28",
-        "@next/swc-linux-x64-musl": "14.2.28",
-        "@next/swc-win32-arm64-msvc": "14.2.28",
-        "@next/swc-win32-ia32-msvc": "14.2.28",
-        "@next/swc-win32-x64-msvc": "14.2.28"
+        "@next/swc-darwin-arm64": "14.2.30",
+        "@next/swc-darwin-x64": "14.2.30",
+        "@next/swc-linux-arm64-gnu": "14.2.30",
+        "@next/swc-linux-arm64-musl": "14.2.30",
+        "@next/swc-linux-x64-gnu": "14.2.30",
+        "@next/swc-linux-x64-musl": "14.2.30",
+        "@next/swc-win32-arm64-msvc": "14.2.30",
+        "@next/swc-win32-ia32-msvc": "14.2.30",
+        "@next/swc-win32-x64-msvc": "14.2.30"
       },
       "peerDependencies": {
         "@opentelemetry/api": "^1.1.0",

examples/twilio-chatbot/client/typescript/package.json

@@ -19,7 +19,7 @@
     "vite": "^6.0.2"
   },
   "dependencies": {
-    "@pipecat-ai/client-js": "^0.4.0",
-    "@pipecat-ai/websocket-transport": "^0.4.2"
+    "@pipecat-ai/client-js": "^1.0.0",
+    "@pipecat-ai/websocket-transport": "^1.0.0"
   }
 }

examples/twilio-chatbot/client/typescript/src/app.ts

@@ -5,21 +5,22 @@
  */
 
 import {
-  RTVIClient,
-  RTVIClientOptions,
-  RTVIEvent,
+  BotLLMTextData,
+  Participant,
+  PipecatClient,
+  PipecatClientOptions,
+  RTVIEvent, RTVIMessage, TranscriptData,
 } from '@pipecat-ai/client-js';
 import {
   WebSocketTransport,
   TwilioSerializer,
-} from "@pipecat-ai/websocket-transport";
+} from '@pipecat-ai/websocket-transport';
 
 class WebsocketClientApp {
+  private static STREAM_SID = 'ws_mock_stream_sid';
+  private static CALL_SID = 'ws_mock_call_sid';
 
-  private static STREAM_SID = "ws_mock_stream_sid"
-  private static CALL_SID = "ws_mock_call_sid"
-
-  private rtviClient: RTVIClient | null = null;
+  private rtviClient: PipecatClient | null = null;
   private connectBtn: HTMLButtonElement | null = null;
   private disconnectBtn: HTMLButtonElement | null = null;
   private statusSpan: HTMLElement | null = null;
@@ -38,8 +39,12 @@ class WebsocketClientApp {
    * 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.connectBtn = document.getElementById(
+      'connect-btn'
+    ) as HTMLButtonElement;
+    this.disconnectBtn = document.getElementById(
+      'disconnect-btn'
+    ) as HTMLButtonElement;
     this.statusSpan = document.getElementById('connection-status');
     this.debugLog = document.getElementById('debug-log');
   }
@@ -80,13 +85,23 @@ class WebsocketClientApp {
   }
 
   private async emulateTwilioMessages() {
-    const connectedMessage={"event": "connected", "protocol": "Call", "version": "1.0.0"}
+    const connectedMessage = {
+      event: 'connected',
+      protocol: 'Call',
+      version: '1.0.0',
+    };
 
-    const websocketTransport = this.rtviClient?.transport as WebSocketTransport
-    void websocketTransport?.sendRawMessage(connectedMessage)
+    const websocketTransport = this.rtviClient?.transport as WebSocketTransport;
+    void websocketTransport?.sendRawMessage(connectedMessage);
 
-    const startMessage={"event": "start", "start": {"streamSid": WebsocketClientApp.STREAM_SID, "callSid": WebsocketClientApp.CALL_SID}}
-    void websocketTransport?.sendRawMessage(startMessage)
+    const startMessage = {
+      event: 'start',
+      start: {
+        streamSid: WebsocketClientApp.STREAM_SID,
+        callSid: WebsocketClientApp.CALL_SID,
+      },
+    };
+    void websocketTransport?.sendRawMessage(startMessage);
   }
 
   /**
@@ -109,7 +124,7 @@ class WebsocketClientApp {
     if (!this.rtviClient) return;
 
     // Listen for new tracks starting
-    this.rtviClient.on(RTVIEvent.TrackStarted, (track, participant) => {
+    this.rtviClient.on(RTVIEvent.TrackStarted, (track: MediaStreamTrack, participant?: Participant) => {
       // Only handle non-local (bot) tracks
       if (!participant?.local && track.kind === 'audio') {
         this.setupAudioTrack(track);
@@ -117,8 +132,10 @@ class WebsocketClientApp {
     });
 
