Compare commits
1 Commits
pk/optiona
...
demo/ttssp
| Author | SHA1 | Date | |
|---|---|---|---|
|
2243cc11b9 |
@@ -1 +0,0 @@
|
||||
../../.claude/skills/changelog
|
||||
@@ -1 +0,0 @@
|
||||
../../.claude/skills/cleanup
|
||||
@@ -1 +0,0 @@
|
||||
../../.claude/skills/code-review
|
||||
@@ -1 +0,0 @@
|
||||
../../.claude/skills/docstring
|
||||
@@ -1 +0,0 @@
|
||||
../../.claude/skills/pr-description
|
||||
@@ -1 +0,0 @@
|
||||
../../.claude/skills/pr-submit
|
||||
@@ -1 +0,0 @@
|
||||
../../.claude/skills/update-docs
|
||||
@@ -1,8 +1,3 @@
|
||||
---
|
||||
name: cleanup
|
||||
description: Review, refactor, document, and validate code changes in the current branch
|
||||
---
|
||||
|
||||
# Code Cleanup Skill
|
||||
|
||||
The **Code Cleanup Skill** reviews, refactors, and documents code changes in your current branch, ensuring alignment with **Pipecat's architecture, coding standards, and example patterns**.
|
||||
|
||||
1
.github/workflows/coverage.yaml
vendored
1
.github/workflows/coverage.yaml
vendored
@@ -42,7 +42,6 @@ jobs:
|
||||
--extra langchain \
|
||||
--extra livekit \
|
||||
--extra piper \
|
||||
--extra runner \
|
||||
--extra sagemaker \
|
||||
--extra tracing \
|
||||
--extra websocket
|
||||
|
||||
8
.github/workflows/format.yaml
vendored
8
.github/workflows/format.yaml
vendored
@@ -32,9 +32,7 @@ jobs:
|
||||
run: uv python install 3.12
|
||||
|
||||
- name: Install development dependencies
|
||||
# `--all-extras` (matching the dev setup in README.md) so pyright can
|
||||
# resolve types from various optional dependencies.
|
||||
run: uv sync --group dev --all-extras --no-extra gstreamer --no-extra local
|
||||
run: uv sync --group dev
|
||||
|
||||
- name: Ruff formatter
|
||||
id: ruff-format
|
||||
@@ -43,7 +41,3 @@ jobs:
|
||||
- name: Ruff linter (all rules)
|
||||
id: ruff-check
|
||||
run: uv run ruff check
|
||||
|
||||
- name: Type check (pyright)
|
||||
id: pyright
|
||||
run: uv run pyright
|
||||
|
||||
1
.github/workflows/tests.yaml
vendored
1
.github/workflows/tests.yaml
vendored
@@ -46,7 +46,6 @@ jobs:
|
||||
--extra langchain \
|
||||
--extra livekit \
|
||||
--extra piper \
|
||||
--extra runner \
|
||||
--extra sagemaker \
|
||||
--extra tracing \
|
||||
--extra websocket
|
||||
|
||||
1
.github/workflows/update-docs.yml
vendored
1
.github/workflows/update-docs.yml
vendored
@@ -114,7 +114,6 @@ jobs:
|
||||
GH_TOKEN=$DOCS_SYNC_TOKEN gh pr create \
|
||||
--repo pipecat-ai/docs \
|
||||
--label auto-docs \
|
||||
--label pipecat \
|
||||
--title "docs: update for pipecat PR #${{ steps.pr.outputs.number }}" \
|
||||
--body "$(cat <<'BODY'
|
||||
Automated documentation update for [pipecat PR #${{ steps.pr.outputs.number }}](https://github.com/pipecat-ai/pipecat/pull/${{ steps.pr.outputs.number }}).
|
||||
|
||||
174
AGENTS.md
174
AGENTS.md
@@ -1,174 +0,0 @@
|
||||
# AGENTS.md
|
||||
|
||||
This file provides guidance to AI coding agents when working with code in this repository.
|
||||
|
||||
## Project Overview
|
||||
|
||||
Pipecat is an open-source Python framework for building real-time voice and multimodal conversational AI agents. It orchestrates audio/video, AI services, transports, and conversation pipelines using a frame-based architecture.
|
||||
|
||||
## Common Commands
|
||||
|
||||
```bash
|
||||
# Setup development environment
|
||||
uv sync --group dev --all-extras --no-extra gstreamer --no-extra local
|
||||
|
||||
# Install pre-commit hooks
|
||||
uv run pre-commit install
|
||||
|
||||
# Run all tests
|
||||
uv run pytest
|
||||
|
||||
# Run a single test file
|
||||
uv run pytest tests/test_name.py
|
||||
|
||||
# Run a specific test
|
||||
uv run pytest tests/test_name.py::test_function_name
|
||||
|
||||
# Preview changelog
|
||||
uv run towncrier build --draft --version Unreleased
|
||||
|
||||
# Lint and format check
|
||||
uv run ruff check
|
||||
uv run ruff format --check
|
||||
|
||||
# Update dependencies (after editing pyproject.toml)
|
||||
uv lock && uv sync
|
||||
```
|
||||
|
||||
## Architecture
|
||||
|
||||
### Frame-Based Pipeline Processing
|
||||
|
||||
All data flows as **Frame** objects through a pipeline of **FrameProcessors**:
|
||||
|
||||
```
|
||||
[Processor1] → [Processor2] → ... → [ProcessorN]
|
||||
```
|
||||
|
||||
**Key components:**
|
||||
|
||||
- **Frames** (`src/pipecat/frames/frames.py`): Data units (audio, text, video) and control signals. Flow DOWNSTREAM (input→output) or UPSTREAM (acknowledgments/errors).
|
||||
|
||||
- **FrameProcessor** (`src/pipecat/processors/frame_processor.py`): Base processing unit. Each processor receives frames, processes them, and pushes results downstream.
|
||||
|
||||
- **Pipeline** (`src/pipecat/pipeline/pipeline.py`): Chains processors together.
|
||||
|
||||
- **ParallelPipeline** (`src/pipecat/pipeline/parallel_pipeline.py`): Runs multiple pipelines in parallel.
|
||||
|
||||
- **Transports** (`src/pipecat/transports/`): Transports are frame processors used for external I/O layer (Daily WebRTC, LiveKit WebRTC, WebSocket, Local). Abstract interface via `BaseTransport`, `BaseInputTransport` and `BaseOutputTransport`.
|
||||
|
||||
- **Pipeline Task (`src/pipecat/pipeline/task.py`)**: Runs and manages a pipeline. Pipeline tasks send the first frame, `StartFrame`, to the pipeline in order for processors to know they can start processing and pushing frames. Pipeline tasks internally create a pipeline with two additional processors, a source processor before the user-defined pipeline and a sink processor at the end. Those are used for multiple things: error handling, pipeline task level events, heartbeat monitoring, etc.
|
||||
|
||||
- **Pipeline Runner (`src/pipecat/pipeline/runner.py`)**: High-level entry point for executing pipeline tasks. Handles signal management (SIGINT/SIGTERM) for graceful shutdown and optional garbage collection. Run a single pipeline task with `await runner.run(task)` or multiple concurrently with `await asyncio.gather(runner.run(task1), runner.run(task2))`.
|
||||
|
||||
- **Services** (`src/pipecat/services/`): 60+ AI provider integrations (STT, TTS, LLM, etc.). Extend base classes: `AIService`, `LLMService`, `STTService`, `TTSService`, `VisionService`.
|
||||
|
||||
- **Serializers** (`src/pipecat/serializers/`): Convert frames to/from wire formats for WebSocket transports. `FrameSerializer` base class defines `serialize()` and `deserialize()`. Telephony serializers (Twilio, Plivo, Vonage, Telnyx, Exotel, Genesys) handle provider-specific protocols and audio encoding (e.g., μ-law).
|
||||
|
||||
- **RTVI** (`src/pipecat/processors/frameworks/rtvi.py`): Real-Time Voice Interface protocol bridging clients and the pipeline. `RTVIProcessor` handles incoming client messages (text input, audio, function call results). `RTVIObserver` converts pipeline frames to outgoing messages: user/bot speaking events, transcriptions, LLM/TTS lifecycle, function calls, metrics, and audio levels.
|
||||
|
||||
- **Observers** (`src/pipecat/observers/`): Monitor frame flow without modifying the pipeline. Passed to `PipelineTask` via the `observers` parameter. Implement `on_process_frame()` and `on_push_frame()` callbacks.
|
||||
|
||||
### Important Patterns
|
||||
|
||||
- **Context Aggregation**: `LLMContext` accumulates messages for LLM calls; `UserResponse` aggregates user input
|
||||
|
||||
- **Turn Management**: Turn management is done through `LLMUserAggregator` and
|
||||
`LLMAssistantAggregator`, created with `LLMContextAggregatorPair`
|
||||
|
||||
- **User turn strategies**: Detection of when the user starts and stops speaking is done via user turn start/stop strategies. They push `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` respectively.
|
||||
|
||||
- **Interruptions**: Interruptions are usually triggered by a user turn start strategy (e.g. `VADUserTurnStartStrategy`) but they can be triggered by other processors as well, in which case the user turn start strategies don't need to. An `InterruptionFrame` carries an optional `asyncio.Event` that is set when the frame reaches the pipeline sink. If a processor stops an `InterruptionFrame` from propagating downstream (i.e., doesn't push it), it **must** call `frame.complete()` to avoid stalling `push_interruption_task_frame_and_wait()` callers.
|
||||
|
||||
- **Uninterruptible Frames**: These are frames that will not be removed from internal queues even if there's an interruption. For example, `EndFrame` and `StopFrame`.
|
||||
|
||||
- **Events**: Most classes in Pipecat have `BaseObject` as the very base class. `BaseObject` has support for events. Events can run in the background in an async task (default) or synchronously (`sync=True`) if we want immediate action. Synchronous event handlers need to execute fast.
|
||||
|
||||
- **Async Task Management**: Always use `self.create_task(coroutine, name)` instead of raw `asyncio.create_task()`. The `TaskManager` automatically tracks tasks and cleans them up on processor shutdown. Use `await self.cancel_task(task, timeout)` for cancellation.
|
||||
|
||||
- **Error Handling**: Use `await self.push_error(msg, exception, fatal)` to push errors upstream. Services should use `fatal=False` (the default) so application code can handle errors and take action (e.g. switch to another service).
|
||||
|
||||
### Key Directories
|
||||
|
||||
| Directory | Purpose |
|
||||
| -------------------------- | -------------------------------------------------- |
|
||||
| `src/pipecat/frames/` | Frame definitions (100+ types) |
|
||||
| `src/pipecat/processors/` | FrameProcessor base + aggregators, filters, audio |
|
||||
| `src/pipecat/pipeline/` | Pipeline orchestration |
|
||||
| `src/pipecat/services/` | AI service integrations (60+ providers) |
|
||||
| `src/pipecat/transports/` | Transport layer (Daily, LiveKit, WebSocket, Local) |
|
||||
| `src/pipecat/serializers/` | Frame serialization for WebSocket protocols |
|
||||
| `src/pipecat/observers/` | Pipeline observers for monitoring frame flow |
|
||||
| `src/pipecat/audio/` | VAD, filters, mixers, turn detection, DTMF |
|
||||
| `src/pipecat/turns/` | User turn management |
|
||||
|
||||
## Code Style
|
||||
|
||||
- **Docstrings**: Google-style. Classes describe purpose; `__init__` has `Args:` section; dataclasses use `Parameters:` section.
|
||||
- **Deprecations**: Use the `.. deprecated:: <version>` Sphinx directive in docstrings (never inline tags like `[DEPRECATED]`), and pair it with a runtime `warnings.warn(..., DeprecationWarning)` at the call site. See `CONTRIBUTING.md` for full conventions.
|
||||
- **Linting**: Ruff (line length 100). Pre-commit hooks enforce formatting.
|
||||
- **Type hints**: Required for complex async code.
|
||||
- **Dataclass vs Pydantic**: Use `@dataclass` for frames and internal pipeline data (high-frequency, no validation needed). Use Pydantic `BaseModel` for configuration, parameters, metrics, and external API data (benefits from validation and serialization). Specifically:
|
||||
- `@dataclass`: Frame types, context aggregator pairs, internal data containers
|
||||
- `BaseModel`: Service `InputParams`, transport/VAD/turn params, metrics data, API request/response models, serializer params
|
||||
|
||||
### Docstring Example
|
||||
|
||||
```python
|
||||
class MyService(LLMService):
|
||||
"""Description of what the service does.
|
||||
|
||||
More detailed description.
|
||||
|
||||
Event handlers available:
|
||||
|
||||
- on_connected: Called when we are connected
|
||||
|
||||
Example::
|
||||
|
||||
@service.event_handler("on_connected")
|
||||
async def on_connected(service, frame):
|
||||
...
|
||||
"""
|
||||
|
||||
def __init__(self, param1: str, **kwargs):
|
||||
"""Initialize the service.
|
||||
|
||||
Args:
|
||||
param1: Description of param1.
|
||||
**kwargs: Additional arguments passed to parent.
|
||||
"""
|
||||
super().__init__(**kwargs)
|
||||
|
||||
|
||||
# Pydantic params class with a deprecated field
|
||||
class MyParams(BaseModel):
|
||||
"""Configuration parameters for MyService.
|
||||
|
||||
Parameters:
|
||||
new_setting: Replacement for ``old_setting``.
|
||||
old_setting: Legacy setting, no longer used.
|
||||
|
||||
.. deprecated:: 1.2.0
|
||||
Use ``new_setting`` instead. Will be removed in 2.0.0.
|
||||
"""
|
||||
|
||||
new_setting: str = "default"
|
||||
old_setting: str | None = None
|
||||
```
|
||||
|
||||
## Service Implementation
|
||||
|
||||
When adding a new service:
|
||||
|
||||
1. Extend the appropriate base class (`STTService`, `TTSService`, `LLMService`, etc.)
|
||||
2. Implement required abstract methods
|
||||
3. Handle necessary frames
|
||||
4. By default, all frames should be pushed in the direction they came
|
||||
5. Push `ErrorFrame` on failures
|
||||
6. Add metrics tracking via `MetricsData` if relevant
|
||||
7. Follow the pattern of existing services in `src/pipecat/services/`
|
||||
|
||||
## Testing
|
||||
|
||||
Test utilities live in `src/pipecat/tests/utils.py`. Use `run_test()` to send frames through a pipeline and assert expected output frames in each direction. Use `SleepFrame(sleep=N)` to add delays between frames.
|
||||
338
CHANGELOG.md
338
CHANGELOG.md
@@ -7,344 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
<!-- towncrier release notes start -->
|
||||
|
||||
## [1.1.0] - 2026-04-27
|
||||
|
||||
### Added
|
||||
|
||||
- Added `MistralSTTService` for real-time speech-to-text using Mistral's
|
||||
Voxtral Realtime API (`voxtral-mini-transcribe-realtime-2602`). Supports
|
||||
streaming transcription with interim results, automatic language detection,
|
||||
and VAD-driven utterance lifecycle.
|
||||
(PR [#4253](https://github.com/pipecat-ai/pipecat/pull/4253))
|
||||
|
||||
- Added `buttons` field to `OutputDTMFFrame` and `OutputDTMFUrgentFrame` for
|
||||
sending multi-key DTMF sequences as a `list[KeypadEntry]`. Use
|
||||
`OutputDTMFFrame.from_string("123#")` (or the equivalent on
|
||||
`OutputDTMFUrgentFrame`) to build one from a dial string, and `to_string()`
|
||||
to convert back.
|
||||
(PR [#4313](https://github.com/pipecat-ai/pipecat/pull/4313))
|
||||
|
||||
- Added `DailyTransport.send_dtmf()` to expose the Daily call client's DTMF
|
||||
sending capability, enabling applications to send tones during a call (e.g.
|
||||
IVR navigation).
|
||||
(PR [#4313](https://github.com/pipecat-ai/pipecat/pull/4313))
|
||||
|
||||
- Added `DailyOutputDTMFFrame` and `DailyOutputDTMFUrgentFrame` frames. In
|
||||
addition to the inherited `buttons`, they accept `session_id`,
|
||||
`digit_duration_ms` and `method`, which are forwarded to Daily's `send_dtmf`
|
||||
as `sessionId`, `digitDurationMs` and `method`.
|
||||
(PR [#4313](https://github.com/pipecat-ai/pipecat/pull/4313))
|
||||
|
||||
- Added incremental `pyright` type checking. A `pyrightconfig.json` at the repo
|
||||
root uses `typeCheckingMode: "basic"` with an explicit `include` list of
|
||||
modules that pass cleanly (`clocks`, `metrics`, `transcriptions`, `frames`,
|
||||
`observers`, `extensions`, `turns`, `pipeline`, `runner`). Remaining modules
|
||||
will be added in subsequent PRs. CI enforces the checked set via `uv run
|
||||
pyright` in the format workflow.
|
||||
(PR [#4324](https://github.com/pipecat-ai/pipecat/pull/4324))
|
||||
|
||||
- Added multilingual support to `DeepgramFluxSTTService` via a new
|
||||
`language_hints: list[Language]` setting. Works with Deepgram's new
|
||||
`flux-general-multi` model to bias transcription across English, Spanish,
|
||||
French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch.
|
||||
Omit the hints to use auto-detection, or pass a subset to bias toward
|
||||
expected languages. Hints can be updated mid-stream via
|
||||
`STTUpdateSettingsFrame` (sent as a Deepgram `Configure` control message, no
|
||||
reconnect) to support detect-then-lock flows.
|
||||
(PR [#4326](https://github.com/pipecat-ai/pipecat/pull/4326))
|
||||
|
||||
- Added fine-grained server-side VAD tuning options to
|
||||
`SarvamSTTService.Settings` for the `saaras:v3` model, including speech
|
||||
thresholds, frame-count controls, pre-speech padding, interruption
|
||||
sensitivity, and initial-frame skipping.
|
||||
(PR [#4334](https://github.com/pipecat-ai/pipecat/pull/4334))
|
||||
|
||||
- Added `XAISTTService` for real-time speech-to-text using xAI's voice STT
|
||||
WebSocket API (`wss://api.x.ai/v1/stt`). Streams raw audio (PCM, µ-law, or
|
||||
A-law) and emits interim and final transcription frames driven by the
|
||||
server's `is_final` / `speech_final` flags. Settings expose
|
||||
`interim_results`, `endpointing`, `language`, `multichannel`, `channels`, and
|
||||
`diarize`. Requires the `xai` optional extra (`pip install
|
||||
"pipecat-ai[xai]"`).
|
||||
(PR [#4340](https://github.com/pipecat-ai/pipecat/pull/4340))
|
||||
|
||||
- Added `XAITTSService` for streaming text-to-speech using xAI's WebSocket TTS
|
||||
endpoint (`wss://api.x.ai/v1/tts`). Streams `text.delta` chunks up and base64
|
||||
`audio.delta` chunks down on the same connection so audio begins flowing
|
||||
before the full utterance finishes synthesizing; complements the batch-HTTP
|
||||
`XAIHttpTTSService`. Defaults to raw PCM output so `TTSAudioRawFrame` needs
|
||||
no decoding. The `xai` optional extra now pulls in
|
||||
`pipecat-ai[websockets-base]`.
|
||||
(PR [#4341](https://github.com/pipecat-ai/pipecat/pull/4341))
|
||||
|
||||
- Added `SonioxTTSService`, a real-time WebSocket TTS service that streams text
|
||||
in and audio out over a persistent connection. Install with `pip install
|
||||
"pipecat-ai[soniox]"`.
|
||||
(PR [#4360](https://github.com/pipecat-ai/pipecat/pull/4360))
|
||||
|
||||
- Added support for Daily's built-in `screenVideo` destination in
|
||||
`DailyTransport`. When `"screenVideo"` is included in
|
||||
`video_out_destinations` transport parameter, a dedicated screen video track
|
||||
is created at join time and frames with `transport_destination="screenVideo"`
|
||||
are routed to it.
|
||||
|
||||
```python
|
||||
params = DailyParams(
|
||||
video_out_enabled=True,
|
||||
video_out_is_live=True,
|
||||
video_out_width=1280,
|
||||
video_out_height=720,
|
||||
video_out_destinations=["screenVideo"]
|
||||
)
|
||||
|
||||
...
|
||||
|
||||
frame = OutputImageRawFrame(...)
|
||||
frame.transport_destination = "screenVideo"
|
||||
```
|
||||
(PR [#4370](https://github.com/pipecat-ai/pipecat/pull/4370))
|
||||
|
||||
- Added `camera_out_send_settings` to `DailyParams`. This dict is passed
|
||||
verbatim to the Daily client's camera publishing settings, allowing
|
||||
applications to fully control encoding, codec, bitrate, and framerate.
|
||||
|
||||
```python
|
||||
params = DailyParams(
|
||||
camera_out_send_settings={
|
||||
"maxQuality": "high",
|
||||
"encodings": {
|
||||
"high": {"maxBitrate": 2_000_000, "maxFramerate": 30}
|
||||
},
|
||||
},
|
||||
)
|
||||
```
|
||||
(PR [#4370](https://github.com/pipecat-ai/pipecat/pull/4370))
|
||||
|
||||
- Added `tool_resources` to `PipelineTask` and `FunctionCallParams`. Pass an
|
||||
application-defined object (DB handles, clients, state, etc.) to
|
||||
`PipelineTask(..., tool_resources=...)` and access it from any tool handler
|
||||
via `params.tool_resources`. Passed by reference; the caller retains their
|
||||
handle and can read mutations after the task finishes. Resolves #4256.
|
||||
(PR [#4371](https://github.com/pipecat-ai/pipecat/pull/4371))
|
||||
|
||||
### Changed
|
||||
|
||||
- Updated NVIDIA STT services to align with Nemotron Speech defaults and
|
||||
configuration: `api_key` is now optional for local deployments, additional
|
||||
recognition settings are available (including alternatives, word offsets, and
|
||||
diarization), and streaming/segmented docs now reflect Nemotron Speech APIs.
|
||||
- NVIDIA streaming STT now sets `TranscriptionFrame.finalized=True` when the
|
||||
provider marks a result as final, and preserves `language` on both
|
||||
`TranscriptionFrame` and `InterimTranscriptionFrame`.
|
||||
(PR [#4269](https://github.com/pipecat-ai/pipecat/pull/4269))
|
||||
|
||||
- Updated `NvidiaLLMService` to emit model reasoning as `LLMThought*Frame`s
|
||||
(from both `reasoning_content` and `<think>...</think>` output), avoid mixing
|
||||
reasoning text into normal assistant content, and allow keyless local NIM
|
||||
endpoints while warning when the cloud endpoint is used without an API key.
|
||||
(PR [#4270](https://github.com/pipecat-ai/pipecat/pull/4270))
|
||||
|
||||
- STT services now reconnect safely when settings change: reconnection is
|
||||
deferred until the current user turn ends (i.e., until
|
||||
`UserStoppedSpeakingFrame` is received) rather than interrupting an active
|
||||
speech session. Audio frames received while the reconnect is in progress are
|
||||
buffered and replayed once the new connection is ready. `CartesiaSTTService`
|
||||
and `DeepgramSTTService` both use this new behavior.
|
||||
(PR [#4311](https://github.com/pipecat-ai/pipecat/pull/4311))
|
||||
|
||||
- Reduced debug log noise for LLM services. The system instruction is now
|
||||
logged once when composed (e.g. when turn completion is enabled) instead of
|
||||
on every LLM call. Per-call logs now show only the conversation messages,
|
||||
consistent across Google, Anthropic, AWS, and OpenAI services.
|
||||
(PR [#4314](https://github.com/pipecat-ai/pipecat/pull/4314))
|
||||
|
||||
- `LiveKitRunnerArguments.token` is now a required `str` (previously `str |
|
||||
None` with a default of `None`). LiveKit requires a token to join a room, so
|
||||
the type now reflects reality. This only affects custom runners that
|
||||
construct `LiveKitRunnerArguments` directly; code consuming the argument from
|
||||
the standard runner is unaffected.
|
||||
(PR [#4324](https://github.com/pipecat-ai/pipecat/pull/4324))
|
||||
|
||||
- `TranscriptionFrame.language` and `InterimTranscriptionFrame.language`
|
||||
emitted by `DeepgramFluxSTTService` now reflect the language Deepgram
|
||||
detected for each turn (read from the `languages` field on Flux's `TurnInfo`
|
||||
event). On `flux-general-multi` this gives per-turn accuracy for downstream
|
||||
consumers (e.g. TTS voice selection). `flux-general-en` continues to emit
|
||||
`Language.EN`.
|
||||
(PR [#4326](https://github.com/pipecat-ai/pipecat/pull/4326))
|
||||
|
||||
- Added `includes_inter_frame_spaces` parameter to
|
||||
`TTSService.add_word_timestamps` and `_add_word_timestamps` (default `None`).
|
||||
When `True`, downstream consumers will not inject additional spaces between
|
||||
tokens; `None` leaves each frame's own default unchanged.
|
||||
- `InworldTTSService` now passes `includes_inter_frame_spaces=True` when
|
||||
reporting word timestamps, since Inworld tokens already include inter-word
|
||||
spacing.
|
||||
(PR [#4330](https://github.com/pipecat-ai/pipecat/pull/4330))
|
||||
|
||||
- `SarvamSTTService` now uses `saaras:v3` as its default model instead of
|
||||
`saarika:v2.5`. Applications that relied on the previous default should set
|
||||
`settings=SarvamSTTService.Settings(model="saarika:v2.5")` explicitly.
|
||||
(PR [#4334](https://github.com/pipecat-ai/pipecat/pull/4334))
|
||||
|
||||
- `SpeechTimeoutUserTurnStopStrategy` now waits only `user_speech_timeout` when
|
||||
a transcript arrives without a VAD stop event, rather than
|
||||
`max(ttfs_p99_latency, user_speech_timeout)`. If you had `ttfs_p99_latency >
|
||||
user_speech_timeout`, turn detection in that path is slightly faster than
|
||||
before.
|
||||
(PR [#4337](https://github.com/pipecat-ai/pipecat/pull/4337))
|
||||
|
||||
- If you use an STT service that emits finalized transcripts (Speechmatics,
|
||||
Soniox, Deepgram Flux, AssemblyAI) with `SpeechTimeoutUserTurnStopStrategy`,
|
||||
user turns now end as soon as `user_speech_timeout` elapses after VAD stop.
|
||||
Previously the strategy also waited for the STT P99 latency
|
||||
(`ttfs_p99_latency`) even when the transcript was already marked final.
|
||||
`user_speech_timeout` is still honored as a floor — STT finalization never
|
||||
shortens it.
|
||||
(PR [#4337](https://github.com/pipecat-ai/pipecat/pull/4337))
|
||||
|
||||
- ⚠️ `PlivoFrameSerializer` and `TelnyxFrameSerializer` now raise `ValueError`
|
||||
at construction when `auto_hang_up=True` (the default) but required
|
||||
credentials are missing, matching `TwilioFrameSerializer`. Previously they
|
||||
constructed successfully and the hangup failed silently at call-end, leaving
|
||||
phantom billable sessions on the provider. If you relied on the old silent
|
||||
behavior, pass `auto_hang_up=False` explicitly or provide the credentials.
|
||||
The specific fields checked are `call_id`/`auth_id`/`auth_token` for Plivo
|
||||
and `call_control_id`/`api_key` for Telnyx.
|
||||
(PR [#4349](https://github.com/pipecat-ai/pipecat/pull/4349))
|
||||
|
||||
- `ToolsSchema(standard_tools=...)` now accepts any `Sequence[FunctionSchema |
|
||||
DirectFunction]` rather than requiring an exact `list` of the union. Callers
|
||||
can pass a narrower `list[FunctionSchema]` (or any other `Sequence`) without
|
||||
the type checker complaining about list invariance.
|
||||
(PR [#4352](https://github.com/pipecat-ai/pipecat/pull/4352))
|
||||
|
||||
- Updated `aic-sdk` dependency to `~=2.2.0`. The `AIC_LICENSE_KEY` environment
|
||||
variable replaces the previous `AICOUSTICS_LICENSE_KEY`.
|
||||
(PR [#4362](https://github.com/pipecat-ai/pipecat/pull/4362))
|
||||
|
||||
- Loosened the `protobuf` dependency to `>=5.29.6,<7`, so projects pinned to
|
||||
protobuf 5.x can install `pipecat-ai` again. The previous `>=6.31.1,<7` pin
|
||||
(introduced in 1.0.8 alongside the `nvidia-riva-client 2.25.1` upgrade)
|
||||
silently blocked any environment whose dependency graph already constrained
|
||||
protobuf to the 5.x line. The bundled `frames_pb2.py` is now compiled with
|
||||
protoc 5.x so it imports cleanly on both 5.x and 6.x runtimes.
|
||||
|
||||
Installing the `nvidia` extra still pulls protobuf 6.x: `nvidia-riva-client
|
||||
2.25.1` ships gencode that requires a 6.x runtime, so `pipecat-ai[nvidia]`
|
||||
now declares `protobuf>=6.31.1,<7` explicitly to cover an upstream packaging
|
||||
gap (https://github.com/nvidia-riva/python-clients/issues/172).
|
||||
(PR [#4372](https://github.com/pipecat-ai/pipecat/pull/4372))
|
||||
|
||||
- Daily rooms created by the development runner (`pipecat.runner.run`) now
|
||||
expire after 4 hours with `eject_at_room_exp=True`, mirroring Pipecat Cloud's
|
||||
max session limit. Previously, runner-created rooms inherited a 2-hour
|
||||
expiration on the default code paths and had no expiration at all when
|
||||
callers posted partial `dailyRoomProperties` (e.g. `{"start_video_off":
|
||||
true}`) to `/start`, causing rooms to accumulate indefinitely. Explicit `exp`
|
||||
and `eject_at_room_exp` values in `dailyRoomProperties` are still respected.
|
||||
(PR [#4374](https://github.com/pipecat-ai/pipecat/pull/4374))
|
||||
|
||||
- Updated `daily-python` dependency to `~=0.28.0`.
|
||||
(PR [#4379](https://github.com/pipecat-ai/pipecat/pull/4379))
|
||||
|
||||
### Deprecated
|
||||
|
||||
- Deprecated `TransportParams.video_out_bitrate` for the Daily transport. Use
|
||||
`DailyParams.camera_out_send_settings` instead to configure camera publishing
|
||||
encodings (bitrate, framerate, codec, etc.).
|
||||
(PR [#4370](https://github.com/pipecat-ai/pipecat/pull/4370))
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed missing tool handlers so unregistered tool calls fail with a normal
|
||||
final tool result instead of leaving tool-call state hanging.
|
||||
(PR [#4301](https://github.com/pipecat-ai/pipecat/pull/4301))
|
||||
|
||||
- Fixed `pipecat-ai[tavus]` not installing the required `daily-python`
|
||||
dependency. Installing the `tavus` extra now correctly pulls in
|
||||
`pipecat-ai[daily]`.
|
||||
(PR [#4304](https://github.com/pipecat-ai/pipecat/pull/4304))
|
||||
|
||||
- Fixed audio loss and potential errors when STT settings were updated
|
||||
mid-speech. Previously, `CartesiaSTTService` and `DeepgramSTTService` would
|
||||
immediately disconnect and reconnect when settings changed, dropping any
|
||||
in-flight audio. Reconnection is now deferred until the user stops speaking,
|
||||
and audio arriving during the reconnect window is buffered and replayed.
|
||||
(PR [#4311](https://github.com/pipecat-ai/pipecat/pull/4311))
|
||||
|
||||
- Fixed `SmallestTTSService` WebSocket endpoint URL to match Smallest AI v4.0.0
|
||||
API (`wss://waves-api.smallest.ai` → `wss://api.smallest.ai`) and restored
|
||||
keepalive using a silent space message instead of the unsupported flush
|
||||
command.
|
||||
(PR [#4320](https://github.com/pipecat-ai/pipecat/pull/4320))
|
||||
|
||||
- Fixed whitespace handling in TTS token streaming mode. Inter-token whitespace
|
||||
(e.g., spaces between words) is now preserved for correct prosody, while
|
||||
leading whitespace before the first non-whitespace token is still stripped to
|
||||
avoid issues with TTS models that are sensitive to leading spaces.
|
||||
(PR [#4323](https://github.com/pipecat-ai/pipecat/pull/4323))
|
||||
|
||||
- Fixed `SentryMetrics` silently dropping `MetricsFrame`s from
|
||||
`stop_ttfb_metrics` and `stop_processing_metrics`. `SentryMetrics` called the
|
||||
base `FrameProcessorMetrics` implementation but discarded its return value,
|
||||
so `FrameProcessor` never pushed the `MetricsFrame` downstream. This
|
||||
prevented observers (e.g. `UserBotLatencyObserver`, `MetricsLogObserver`)
|
||||
from seeing TTFB and processing metrics for any service using
|
||||
`metrics=SentryMetrics()`. The metrics were still calculated and Sentry
|
||||
transactions still completed — only the downstream frame push was affected.
|
||||
(PR [#4325](https://github.com/pipecat-ai/pipecat/pull/4325))
|
||||
|
||||
- Fixed `ElevenLabsTTSService` and `ElevenLabsHttpTTSService` emitting word
|
||||
timestamps and `TTSTextFrame` content that matched the input text instead of
|
||||
the spoken audio when a pronunciation dictionary
|
||||
(`pronunciation_dictionary_locators`) or text normalization rewrote the
|
||||
input. Both services now consume ElevenLabs' normalized alignment, so
|
||||
downstream consumers (captions, transcripts, context aggregation) reflect
|
||||
what the listener actually hears.
|
||||
(PR [#4344](https://github.com/pipecat-ai/pipecat/pull/4344))
|
||||
|
||||
- Fixed a crash in `DeepgramSTTService` when an `STTUpdateSettingsFrame`
|
||||
arrived before the WebSocket handshake completed (for example, when pushing
|
||||
an update upstream on `StartFrame`). The settings-triggered reconnect
|
||||
cancelled the in-flight connection task before its keepalive task was
|
||||
created, causing an `UnboundLocalError: cannot access local variable
|
||||
'keepalive_task'` in the handler's `finally` block.
|
||||
(PR [#4347](https://github.com/pipecat-ai/pipecat/pull/4347))
|
||||
|
||||
- Fixed direct-function registration crashing for functions without a
|
||||
docstring. `DirectFunctionWrapper` passed `inspect.getdoc()`'s result to
|
||||
`docstring_parser.parse()`, which raises when the docstring is `None`.
|
||||
Functions now register cleanly whether or not they have a docstring; an empty
|
||||
docstring produces empty description and parameter metadata as expected.
|
||||
(PR [#4352](https://github.com/pipecat-ai/pipecat/pull/4352))
|
||||
|
||||
- Fixed `AssemblyAISTTService`, `CartesiaSTTService`, `GradiumSTTService`, and
|
||||
`SonioxSTTService` crashing the pipeline on transient WebSocket send
|
||||
failures. Each `run_stt` sent audio directly without catching errors, so a
|
||||
single network hiccup mid-stream raised an uncaught exception through
|
||||
`process_frame`. The guards now log a warning and let the connection-state
|
||||
check on the next call handle recovery, matching the pattern used by
|
||||
Deepgram, xAI, Azure, and other push-based STTs.
|
||||
(PR [#4352](https://github.com/pipecat-ai/pipecat/pull/4352))
|
||||
|
||||
- Fixed Gemini Live losing conversation history in the (rare) case of a
|
||||
WebSocket reconnect before any session resumption handle is received. When
|
||||
the session reconnects (e.g. on system instruction change), conversation
|
||||
history is now re-seeded into the new session before it is marked ready for
|
||||
input.
|
||||
(PR [#4355](https://github.com/pipecat-ai/pipecat/pull/4355))
|
||||
|
||||
- Fixed SmallWebRTC data channel silently stalling on networks with a 1280-byte
|
||||
MTU (IPv6, Tailscale overlays, many consumer VPNs). aiortc's default SCTP
|
||||
chunk size of 1200 bytes produces ~1305-byte UDP datagrams after headers,
|
||||
which the kernel rejects with EMSGSIZE; aiortc has no path-MTU discovery so
|
||||
it retransmits forever at the same oversized size. The chunk size is now
|
||||
clamped to 1100 bytes (~1205-byte datagrams, ~75 bytes of slack). Override
|
||||
with `PIPECAT_SCTP_MAX_CHUNK_SIZE` if your path MTU requires a different
|
||||
value.
|
||||
(PR [#4358](https://github.com/pipecat-ai/pipecat/pull/4358))
|
||||
|
||||
## [1.0.0] - 2026-04-14
|
||||
|
||||
Migration guide: https://docs.pipecat.ai/pipecat/migration/migration-1.0
|
||||
|
||||
158
CLAUDE.md
158
CLAUDE.md
@@ -1 +1,157 @@
|
||||
@AGENTS.md
|
||||
# CLAUDE.md
|
||||
|
||||
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
|
||||
|
||||
## Project Overview
|
||||
|
||||
Pipecat is an open-source Python framework for building real-time voice and multimodal conversational AI agents. It orchestrates audio/video, AI services, transports, and conversation pipelines using a frame-based architecture.
|
||||
|
||||
## Common Commands
|
||||
|
||||
```bash
|
||||
# Setup development environment
|
||||
uv sync --group dev --all-extras --no-extra gstreamer
|
||||
|
||||
# Install pre-commit hooks
|
||||
uv run pre-commit install
|
||||
|
||||
# Run all tests
|
||||
uv run pytest
|
||||
|
||||
# Run a single test file
|
||||
uv run pytest tests/test_name.py
|
||||
|
||||
# Run a specific test
|
||||
uv run pytest tests/test_name.py::test_function_name
|
||||
|
||||
# Preview changelog
|
||||
uv run towncrier build --draft --version Unreleased
|
||||
|
||||
# Lint and format check
|
||||
uv run ruff check
|
||||
uv run ruff format --check
|
||||
|
||||
# Update dependencies (after editing pyproject.toml)
|
||||
uv lock && uv sync
|
||||
```
|
||||
|
||||
## Architecture
|
||||
|
||||
### Frame-Based Pipeline Processing
|
||||
|
||||
All data flows as **Frame** objects through a pipeline of **FrameProcessors**:
|
||||
|
||||
```
|
||||
[Processor1] → [Processor2] → ... → [ProcessorN]
|
||||
```
|
||||
|
||||
**Key components:**
|
||||
|
||||
- **Frames** (`src/pipecat/frames/frames.py`): Data units (audio, text, video) and control signals. Flow DOWNSTREAM (input→output) or UPSTREAM (acknowledgments/errors).
|
||||
|
||||
- **FrameProcessor** (`src/pipecat/processors/frame_processor.py`): Base processing unit. Each processor receives frames, processes them, and pushes results downstream.
|
||||
|
||||
- **Pipeline** (`src/pipecat/pipeline/pipeline.py`): Chains processors together.
|
||||
|
||||
- **ParallelPipeline** (`src/pipecat/pipeline/parallel_pipeline.py`): Runs multiple pipelines in parallel.
|
||||
|
||||
- **Transports** (`src/pipecat/transports/`): Transports are frame processors used for external I/O layer (Daily WebRTC, LiveKit WebRTC, WebSocket, Local). Abstract interface via `BaseTransport`, `BaseInputTransport` and `BaseOutputTransport`.
|
||||
|
||||
- **Pipeline Task (`src/pipecat/pipeline/task.py`)**: Runs and manages a pipeline. Pipeline tasks send the first frame, `StartFrame`, to the pipeline in order for processors to know they can start processing and pushing frames. Pipeline tasks internally create a pipeline with two additional processors, a source processor before the user-defined pipeline and a sink processor at the end. Those are used for multiple things: error handling, pipeline task level events, heartbeat monitoring, etc.
|
||||
|
||||
- **Pipeline Runner (`src/pipecat/pipeline/runner.py`)**: High-level entry point for executing pipeline tasks. Handles signal management (SIGINT/SIGTERM) for graceful shutdown and optional garbage collection. Run a single pipeline task with `await runner.run(task)` or multiple concurrently with `await asyncio.gather(runner.run(task1), runner.run(task2))`.
|
||||
|
||||
- **Services** (`src/pipecat/services/`): 60+ AI provider integrations (STT, TTS, LLM, etc.). Extend base classes: `AIService`, `LLMService`, `STTService`, `TTSService`, `VisionService`.
|
||||
|
||||
- **Serializers** (`src/pipecat/serializers/`): Convert frames to/from wire formats for WebSocket transports. `FrameSerializer` base class defines `serialize()` and `deserialize()`. Telephony serializers (Twilio, Plivo, Vonage, Telnyx, Exotel, Genesys) handle provider-specific protocols and audio encoding (e.g., μ-law).
|
||||
|
||||
- **RTVI** (`src/pipecat/processors/frameworks/rtvi.py`): Real-Time Voice Interface protocol bridging clients and the pipeline. `RTVIProcessor` handles incoming client messages (text input, audio, function call results). `RTVIObserver` converts pipeline frames to outgoing messages: user/bot speaking events, transcriptions, LLM/TTS lifecycle, function calls, metrics, and audio levels.
|
||||
|
||||
- **Observers** (`src/pipecat/observers/`): Monitor frame flow without modifying the pipeline. Passed to `PipelineTask` via the `observers` parameter. Implement `on_process_frame()` and `on_push_frame()` callbacks.
|
||||
|
||||
### Important Patterns
|
||||
|
||||
- **Context Aggregation**: `LLMContext` accumulates messages for LLM calls; `UserResponse` aggregates user input
|
||||
|
||||
- **Turn Management**: Turn management is done through `LLMUserAggregator` and
|
||||
`LLMAssistantAggregator`, created with `LLMContextAggregatorPair`
|
||||
|
||||
- **User turn strategies**: Detection of when the user starts and stops speaking is done via user turn start/stop strategies. They push `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` respectively.
|
||||
|
||||
- **Interruptions**: Interruptions are usually triggered by a user turn start strategy (e.g. `VADUserTurnStartStrategy`) but they can be triggered by other processors as well, in which case the user turn start strategies don't need to. An `InterruptionFrame` carries an optional `asyncio.Event` that is set when the frame reaches the pipeline sink. If a processor stops an `InterruptionFrame` from propagating downstream (i.e., doesn't push it), it **must** call `frame.complete()` to avoid stalling `push_interruption_task_frame_and_wait()` callers.
|
||||
|
||||
- **Uninterruptible Frames**: These are frames that will not be removed from internal queues even if there's an interruption. For example, `EndFrame` and `StopFrame`.
|
||||
|
||||
- **Events**: Most classes in Pipecat have `BaseObject` as the very base class. `BaseObject` has support for events. Events can run in the background in an async task (default) or synchronously (`sync=True`) if we want immediate action. Synchronous event handlers need to execute fast.
|
||||
|
||||
- **Async Task Management**: Always use `self.create_task(coroutine, name)` instead of raw `asyncio.create_task()`. The `TaskManager` automatically tracks tasks and cleans them up on processor shutdown. Use `await self.cancel_task(task, timeout)` for cancellation.
|
||||
|
||||
- **Error Handling**: Use `await self.push_error(msg, exception, fatal)` to push errors upstream. Services should use `fatal=False` (the default) so application code can handle errors and take action (e.g. switch to another service).
|
||||
|
||||
### Key Directories
|
||||
|
||||
| Directory | Purpose |
|
||||
| -------------------------- | -------------------------------------------------- |
|
||||
| `src/pipecat/frames/` | Frame definitions (100+ types) |
|
||||
| `src/pipecat/processors/` | FrameProcessor base + aggregators, filters, audio |
|
||||
| `src/pipecat/pipeline/` | Pipeline orchestration |
|
||||
| `src/pipecat/services/` | AI service integrations (60+ providers) |
|
||||
| `src/pipecat/transports/` | Transport layer (Daily, LiveKit, WebSocket, Local) |
|
||||
| `src/pipecat/serializers/` | Frame serialization for WebSocket protocols |
|
||||
| `src/pipecat/observers/` | Pipeline observers for monitoring frame flow |
|
||||
| `src/pipecat/audio/` | VAD, filters, mixers, turn detection, DTMF |
|
||||
| `src/pipecat/turns/` | User turn management |
|
||||
|
||||
## Code Style
|
||||
|
||||
- **Docstrings**: Google-style. Classes describe purpose; `__init__` has `Args:` section; dataclasses use `Parameters:` section.
|
||||
- **Linting**: Ruff (line length 100). Pre-commit hooks enforce formatting.
|
||||
- **Type hints**: Required for complex async code.
|
||||
- **Dataclass vs Pydantic**: Use `@dataclass` for frames and internal pipeline data (high-frequency, no validation needed). Use Pydantic `BaseModel` for configuration, parameters, metrics, and external API data (benefits from validation and serialization). Specifically:
|
||||
- `@dataclass`: Frame types, context aggregator pairs, internal data containers
|
||||
- `BaseModel`: Service `InputParams`, transport/VAD/turn params, metrics data, API request/response models, serializer params
|
||||
|
||||
### Docstring Example
|
||||
|
||||
```python
|
||||
class MyService(LLMService):
|
||||
"""Description of what the service does.
|
||||
|
||||
More detailed description.
|
||||
|
||||
Event handlers available:
|
||||
|
||||
- on_connected: Called when we are connected
|
||||
|
||||
Example::
|
||||
|
||||
@service.event_handler("on_connected")
|
||||
async def on_connected(service, frame):
|
||||
...
|
||||
"""
|
||||
|
||||
def __init__(self, param1: str, **kwargs):
|
||||
"""Initialize the service.
|
||||
|
||||
Args:
|
||||
param1: Description of param1.
|
||||
**kwargs: Additional arguments passed to parent.
|
||||
"""
|
||||
super().__init__(**kwargs)
|
||||
```
|
||||
|
||||
## Service Implementation
|
||||
|
||||
When adding a new service:
|
||||
|
||||
1. Extend the appropriate base class (`STTService`, `TTSService`, `LLMService`, etc.)
|
||||
2. Implement required abstract methods
|
||||
3. Handle necessary frames
|
||||
4. By default, all frames should be pushed in the direction they came
|
||||
5. Push `ErrorFrame` on failures
|
||||
6. Add metrics tracking via `MetricsData` if relevant
|
||||
7. Follow the pattern of existing services in `src/pipecat/services/`
|
||||
|
||||
## Testing
|
||||
|
||||
Test utilities live in `src/pipecat/tests/utils.py`. Use `run_test()` to send frames through a pipeline and assert expected output frames in each direction. Use `SleepFrame(sleep=N)` to add delays between frames.
|
||||
|
||||
36
README.md
36
README.md
@@ -28,10 +28,6 @@
|
||||
|
||||
## 🌐 Pipecat Ecosystem
|
||||
|
||||
### 🧩 Multi-agent systems
|
||||
|
||||
Need multiple AI agents working together? [Pipecat Subagents](https://github.com/pipecat-ai/pipecat-subagents) lets you build distributed multi-agent systems where each agent runs its own pipeline and communicates through a shared message bus. Hand off conversations between specialists, dispatch background tasks, and scale agents across processes or machines.
|
||||
|
||||
### 📱 Client SDKs
|
||||
|
||||
Building client applications? You can connect to Pipecat from any platform using our official SDKs:
|
||||
@@ -71,7 +67,7 @@ and install any of the available plugins.
|
||||
|
||||
### 🧩 Community Integrations
|
||||
|
||||
Build and share your own Pipecat service integrations! Browse existing [community integrations](https://docs.pipecat.ai/api-reference/server/services/community-integrations) or check out our [guide](COMMUNITY_INTEGRATIONS.md) to create your own.
|
||||
Build and share your own Pipecat service integrations! Browse existing [community integrations](https://docs.pipecat.ai/server/services/community-integrations) or check out our [guide](COMMUNITY_INTEGRATIONS.md) to create your own.
|
||||
|
||||
### 📺️ Pipecat TV Channel
|
||||
|
||||
@@ -89,22 +85,22 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
|
||||
|
||||
## 🧩 Available services
|
||||
|
||||
| Category | Services |
|
||||
| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/api-reference/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/api-reference/server/services/stt/aws), [Azure](https://docs.pipecat.ai/api-reference/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/api-reference/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/api-reference/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/api-reference/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/api-reference/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/api-reference/server/services/stt/gladia), [Google](https://docs.pipecat.ai/api-reference/server/services/stt/google), [Gradium](https://docs.pipecat.ai/api-reference/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/api-reference/server/services/stt/groq), [Mistral](https://docs.pipecat.ai/api-reference/server/services/stt/mistral), [NVIDIA](https://docs.pipecat.ai/api-reference/server/services/stt/nvidia), [OpenAI (Whisper)](https://docs.pipecat.ai/api-reference/server/services/stt/openai), [Sarvam](https://docs.pipecat.ai/api-reference/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/api-reference/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/api-reference/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/api-reference/server/services/stt/whisper), [xAI](https://docs.pipecat.ai/api-reference/server/services/stt/xai) |
|
||||
| LLMs | [Anthropic](https://docs.pipecat.ai/api-reference/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/api-reference/server/services/llm/aws), [Azure](https://docs.pipecat.ai/api-reference/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/api-reference/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/api-reference/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/api-reference/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/api-reference/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/api-reference/server/services/llm/grok), [Groq](https://docs.pipecat.ai/api-reference/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/api-reference/server/services/llm/mistral), [Nebius](https://docs.pipecat.ai/api-reference/server/services/llm/nebius), [Novita](https://docs.pipecat.ai/api-reference/server/services/llm/novita), [NVIDIA NIM](https://docs.pipecat.ai/api-reference/server/services/llm/nvidia), [Ollama](https://docs.pipecat.ai/api-reference/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/api-reference/server/services/llm/openai), [OpenAI Responses](https://docs.pipecat.ai/api-reference/server/services/llm/openai-responses), [OpenRouter](https://docs.pipecat.ai/api-reference/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/api-reference/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/api-reference/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/api-reference/server/services/llm/sambanova), [Sarvam](https://docs.pipecat.ai/api-reference/server/services/llm/sarvam), [Together AI](https://docs.pipecat.ai/api-reference/server/services/llm/together) |
|
||||
| Text-to-Speech | [Async](https://docs.pipecat.ai/api-reference/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/api-reference/server/services/tts/aws), [Azure](https://docs.pipecat.ai/api-reference/server/services/tts/azure), [Camb AI](https://docs.pipecat.ai/api-reference/server/services/tts/camb), [Cartesia](https://docs.pipecat.ai/api-reference/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/api-reference/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/api-reference/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/api-reference/server/services/tts/fish), [Google](https://docs.pipecat.ai/api-reference/server/services/tts/google), [Gradium](https://docs.pipecat.ai/api-reference/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/api-reference/server/services/tts/groq), [Hume](https://docs.pipecat.ai/api-reference/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/api-reference/server/services/tts/inworld), [Kokoro](https://docs.pipecat.ai/api-reference/server/services/tts/kokoro), [LMNT](https://docs.pipecat.ai/api-reference/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/api-reference/server/services/tts/minimax), [Mistral](https://docs.pipecat.ai/api-reference/server/services/tts/mistral), [Neuphonic](https://docs.pipecat.ai/api-reference/server/services/tts/neuphonic), [NVIDIA](https://docs.pipecat.ai/api-reference/server/services/tts/nvidia), [OpenAI](https://docs.pipecat.ai/api-reference/server/services/tts/openai), [Piper](https://docs.pipecat.ai/api-reference/server/services/tts/piper), [Resemble](https://docs.pipecat.ai/api-reference/server/services/tts/resemble), [Rime](https://docs.pipecat.ai/api-reference/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/api-reference/server/services/tts/sarvam), [Smallest](https://docs.pipecat.ai/api-reference/server/services/tts/smallest), [Soniox](https://docs.pipecat.ai/api-reference/server/services/tts/soniox), [Speechmatics](https://docs.pipecat.ai/api-reference/server/services/tts/speechmatics), [xAI](https://docs.pipecat.ai/api-reference/server/services/tts/xai), [XTTS](https://docs.pipecat.ai/api-reference/server/services/tts/xtts) |
|
||||
| Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/api-reference/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/api-reference/server/services/s2s/gemini), [Grok Voice Agent](https://docs.pipecat.ai/api-reference/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/api-reference/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/api-reference/server/services/s2s/ultravox), |
|
||||
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/api-reference/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/api-reference/server/services/transport/fastapi-websocket), [LiveKit (WebRTC)](https://docs.pipecat.ai/api-reference/server/services/transport/livekit), [SmallWebRTCTransport](https://docs.pipecat.ai/api-reference/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/api-reference/server/services/transport/websocket-server), [WhatsApp](https://docs.pipecat.ai/api-reference/server/services/transport/whatsapp), Local |
|
||||
| Serializers | [Exotel](https://docs.pipecat.ai/api-reference/server/services/serializers/exotel), [Genesys](https://docs.pipecat.ai/api-reference/server/services/serializers/genesys), [Plivo](https://docs.pipecat.ai/api-reference/server/services/serializers/plivo), [Twilio](https://docs.pipecat.ai/api-reference/server/services/serializers/twilio), [Telnyx](https://docs.pipecat.ai/api-reference/server/services/serializers/telnyx), [Vonage](https://docs.pipecat.ai/api-reference/server/services/serializers/vonage) |
|
||||
| Video | [HeyGen](https://docs.pipecat.ai/api-reference/server/services/video/heygen), [LemonSlice](https://docs.pipecat.ai/api-reference/server/services/transport/lemonslice), [Tavus](https://docs.pipecat.ai/api-reference/server/services/video/tavus), [Simli](https://docs.pipecat.ai/api-reference/server/services/video/simli) |
|
||||
| Memory | [mem0](https://docs.pipecat.ai/api-reference/server/services/memory/mem0) |
|
||||
| Vision & Image | [fal](https://docs.pipecat.ai/api-reference/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/api-reference/server/services/image-generation/google-imagen), [Moondream](https://docs.pipecat.ai/api-reference/server/services/vision/moondream) |
|
||||
| Audio Processing | [Silero VAD](https://docs.pipecat.ai/api-reference/server/utilities/audio/silero-vad-analyzer), [Krisp Viva](https://docs.pipecat.ai/guides/features/krisp-viva), [Koala](https://docs.pipecat.ai/api-reference/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/api-reference/server/utilities/audio/aic-filter), [RNNoise](https://docs.pipecat.ai/api-reference/server/utilities/audio/rnnoise-filter) |
|
||||
| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/api-reference/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/api-reference/server/services/analytics/sentry) |
|
||||
| Community | [Browse community integrations →](https://docs.pipecat.ai/api-reference/server/services/community-integrations) |
|
||||
| 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), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
|
||||
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [Nebius](https://docs.pipecat.ai/server/services/llm/nebius), [Novita](https://docs.pipecat.ai/server/services/llm/novita), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nvidia), [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), [Sarvam](https://docs.pipecat.ai/server/services/llm/sarvam), [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
|
||||
| Text-to-Speech | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [Kokoro](https://docs.pipecat.ai/server/services/tts/kokoro), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [Resemble](https://docs.pipecat.ai/server/services/tts/resemble), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Smallest](https://docs.pipecat.ai/server/services/tts/smallest), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [xAI](https://docs.pipecat.ai/server/services/tts/xai), [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), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox), |
|
||||
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [LiveKit (WebRTC)](https://docs.pipecat.ai/server/services/transport/livekit), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), [WhatsApp](https://docs.pipecat.ai/server/services/transport/whatsapp), Local |
|
||||
| Serializers | [Exotel](https://docs.pipecat.ai/server/services/serializers/exotel), [Genesys](https://docs.pipecat.ai/server/services/serializers/genesys), [Plivo](https://docs.pipecat.ai/server/services/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/services/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/services/serializers/telnyx), [Vonage](https://docs.pipecat.ai/server/services/serializers/vonage) |
|
||||
| Video | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [LemonSlice](https://docs.pipecat.ai/server/services/transport/lemonslice), [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/google-imagen), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream) |
|
||||
| Audio Processing | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp Viva](https://docs.pipecat.ai/guides/features/krisp-viva), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter), [RNNoise](https://docs.pipecat.ai/server/utilities/audio/rnnoise-filter) |
|
||||
| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) |
|
||||
| Community | [Browse community integrations →](https://docs.pipecat.ai/server/services/community-integrations) |
|
||||
|
||||
📚 [View full services documentation →](https://docs.pipecat.ai/api-reference/server/services/supported-services)
|
||||
📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
|
||||
|
||||
## ⚡ Getting started
|
||||
|
||||
|
||||
1
changelog/4304.fixed.md
Normal file
1
changelog/4304.fixed.md
Normal file
@@ -0,0 +1 @@
|
||||
- Fixed `pipecat-ai[tavus]` not installing the required `daily-python` dependency. Installing the `tavus` extra now correctly pulls in `pipecat-ai[daily]`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added a `session_id` field to `RunnerArguments` so bots can log or trace a per-session identifier in local development the same way they can in Pipecat Cloud. The development runner now mints a UUID at every construction site, and paths that already returned a `sessionId` to the caller (Daily `/start`, dial-in webhook) share that same UUID with the runner args instead of generating two. The SmallWebRTC `/api/offer` endpoint also accepts an optional `session_id` query parameter so the `/sessions/{session_id}/...` proxy can thread it through.
|
||||
@@ -1 +0,0 @@
|
||||
- Updated the default `SonioxTTSService` model from `tts-rt-v1-preview` to the generally available `tts-rt-v1`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added a `max_buffer_delay_ms` constructor argument to `CartesiaTTSService` for controlling Cartesia's server-side text buffering. When unset, Pipecat picks a sensible default based on `text_aggregation_mode`: `0` in `SENTENCE` mode (custom buffering — avoids stacking client-side aggregation on top of Cartesia's default 3000ms server buffer) and unset in `TOKEN` mode (Cartesia's managed buffering applies). Pass an explicit value (0–5000ms) to override.
|
||||
@@ -1 +0,0 @@
|
||||
- Default `cartesia_version` for `CartesiaTTSService` bumped from `2025-04-16` to `2026-03-01`, matching `CartesiaHttpTTSService` and unlocking the `use_normalized_timestamps` and `max_buffer_delay_ms` fields.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ `CartesiaTTSService` now sends `use_normalized_timestamps: true` instead of the deprecated `use_original_timestamps` field. Word timestamps now reflect what was actually spoken (post text-normalization and pronunciation-dictionary substitution), matching the convention Pipecat uses for ElevenLabs. This is a behavior change for `sonic-3` users, who were previously receiving timestamps tied to the input transcript.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed `CartesiaHttpTTSService` pushing two `ErrorFrame`s on a non-200 response — one with the API's error text and a second, less informative "Unknown error" frame from the outer exception handler. It now pushes a single frame that includes the HTTP status code and returns cleanly.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed Cartesia tag helpers (`SPELL`, `EMOTION_TAG`, `PAUSE_TAG`, `VOLUME_TAG`, `SPEED_TAG`) raising `TypeError` when called on an instance (e.g. `tts.SPELL("hi")`). They're now `@staticmethod` and callable from both the class and an instance.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed `CartesiaTTSService` surfacing `flush_done` messages from Cartesia as `ErrorFrame`s. The latest API emits a `flush_done` per transcript when server-side buffering is disabled; Pipecat now consumes them silently since each turn already has its own `context_id`.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed an issue where `LocalSmartTurnAnalyzerV3` was imported unconditionally for user turn stop strategies. It is now only imported when `default_user_turn_stop_strategies()` is called. This improves startup time and removes the `transformers` "PyTorch/TensorFlow/Flax not found" warning when the default stop strategies are not used.
|
||||
@@ -1 +0,0 @@
|
||||
- Broadened `tool_resources` to `app_resources` for easy access not just in tool handlers but in other places like custom `FrameProcessor`s. Three changes: a rename (`tool_resources` → `app_resources`), a new `app_resources` property on `PipelineTask`, and a new `pipeline_task` property on `FrameProcessor`. Tool handlers now read `params.app_resources`; custom processors read `self.pipeline_task.app_resources`. The previous `tool_resources` aliases (on `PipelineTask`, `FunctionCallParams`, and `FrameProcessorSetup`) keep working but are deprecated as of 1.2.0 and emit `DeprecationWarning`s.
|
||||
@@ -1 +0,0 @@
|
||||
- Lowered the per-message log in `SmallWebRTCInputTransport._handle_app_message` from `debug` to `trace`. App messages can be high-frequency and were noisy at debug level; set the loguru level to `TRACE` to see them again.
|
||||
@@ -1 +0,0 @@
|
||||
- Added a `mip_opt_out` constructor argument to `DeepgramTTSService` and `DeepgramHttpTTSService` so callers can opt out of the Deepgram Model Improvement Program. When set, the value is forwarded to Deepgram as a query parameter on the speak request. Defaults to `None`, which preserves the existing behavior. See https://dpgr.am/deepgram-mip for pricing implications before enabling.
|
||||
@@ -1 +0,0 @@
|
||||
- Changed the default model for `GrokRealtimeLLMService` to `grok-voice-think-fast-1.0`, xAI's recommended Voice Agent model. The previous default of `grok-voice-fast-1.0` has been deprecated by xAI and is being removed.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed `GrokRealtimeLLMService` ignoring the configured model. The model was stored in `Settings` but never sent to xAI, so every session silently fell back to xAI's server-side default. The model is now passed via the `?model=` query parameter on the WebSocket URL as xAI's Voice Agent API requires.
|
||||
@@ -1 +0,0 @@
|
||||
- Added an opt-in `add_tool_change_messages` flag to the LLM aggregators (set via `LLMContextAggregatorPair(..., add_tool_change_messages=True)`) that appends a developer-role message to the context whenever `LLMSetToolsFrame` changes the set of advertised standard tools. Helps the LLM stay coherent across mid-conversation tool changes, mitigating several flavors of tool-call-related hallucination: calling tools that have been removed, avoiding tools that have been re-added, and hallucinating output (made-up answers or tool-call-shaped non-tool-calls) when tools are unavailable.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `LLMTurnCompletionUserTurnStopStrategy` in `pipecat.turns.user_stop`. When installed, the strategy gates `on_user_turn_stopped` on a `UserTurnInferenceCompletedFrame` (a new fieldless system frame emitted by any component that can judge turn completeness — e.g. the `UserTurnCompletionLLMServiceMixin` on `✓`). A `finalization_timeout` provides a safety net if no completion frame ever arrives.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `deferred(strategy)` and `DeferredUserTurnStopStrategy` in `pipecat.turns.user_stop`. Wraps a stop strategy so it fires only the inference-triggered event and suppresses `on_user_turn_stopped`, leaving finalization to another strategy in the chain such as `LLMTurnCompletionUserTurnStopStrategy`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `FilterIncompleteUserTurnStrategies` in `pipecat.turns.user_turn_strategies` — a `UserTurnStrategies` specialization that wraps the detector chain with `deferred(...)` and appends `LLMTurnCompletionUserTurnStopStrategy` as the finalizer. Common case: `user_turn_strategies=FilterIncompleteUserTurnStrategies()`. Pass `config=UserTurnCompletionConfig(...)` to customize timeouts and prompts.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `ExternalUserTurnCompletionStopStrategy` in `pipecat.turns.user_stop` — a generic stop strategy that finalizes the user turn whenever a `UserTurnInferenceCompletedFrame` arrives, regardless of which component produced it. `LLMTurnCompletionUserTurnStopStrategy` now extends this base; future producers (Flux, custom end-of-turn classifiers, etc.) can use the base directly or subclass it to add producer-specific setup.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `on_user_turn_inference_triggered`, a new event on the user turn controller, processor, aggregator and stop strategies that fires when a strategy has enough signal to start LLM inference. By default it fires together with `on_user_turn_stopped`; a gating strategy can fire only the inference-triggered event and defer finalization to a peer.
|
||||
@@ -1 +0,0 @@
|
||||
- Deprecated `LLMUserAggregatorParams.filter_incomplete_user_turns`. Use `user_turn_strategies=FilterIncompleteUserTurnStrategies()` (or add `LLMTurnCompletionUserTurnStopStrategy` to a custom `user_turn_strategies.stop`) instead. Setting the legacy flag still works for one release: the aggregator emits a `DeprecationWarning` and rewires the strategies as if you had passed `FilterIncompleteUserTurnStrategies` directly.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed `on_user_turn_stopped` firing prematurely when `filter_incomplete_user_turns` was enabled. The event now fires only after the LLM confirms the user turn is complete (`✓`); previously the smart-turn detector's tentative stop was bubbling up before the LLM had a chance to veto it, causing observers, transcript appenders and UI indicators to receive an early — and sometimes duplicated — signal.
|
||||
@@ -1,6 +0,0 @@
|
||||
- Added first-class RTVI support for the UI Agent Protocol:
|
||||
- Adds `ui-event`, `ui-snapshot`, and `ui-cancel-task` client-to-server messages, plus `ui-command` and `ui-task` server-to-client messages, with paired `*Data` / `*Message` pydantic models.
|
||||
- Adds built-in command payload models for `Toast`, `Navigate`, `ScrollTo`, `Highlight`, `Focus`, `Click`, `SetInputValue`, and `SelectText`; matching default handlers live in `@pipecat-ai/client-react`.
|
||||
- Adds `RTVIProcessor.on_ui_message` for inbound `ui-event`, `ui-snapshot`, and `ui-cancel-task` messages.
|
||||
- Adds five UI pipeline frames, mirroring the `client-message` frame-and-event pattern: downstream code pushes `RTVIUICommandFrame` / `RTVIUITaskFrame` for the observer to wrap into outbound `UICommandMessage` / `UITaskMessage` envelopes, while the processor pushes inbound `RTVIUIEventFrame`, `RTVIUISnapshotFrame`, and `RTVIUICancelTaskFrame` alongside `on_ui_message`.
|
||||
- Bumps the RTVI `PROTOCOL_VERSION` from `1.2.0` to `1.3.0`.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed `TTSSpeakFrame(append_to_context=True)` greetings sometimes splitting across two assistant messages in the LLM context and not surfacing in `on_assistant_turn_stopped`. The `LLMAssistantPushAggregationFrame` emitted at the end of a TTS context now carries a PTS just past the last word so it can't overtake clock-queued `TTSTextFrame`s in the transport's output, and `LLMAssistantAggregator` now triggers `on_assistant_turn_started`/`on_assistant_turn_stopped` when it receives the frame outside an LLM response cycle (restoring v0.0.104 behavior for greeting transcripts).
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed `ElevenLabsTTSService` and `ElevenLabsHttpTTSService` producing merged words (e.g. `bookLook`) when using Flash models. Flash often splits sentences mid-stream into alignment chunks that begin with a real inter-word space, but the previous fix unconditionally stripped that space from every chunk. Leading spaces are now stripped only on the first alignment chunk of an utterance, so subsequent chunks correctly flush partial words across boundaries.
|
||||
@@ -1 +0,0 @@
|
||||
- AWS Transcribe STT, Polly TTS, Bedrock LLM, and the Bedrock AgentCore processor now resolve credentials via the standard boto3 provider chain (EC2 instance profiles, EKS pod roles / IRSA, ECS task roles, SSO, `~/.aws/credentials`) when explicit credentials and `AWS_*` environment variables are absent. Services running with IAM roles no longer need to export static credentials.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed AWS Polly TTS, Bedrock LLM, and the Bedrock AgentCore processor erroring out when only one of `AWS_ACCESS_KEY_ID` / `AWS_SECRET_ACCESS_KEY` was set in the environment. The half-populated kwargs are no longer forwarded to aioboto3; partial env-var configurations now fall through to the boto3 credential chain like fully-unset configurations do.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed a path traversal issue in the development runner's `/files/{filename:path}` download endpoint. Previously, when the runner was started with `--folder`, a request like `/files/..%2F..%2Fetc%2Fpasswd` could escape the configured folder because `%2F`-encoded separators bypassed Starlette's path normalisation. The endpoint now resolves the joined path and rejects any filename that escapes the allowed base with a 403, and also returns 404 (instead of an implicit `null` 200) when `--folder` is unset.
|
||||
@@ -1 +0,0 @@
|
||||
- Changed the default Inworld TTS model from `inworld-tts-1.5-max` to `inworld-tts-2` (Realtime TTS-2) across `InworldHttpTTSService`, `InworldTTSService`, and the `InworldRealtimeLLMService` cascade. Existing users can pin the prior model explicitly via the `model`/`tts_model` argument; both `inworld-tts-1.5-max` and `inworld-tts-1.5-mini` remain valid model IDs.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed `ElevenLabsTTSService` and `ElevenLabsHttpTTSService` writing romanized/normalized text to the LLM context. With non-Latin input (e.g., Chinese), the assistant transcript was getting populated with pinyin (`Ni Hao !` instead of `你好！`), which then degraded subsequent LLM turns. The services now consume `alignment` by default and only switch to `normalizedAlignment` / `normalized_alignment` when `pronunciation_dictionary_locators` is configured (where `alignment` has overlapping restarts that produce duplicated/garbled words, per #4316). Both fields are read with preferred-with-fallback semantics since each is nullable per the API schema.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `keyterms` support to ElevenLabs STT services so Scribe V2 callers can bias transcription for both file-based and realtime transcription.
|
||||
@@ -1 +0,0 @@
|
||||
- Deprecated `ResampyResampler` in favor of `SOXRAudioResampler` (or the `create_file_resampler()` / `create_stream_resampler()` factories). Instantiating `ResampyResampler` now emits a `DeprecationWarning`. The class will be removed in Pipecat 2.0 along with the default `resampy` and `numba` dependencies.
|
||||
@@ -1 +0,0 @@
|
||||
- Changed the default model for `GrokLLMService` from `grok-3` to `grok-4.20-non-reasoning`. xAI is retiring `grok-3` on May 15, 2026.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `watchdog_min_timeout` parameter to `DeepgramFluxSTT` and `DeepgramFluxSageMakerSTT` (default `0.5` seconds) to control the minimum silence duration before the watchdog sends a silence packet to prevent dangling turns. The actual threshold is `max(chunk_duration * 2, watchdog_min_timeout)`, so it also adapts automatically to the audio chunk size in use.
|
||||
@@ -1 +0,0 @@
|
||||
- `DeepgramFluxSTT` watchdog silence threshold is now dynamic: `max(chunk_duration * 2, watchdog_min_timeout)` instead of a fixed 500 ms. This prevents false silence injections when large audio chunks are sent at lower frequency.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed a deadlock in `TTSService` that could permanently stall pipeline processing when all three conditions occurred together: `pause_frame_processing=True`, an interruption arrived before any TTS audio was played, and an `UninterruptibleFrame` (e.g. `TTSUpdateSettingsFrame`, `FunctionCallResultFrame`) was in the processing queue at that moment. The process task would block on `__process_event.wait()` indefinitely because `BotStoppedSpeakingFrame` never arrives (no audio was played) and the interruption handler did not resume processing. Affects services using `pause_frame_processing=True` such as ElevenLabs, Rime, AsyncAI, Gradium, and ResembleAI.
|
||||
@@ -1 +0,0 @@
|
||||
- `ElevenLabsTTSService` now sends `close_context` to the server as soon as the turn is complete (on `on_turn_context_completed`) rather than waiting until all audio has finished playing back. The `isFinal` message from ElevenLabs is now used to signal `TTSStoppedFrame` and clean up the audio context, improving turn transition timing.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed interruptions being delayed when a slow non-uninterruptible frame was processing and an uninterruptible frame was waiting in the queue. The bot would stall until the slow frame finished instead of cancelling it immediately on interruption.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed `TTSService` dropping uninterruptible frames (e.g. `FunctionCallResultFrame`) from its internal serialization queue when an interruption occurs. Previously, the queue was recreated on every interruption, silently discarding any queued frames. The queue is now reset instead of recreated, preserving uninterruptible frames so they are always delivered downstream.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed a race condition in the Daily transport that caused `AttributeError: 'NoneType' object has no attribute 'send_app_message'` when tearing down a pipeline. Both `DailyInputTransport` and `DailyOutputTransport` share the same `DailyTransportClient` and both call `cleanup()`, which was releasing the underlying `CallClient` on the first call — leaving the second caller with a `None` client.
|
||||
@@ -1 +0,0 @@
|
||||
- Restored `cancel_on_interruption=False` support for `AWSNovaSonicLLMService` and `OpenAIRealtimeLLMService`. These services previously honored the flag by simply not cancelling in-flight function calls on interruption; the introduction of the new async-tool mechanism (which threads started/intermediate/final messages through the LLM context) broke that path because the realtime services didn't know how to interpret those messages. Note that new-style streamed intermediate results (`FunctionCallResultProperties(is_final=False)`) are not supported on these realtime services. Similar fixes for other impacted realtime services are forthcoming.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed two misspelled Gemini TTS voice names in `GeminiTTSService.AVAILABLE_VOICES`.
|
||||
@@ -1 +0,0 @@
|
||||
- Updated `InworldHttpTTSService` and `InworldTTSService` to use PCM audio encoding by default, which returns audio bytes without headers.
|
||||
@@ -1 +0,0 @@
|
||||
- Extended the `cancel_on_interruption=False` regression fix to `GrokRealtimeLLMService`, `AzureRealtimeLLMService`, and `UltravoxRealtimeLLMService`. Grok and Azure use the same approach as in #4441 (each service detects async-tool messages in the LLM context and routes the final result to its formal tool-result channel; Azure inherits transitively from `OpenAIRealtimeLLMService`). Ultravox needed a different approach because its API freezes the conversation between `client_tool_invocation` and the matching `client_tool_result` — for async-registered functions it now ships a placeholder `client_tool_result` immediately when the function is invoked (to unfreeze the conversation), then injects the real result as user-side text once the tool finishes. Streamed intermediate results (`FunctionCallResultProperties(is_final=False)`) are still not supported on any of these realtime services. `GeminiLiveLLMService` and `InworldRealtimeLLMService` are excluded for now: Gemini Live's async-tool path needs deeper investigation, and Inworld appears to have a pre-existing problem with even simple tool calling on its Realtime API.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `cancel_on_interruption=False` support for `GeminiLiveLLMService` on models that support Gemini's NON_BLOCKING tool mechanism (currently Gemini 2.x); the conversation now continues while the tool runs. On models that don't yet support NON_BLOCKING (Gemini 3.x), the service surfaces a one-time warning explaining the limitation. (Note: an intermittent 1008 error can occasionally fire on Gemini 2.5 during long-running tool calls; we auto-reconnect.)
|
||||
@@ -1 +0,0 @@
|
||||
- Moved `create_task`, `cancel_task`, the `task_manager` property, and `setup(task_manager)` up from `FrameProcessor` to `BaseObject`. Custom `BaseObject` subclasses (turn strategies, controllers, etc.) now inherit these methods directly instead of reimplementing the task manager wiring. Owners propagate the task manager to their child `BaseObject`s via `await child.setup(task_manager)`.
|
||||
@@ -1 +0,0 @@
|
||||
- Changed the default OpenAI Realtime input audio transcription model from `gpt-4o-transcribe` to `gpt-realtime-whisper` for both `OpenAIRealtimeSTTService` and `OpenAIRealtimeLLMService`. The new model does not accept the `prompt` parameter; if a prompt is supplied alongside `gpt-realtime-whisper`, it is dropped automatically and a warning is logged. To keep using prompt hints, explicitly pin `model="gpt-4o-transcribe"` (or `"gpt-4o-mini-transcribe"`).
|
||||
@@ -1 +0,0 @@
|
||||
- Updated the default model for `CartesiaTTSService` and `CartesiaHttpTTSService` from `sonic-3` to `sonic-3.5`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added NVIDIA Magpie TTS services via AWS SageMaker: `NvidiaSageMakerHTTPTTSService` (single HTTP invocation, streams raw PCM back) and `NvidiaSageMakerWebsocketTTSService` (persistent HTTP/2 bidi-stream with full interruption support via `InterruptibleTTSService`).
|
||||
@@ -1 +0,0 @@
|
||||
- Added `NvidiaSageMakerWebsocketSTTService` for streaming speech recognition using NVIDIA Nemotron ASR via an AWS SageMaker bidirectional-stream endpoint. Produces `InterimTranscriptionFrame` and `TranscriptionFrame` frames, is VAD-aware, and automatically reconnects on error.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed `OpenAIRealtimeLLMService` handling of multi-output-item responses (observed with `gpt-realtime-2`). A single response can now contain more than one audio item, and the first item's `audio.done` may arrive after the second item's deltas have started. Deltas still arrive strictly in playback order, so we continue to forward them as received (matching OpenAI's reference implementation). The fix removes spurious warnings, ensures truncation always targets the latest audio item, and emits a single bracketing `TTSStartedFrame`/`TTSStoppedFrame` pair per assistant turn (the Stopped is now pushed on `response.done`).
|
||||
@@ -1 +0,0 @@
|
||||
- Added support for `reasoning` configuration on `OpenAIRealtimeLLMService`, for use with reasoning-capable Realtime models such as `gpt-realtime-2`.
|
||||
@@ -1 +0,0 @@
|
||||
- Changed the default model for `OpenAIRealtimeLLMService` from `gpt-realtime-1.5` to `gpt-realtime-2`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `wait_for_transcript_to_end_user_turn` on `LLMUserAggregatorParams` for pipelines where local turn detection drives a realtime service like Gemini Live. Set it to False to avoid unnecessary latency from transcript delay — the realtime service consumes user audio directly, so we don't need user transcripts in context before it can respond. The option makes it so that (1) turn strategies do not consider user transcripts, letting the user turn end sooner, and (2) user transcripts are then handled by the aggregator: a simple timer gives it time to gather those transcripts after the user turn ends, and once gathered, the aggregator emits a new `on_user_turn_message_finalized` event with the new user context message. The new event also fires in the default mode (coinciding with `on_user_turn_stopped`), so consumers that want the populated user transcript can subscribe to it uniformly. See `examples/realtime/realtime-gemini-live-local-vad.py` for the full pattern.
|
||||
@@ -5,7 +5,7 @@
|
||||
|
||||
{% for text, values in sections[section][category].items() %}
|
||||
{{ text }}
|
||||
(PR {{ values|join(', ') }})
|
||||
(PR {{ values|join(', ') }})
|
||||
|
||||
{% endfor %}
|
||||
{% endfor %}
|
||||
|
||||
14
env.example
14
env.example
@@ -1,5 +1,5 @@
|
||||
# AI-COUSTICS
|
||||
AIC_LICENSE_KEY=...
|
||||
AICOUSTICS_LICENSE_KEY=...
|
||||
|
||||
# Anthropic
|
||||
ANTHROPIC_API_KEY=...
|
||||
@@ -132,10 +132,6 @@ NOVITA_API_KEY=...
|
||||
|
||||
# NVIDIA
|
||||
NVIDIA_API_KEY=...
|
||||
# For a full example of how to deploy to SageMaker, see:
|
||||
# https://github.com/pipecat-ai/pipecat-examples/tree/main/nvidia_sagemaker_example/deployment/aws-sagemaker-nvidia
|
||||
SAGEMAKER_ASR_ENDPOINT_NAME=...
|
||||
SAGEMAKER_MAGPIE_ENDPOINT_NAME=...
|
||||
|
||||
# OpenAI
|
||||
OPENAI_API_KEY=...
|
||||
@@ -218,10 +214,4 @@ WHATSAPP_PHONE_NUMBER_ID=...
|
||||
WHATSAPP_APP_SECRET=...
|
||||
|
||||
# xAI / Grok
|
||||
XAI_API_KEY=...
|
||||
|
||||
# PIPECAT_SCTP_MAX_CHUNK_SIZE controls the maximum SCTP DATA-chunk payload
|
||||
# size (bytes) used by aiortc's data channel. The default is 1100.
|
||||
# All the details here:
|
||||
# https://docs.pipecat.ai/api-reference/server/services/transport/small-webrtc#pipecat_sctp_max_chunk_size
|
||||
#PIPECAT_SCTP_MAX_CHUNK_SIZE=1100
|
||||
XAI_API_KEY=...
|
||||
@@ -71,17 +71,17 @@ transport_params = {
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
|
||||
@@ -108,17 +108,17 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"], audio_passthrough=True)
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"), audio_passthrough=True)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121",
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
|
||||
@@ -102,17 +102,17 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
|
||||
@@ -89,10 +89,10 @@ async def get_current_weather(params: FunctionCallParams):
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info("Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
@@ -109,7 +109,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
# Primary LLM for conversation (could be any provider)
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction=system_prompt,
|
||||
),
|
||||
@@ -117,7 +117,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
# Dedicated cheap/fast LLM for summarization only
|
||||
summarization_llm = GoogleLLMService(
|
||||
api_key=os.environ["GOOGLE_API_KEY"],
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
settings=GoogleLLMService.Settings(
|
||||
model="gemini-2.5-flash",
|
||||
),
|
||||
|
||||
@@ -77,17 +77,17 @@ async def get_current_weather(params: FunctionCallParams):
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info("Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = GoogleLLMService(
|
||||
api_key=os.environ["GOOGLE_API_KEY"],
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
settings=GoogleLLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way. You have access to tools to get the current weather - use them when relevant.",
|
||||
),
|
||||
|
||||
@@ -72,10 +72,10 @@ async def summarize_conversation(params: FunctionCallParams):
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info("Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
@@ -91,7 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
"""
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction=system_prompt,
|
||||
),
|
||||
|
||||
@@ -77,17 +77,17 @@ async def get_current_weather(params: FunctionCallParams):
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info("Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way. You have access to tools to get the current weather - use them when relevant.",
|
||||
),
|
||||
|
||||
@@ -1,232 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""Manual validation harness for the ``add_tool_change_messages`` feature.
|
||||
|
||||
When tools change mid-conversation, LLMs can produce a few different
|
||||
flavors of tool-call-related hallucination:
|
||||
|
||||
- **Forward hallucination** — calling a tool that has been removed.
|
||||
- **Negative hallucination** — refusing to call a tool that has been
|
||||
re-added (because recent context is full of "I can't" responses).
|
||||
- **Hallucinated output when tools are unavailable** — making up an
|
||||
answer rather than declining gracefully, or producing JSON that
|
||||
*looks* like a tool call but is actually just an assistant text
|
||||
response.
|
||||
|
||||
The ``add_tool_change_messages`` feature mitigates these by appending a
|
||||
developer-role message to the conversation whenever ``LLMSetToolsFrame``
|
||||
changes the set of advertised tools, so the LLM stays in sync with what's
|
||||
actually available.
|
||||
|
||||
This harness exercises all of those flavors by flipping the advertised
|
||||
tool set on a turn counter:
|
||||
|
||||
Phase 0 (turns 1–4): weather tool ACTIVE — confirm baseline.
|
||||
Phase 1 (turns 5–8): tool REMOVED — keep asking for weather.
|
||||
Phase 2 (turn 9+): tool RE-ADDED — does the LLM call it again?
|
||||
|
||||
Set ``ADD_TOOL_CHANGE_MESSAGES=0`` to disable the mitigation and see the
|
||||
unmitigated behavior. The default is ON so a fresh run shows the feature
|
||||
working.
|
||||
|
||||
Defaults to Llama 3.1 8B Instruct via a locally-running Ollama —
|
||||
anecdotally one of the more hallucination-prone of the easily accessible
|
||||
models. Pull the model once with ``ollama pull llama3.1:8b`` and make
|
||||
sure ``ollama serve`` is running. Swap the LLM service to validate other
|
||||
providers.
|
||||
|
||||
Run with::
|
||||
|
||||
uv run examples/features/features-add-tool-change-messages.py
|
||||
ADD_TOOL_CHANGE_MESSAGES=0 uv run examples/features/features-add-tool-change-messages.py
|
||||
"""
|
||||
|
||||
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 LLMRunFrame, LLMSetToolsFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import NOT_GIVEN, LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
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.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# Default ON so a fresh run shows the feature working. Set to "0" to A/B
|
||||
# against the unmitigated behavior.
|
||||
ADD_TOOL_CHANGE_MESSAGES = os.environ.get("ADD_TOOL_CHANGE_MESSAGES", "1") == "1"
|
||||
|
||||
|
||||
async def fetch_weather_from_api(params: FunctionCallParams):
|
||||
await params.result_callback({"conditions": "nice", "temperature": "75"})
|
||||
|
||||
|
||||
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"],
|
||||
)
|
||||
weather_tools = ToolsSchema(standard_tools=[weather_function])
|
||||
|
||||
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_in_enabled=True, audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_in_enabled=True, audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_in_enabled=True, audio_out_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(
|
||||
f"Starting add_tool_change_messages demo bot "
|
||||
f"(ADD_TOOL_CHANGE_MESSAGES={ADD_TOOL_CHANGE_MESSAGES})"
|
||||
)
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = OLLamaLLMService(
|
||||
settings=OLLamaLLMService.Settings(
|
||||
# Llama 3.1 8B Instruct is anecdotally one of the more
|
||||
# hallucination-prone of the easily accessible models — exactly
|
||||
# what we want for this validation harness. Pull it with
|
||||
# ``ollama pull llama3.1:8b`` and make sure ``ollama serve``
|
||||
# is running.
|
||||
model="llama3.1:8b",
|
||||
system_instruction=(
|
||||
"You are a helpful assistant in a voice conversation. Your responses "
|
||||
"will be spoken aloud, so avoid emojis, bullet points, or other "
|
||||
"formatting that can't be spoken. Respond briefly and naturally. "
|
||||
"If the user asks for the current weather, use the `get_current_weather` "
|
||||
"function if it's available. IMPORTANT: if you do not have access to the function, "
|
||||
"say something along the lines of 'Sorry, I can't check the weather right now.'."
|
||||
),
|
||||
),
|
||||
)
|
||||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
||||
|
||||
context = LLMContext(tools=weather_tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
add_tool_change_messages=ADD_TOOL_CHANGE_MESSAGES,
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
user_aggregator,
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
assistant_aggregator,
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(enable_metrics=True, enable_usage_metrics=True),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Phase controller: roughly 4 turns per phase.
|
||||
user_turn_count = 0
|
||||
REMOVE_AT_TURN = 5 # tool gone for turn N onward
|
||||
READD_AT_TURN = 9 # tool back for turn N onward
|
||||
|
||||
@user_aggregator.event_handler("on_user_turn_stopped")
|
||||
async def on_user_turn_stopped(aggregator, strategy, message):
|
||||
nonlocal user_turn_count
|
||||
user_turn_count += 1
|
||||
logger.info(f"=== User turn {user_turn_count} complete ===")
|
||||
|
||||
if user_turn_count == REMOVE_AT_TURN - 1:
|
||||
logger.info(
|
||||
"=== Phase 1: weather tool REMOVED. Keep asking about the weather "
|
||||
"to exercise hallucination scenarios. ==="
|
||||
)
|
||||
await task.queue_frame(LLMSetToolsFrame(tools=NOT_GIVEN))
|
||||
elif user_turn_count == READD_AT_TURN - 1:
|
||||
logger.info(
|
||||
"=== Phase 2: weather tool RE-ADDED. Ask for the weather again — "
|
||||
"does the LLM call it, or keep refusing? (THIS IS THE TEST.) ==="
|
||||
)
|
||||
await task.queue_frame(LLMSetToolsFrame(tools=weather_tools))
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info("Client connected")
|
||||
logger.info(
|
||||
"=== Phase 0: weather tool ACTIVE. Ask for the weather a few times "
|
||||
"to confirm it's working. ==="
|
||||
)
|
||||
context.add_message(
|
||||
{
|
||||
"role": "developer",
|
||||
"content": (
|
||||
"Please introduce yourself briefly to the user, then invite them "
|
||||
"to ask about the weather."
|
||||
),
|
||||
}
|
||||
)
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info("Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,327 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""Example demonstrating ``PipelineTask(app_resources=...)``.
|
||||
|
||||
``app_resources`` is an application-defined bag of anything your
|
||||
application code may want to share across a session: database handles,
|
||||
HTTP clients, feature flags, per-user state, observability clients,
|
||||
in-memory caches — whatever fits your app. Pipecat passes it through
|
||||
untouched and exposes it as ``task.app_resources``, so any code with a
|
||||
handle on the task can read or mutate it.
|
||||
|
||||
Two of the convenience aliases exercised below:
|
||||
|
||||
- Tool handlers read it from ``FunctionCallParams.app_resources``.
|
||||
- Custom ``FrameProcessor`` subclasses read it from
|
||||
``self.pipeline_task.app_resources``.
|
||||
|
||||
This example uses two small loggers as stand-ins for that "shared thing":
|
||||
``ToolCallLogger`` (written from tool handlers) and
|
||||
``TranscriptionLogger`` (written from a custom ``FrameProcessor`` that
|
||||
sits in the pipeline). A real app might just as easily pass a Postgres
|
||||
pool, a Redis client, a Stripe SDK instance, or any combination thereof.
|
||||
The mechanics shown here — construct once, hand to the task, read it
|
||||
from each site, inspect it after the session — are the same regardless
|
||||
of what you put in.
|
||||
|
||||
We bundle resources in a typed ``AppResources`` dataclass and cast back
|
||||
to it at each read site. Pipecat doesn't care what type you pass (a
|
||||
plain dict works too), but a typed container gives you autocomplete and
|
||||
refactor safety instead of dict-by-string-key lookups.
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
from collections.abc import Mapping
|
||||
from dataclasses import dataclass
|
||||
from datetime import UTC, datetime
|
||||
from typing import Any, cast
|
||||
|
||||
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 Frame, LLMRunFrame, TranscriptionFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
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.responses.llm import OpenAIResponsesLLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
class ToolCallLogger:
|
||||
"""Stand-in shared resource — swap for whatever your app actually needs."""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the logger with an empty list of recorded calls."""
|
||||
self._calls: list[dict[str, Any]] = []
|
||||
|
||||
def log_tool_call(self, function_name: str, arguments: Mapping[str, Any]) -> None:
|
||||
"""Record a tool call invocation.
|
||||
|
||||
Args:
|
||||
function_name: The name of the tool being invoked.
|
||||
arguments: The arguments passed to the tool.
|
||||
"""
|
||||
entry = {
|
||||
"timestamp": datetime.now(UTC).isoformat(),
|
||||
"function_name": function_name,
|
||||
"arguments": dict(arguments),
|
||||
}
|
||||
self._calls.append(entry)
|
||||
logger.info(f"[ToolCallLogger] {function_name} called with {dict(arguments)}")
|
||||
|
||||
def dump(self) -> str:
|
||||
"""Return all recorded tool calls as a JSON string."""
|
||||
return json.dumps(self._calls, indent=2)
|
||||
|
||||
|
||||
class TranscriptionLogger:
|
||||
"""Records final user transcriptions — written from a custom FrameProcessor."""
|
||||
|
||||
def __init__(self):
|
||||
"""Initialize the logger with an empty list of recorded transcriptions."""
|
||||
self._entries: list[dict[str, Any]] = []
|
||||
|
||||
def log_transcription(self, text: str) -> None:
|
||||
"""Record a transcription.
|
||||
|
||||
Args:
|
||||
text: The transcribed user utterance.
|
||||
"""
|
||||
entry = {
|
||||
"timestamp": datetime.now(UTC).isoformat(),
|
||||
"text": text,
|
||||
}
|
||||
self._entries.append(entry)
|
||||
logger.info(f"[TranscriptionLogger] {text!r}")
|
||||
|
||||
def dump(self) -> str:
|
||||
"""Return all recorded transcriptions as a JSON string."""
|
||||
return json.dumps(self._entries, indent=2)
|
||||
|
||||
|
||||
@dataclass
|
||||
class AppResources:
|
||||
"""Typed container for everything the app shares across this session.
|
||||
|
||||
Add fields here as the app grows (e.g. ``db: AsyncConnection``,
|
||||
``http: httpx.AsyncClient``). Read sites ``cast()`` to this type to
|
||||
get autocomplete and refactor safety:
|
||||
|
||||
- In tools: ``cast(AppResources, params.app_resources)``.
|
||||
- In custom processors: ``cast(AppResources, self.pipeline_task.app_resources)``.
|
||||
"""
|
||||
|
||||
tool_call_logger: ToolCallLogger
|
||||
transcription_logger: TranscriptionLogger
|
||||
|
||||
|
||||
async def fetch_weather_from_api(params: FunctionCallParams):
|
||||
resources = cast(AppResources, params.app_resources)
|
||||
resources.tool_call_logger.log_tool_call(params.function_name, params.arguments)
|
||||
await params.result_callback({"conditions": "nice", "temperature": "75"})
|
||||
|
||||
|
||||
async def fetch_restaurant_recommendation(params: FunctionCallParams):
|
||||
resources = cast(AppResources, params.app_resources)
|
||||
resources.tool_call_logger.log_tool_call(params.function_name, params.arguments)
|
||||
await params.result_callback({"name": "The Golden Dragon"})
|
||||
|
||||
|
||||
class TranscriptionLoggingProcessor(FrameProcessor):
|
||||
"""Logs each final user transcription into the shared app resources.
|
||||
|
||||
Demonstrates the second read site for ``app_resources``: any custom
|
||||
``FrameProcessor`` can reach the same bag every tool handler sees by
|
||||
going through ``self.pipeline_task.app_resources``. ``pipeline_task``
|
||||
is ``None`` until the task sets the processor up, so we guard against
|
||||
that case.
|
||||
"""
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
"""Forward all frames; log final user transcriptions on the way through."""
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, TranscriptionFrame) and self.pipeline_task is not None:
|
||||
resources = cast(AppResources, self.pipeline_task.app_resources)
|
||||
resources.transcription_logger.log_transcription(frame.text)
|
||||
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAIResponsesLLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
settings=OpenAIResponsesLLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
)
|
||||
|
||||
# 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_connection_error")
|
||||
async def on_connection_error(service, error):
|
||||
logger.error(f"LLM connection error: {error}")
|
||||
|
||||
@llm.event_handler("on_function_calls_started")
|
||||
async def on_function_calls_started(service, function_calls):
|
||||
# Avoid appending this filler message to the LLM context — it would
|
||||
# alter the conversation history and prevent
|
||||
# OpenAIResponsesLLMService's previous_response_id optimization from
|
||||
# matching, forcing a full context resend.
|
||||
await tts.queue_frame(TTSSpeakFrame("Let me check on that.", append_to_context=False))
|
||||
|
||||
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])
|
||||
|
||||
context = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
TranscriptionLoggingProcessor(),
|
||||
user_aggregator,
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
assistant_aggregator,
|
||||
]
|
||||
)
|
||||
|
||||
# Keep local handles so we can read collected state after the session
|
||||
# ends; Pipecat never copies or clears the object.
|
||||
tool_call_logger = ToolCallLogger()
|
||||
transcription_logger = TranscriptionLogger()
|
||||
resources = AppResources(
|
||||
tool_call_logger=tool_call_logger,
|
||||
transcription_logger=transcription_logger,
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
app_resources=resources,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
context.add_message(
|
||||
{"role": "developer", "content": "Please introduce yourself to the user."}
|
||||
)
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
# The session has ended; read whatever state the handlers built up.
|
||||
logger.info(f"Tool calls logged during session:\n{tool_call_logger.dump()}")
|
||||
logger.info(f"Transcriptions logged during session:\n{transcription_logger.dump()}")
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -63,17 +63,17 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
|
||||
@@ -58,24 +58,24 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
openai_llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
)
|
||||
|
||||
groq_llm = GroqLLMService(
|
||||
api_key=os.environ["GROQ_API_KEY"],
|
||||
api_key=os.getenv("GROQ_API_KEY"),
|
||||
settings=GroqLLMService.Settings(
|
||||
system_instruction="You are a very helpful assistant. Your goal is to demonstrate your capabilities in detail in a creative and helpful way.",
|
||||
),
|
||||
|
||||
@@ -63,10 +63,10 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info("Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
@@ -74,7 +74,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
# Main LLM — drives the conversation. Its RTVI events reach the client.
|
||||
main_llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
@@ -83,7 +83,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
# Evaluator LLM — silently grades the user's message in the background.
|
||||
# Its RTVI events will be suppressed so the client is unaware of this branch.
|
||||
evaluator_llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
name="EvaluatorLLM",
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a silent quality evaluator. When given a user message, respond with a single JSON object: {'score': <1-5>, 'reason': '<brief reason>'}. Do not respond conversationally.",
|
||||
|
||||
@@ -91,17 +91,17 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
|
||||
@@ -56,10 +56,10 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = DeepgramTTSService(
|
||||
api_key=os.environ["DEEPGRAM_API_KEY"],
|
||||
api_key=os.getenv("DEEPGRAM_API_KEY"),
|
||||
settings=DeepgramTTSService.Settings(
|
||||
voice="aura-asteria-en",
|
||||
),
|
||||
@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
llm = OpenAILLMService(
|
||||
# To use OpenAI
|
||||
# api_key=os.environ["OPENAI_API_KEY"],
|
||||
# api_key=os.getenv("OPENAI_API_KEY"),
|
||||
# Or, to use a local vLLM (or similar) api server
|
||||
settings=OpenAILLMService.Settings(
|
||||
model="meta-llama/Meta-Llama-3-8B-Instruct",
|
||||
|
||||
@@ -55,17 +55,17 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="d4db5fb9-f44b-4bd1-85fa-192e0f0d75f9", # Spanish-speaking Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a live translation assistant. Your sole purpose is to translate English text into Spanish. When you receive English text from the user, immediately translate it into natural, fluent Spanish. Do not add explanations, commentary, or extra information—only provide the Spanish translation of the text you receive.",
|
||||
),
|
||||
|
||||
@@ -126,14 +126,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
llm_text_aggregator.on_pattern_match("voice", on_voice_tag)
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
# Process LLM text through the pattern aggregator before TTS
|
||||
llm_text_processor = LLMTextProcessor(text_aggregator=llm_text_aggregator)
|
||||
|
||||
# Initialize TTS with narrator voice as default
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice=VOICE_IDS["narrator"],
|
||||
),
|
||||
@@ -190,7 +190,7 @@ Remember: Use narrator voice for EVERYTHING except the actual quoted dialogue.""
|
||||
|
||||
# Initialize LLM
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction=system_prompt,
|
||||
),
|
||||
|
||||
@@ -94,19 +94,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
required=["location", "format"],
|
||||
)
|
||||
|
||||
stt_cartesia = CartesiaSTTService(api_key=os.environ["CARTESIA_API_KEY"])
|
||||
stt_deepgram = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt_cartesia = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
|
||||
stt_deepgram = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
# Uses ServiceSwitcherStrategyManual by default
|
||||
stt_switcher = ServiceSwitcher(services=[stt_cartesia, stt_deepgram])
|
||||
|
||||
tts_cartesia = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
tts_deepgram = DeepgramTTSService(
|
||||
api_key=os.environ["DEEPGRAM_API_KEY"],
|
||||
api_key=os.getenv("DEEPGRAM_API_KEY"),
|
||||
settings=DeepgramTTSService.Settings(
|
||||
voice="aura-2-helena-en",
|
||||
),
|
||||
@@ -117,11 +117,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
system_prompt = "You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way."
|
||||
|
||||
llm_openai = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(system_instruction=system_prompt),
|
||||
)
|
||||
llm_google = GoogleLLMService(
|
||||
api_key=os.environ["GOOGLE_API_KEY"],
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
settings=GoogleLLMService.Settings(system_instruction=system_prompt),
|
||||
)
|
||||
# Uses ServiceSwitcherStrategyManual by default
|
||||
|
||||
@@ -42,14 +42,14 @@ class SwitchLanguage(ParallelPipeline):
|
||||
self._current_language = "English"
|
||||
|
||||
english_tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
spanish_tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="d4db5fb9-f44b-4bd1-85fa-192e0f0d75f9", # Spanish-speaking Lady
|
||||
),
|
||||
@@ -101,7 +101,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(
|
||||
api_key=os.environ["DEEPGRAM_API_KEY"],
|
||||
api_key=os.getenv("DEEPGRAM_API_KEY"),
|
||||
settings=DeepgramSTTService.Settings(
|
||||
language="multi",
|
||||
),
|
||||
@@ -110,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
tts = SwitchLanguage()
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way. You can speak the following languages: 'English' and 'Spanish'.",
|
||||
),
|
||||
|
||||
@@ -42,21 +42,21 @@ class SwitchVoices(ParallelPipeline):
|
||||
self._current_voice = "News Lady"
|
||||
|
||||
news_lady = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="bf991597-6c13-47e4-8411-91ec2de5c466", # Newslady
|
||||
),
|
||||
)
|
||||
|
||||
british_lady = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
barbershop_man = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="a0e99841-438c-4a64-b679-ae501e7d6091", # Barbershop Man
|
||||
),
|
||||
@@ -114,12 +114,12 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = SwitchVoices()
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative and helpful way. You can do the following voices: 'News Lady', 'British Lady' and 'Barbershop Man'.",
|
||||
),
|
||||
|
||||
204
examples/features/features-ttsspeakframe-timing.py
Normal file
204
examples/features/features-ttsspeakframe-timing.py
Normal file
@@ -0,0 +1,204 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""TTSSpeakFrame timing and transcript ordering example.
|
||||
|
||||
Demonstrates two common patterns for injecting hardcoded speech into a voice
|
||||
agent without breaking the LLM context / transcript ordering:
|
||||
|
||||
1. Intro / pre-roll. Say something before the agent speaks, and make sure
|
||||
it shows up in the LLM context in the right place.
|
||||
2. Tool-call filler. Say something while a function call is in flight,
|
||||
without the filler audio overlapping the post-tool LLM response and
|
||||
without the filler text landing on the wrong turn in the transcript.
|