     // Listen for tracks stopping
-    this.rtviClient.on(RTVIEvent.TrackStopped, (track, participant) => {
-      this.log(`Track stopped: ${track.kind} from ${participant?.name || 'unknown'}`);
+    this.rtviClient.on(RTVIEvent.TrackStopped, (track: MediaStreamTrack, participant?: Participant) => {
+      this.log(
+        `Track stopped: ${track.kind} from ${participant?.name || 'unknown'}`
+      );
     });
   }
 
@@ -128,7 +145,10 @@ class WebsocketClientApp {
    */
   private setupAudioTrack(track: MediaStreamTrack): void {
     this.log('Setting up audio track');
-    if (this.botAudio.srcObject && "getAudioTracks" in this.botAudio.srcObject) {
+    if (
+      this.botAudio.srcObject &&
+      'getAudioTracks' in this.botAudio.srcObject
+    ) {
       const oldTrack = this.botAudio.srcObject.getAudioTracks()[0];
       if (oldTrack?.id === track.id) return;
     }
@@ -143,23 +163,19 @@ class WebsocketClientApp {
     try {
       const startTime = Date.now();
 
-      const transport = new WebSocketTransport({
+      const ws_opts = {
         serializer: new TwilioSerializer(),
         recorderSampleRate: 8000,
-        playerSampleRate: 8000
-      });
-      const RTVIConfig: RTVIClientOptions = {
-        transport,
-        params: {
-          // The baseURL and endpoint of your bot server that the client will connect to
-          baseUrl: 'http://localhost:8765',
-          endpoints: { connect: '/' },
-        },
+        playerSampleRate: 8000,
+        ws_url: 'http://localhost:8765/ws',
+      };
+      const RTVIConfig: PipecatClientOptions = {
+        transport: new WebSocketTransport(ws_opts),
         enableMic: true,
         enableCam: false,
         callbacks: {
           onConnected: () => {
-            this.emulateTwilioMessages()
+            this.emulateTwilioMessages();
             this.updateStatus('Connected');
             if (this.connectBtn) this.connectBtn.disabled = true;
             if (this.disconnectBtn) this.disconnectBtn.disabled = false;
@@ -170,27 +186,21 @@ class WebsocketClientApp {
             if (this.disconnectBtn) this.disconnectBtn.disabled = true;
             this.log('Client disconnected');
           },
-          onBotReady: (data) => {
+          onBotReady: (data: any) => {
             this.log(`Bot ready: ${JSON.stringify(data)}`);
             this.setupMediaTracks();
           },
-          onUserTranscript: (data) => {
+          onUserTranscript: (data: TranscriptData) => {
             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),
+          onBotTranscript: (data: BotLLMTextData) => this.log(`Bot: ${data.text}`),
+          onMessageError: (error: RTVIMessage) => console.error('Message error:', error),
+          onError: (error: RTVIMessage) => console.error('Error:', error),
         },
-      }
-      // @ts-ignore
-      RTVIConfig.customConnectHandler = () => Promise.resolve(
-          {
-              ws_url: "/ws",
-          }
-      );
-      this.rtviClient = new RTVIClient(RTVIConfig);
+      };
+      this.rtviClient = new PipecatClient(RTVIConfig);
       this.setupTrackListeners();
 
       this.log('Initializing devices...');
@@ -223,8 +233,13 @@ class WebsocketClientApp {
       try {
         await this.rtviClient.disconnect();
         this.rtviClient = null;
-        if (this.botAudio.srcObject && "getAudioTracks" in this.botAudio.srcObject) {
-          this.botAudio.srcObject.getAudioTracks().forEach((track) => track.stop());
+        if (
+          this.botAudio.srcObject &&
+          'getAudioTracks' in this.botAudio.srcObject
+        ) {
+          this.botAudio.srcObject
+            .getAudioTracks()
+            .forEach((track) => track.stop());
           this.botAudio.srcObject = null;
         }
       } catch (error) {
@@ -232,7 +247,6 @@ class WebsocketClientApp {
       }
     }
   }
-
 }
 
 declare global {

examples/websocket/client/README.md

@@ -6,10 +6,10 @@ Basic implementation using the [Pipecat JavaScript SDK](https://docs.pipecat.ai/
 
 1. Run the bot server. See the [server README](../README).
 
-2. Navigate to the `client/javascript` directory:
+2. Navigate to the `client` directory:
 
 ```bash
-cd client/javascript
+cd client
 ```
 
 3. Install dependencies: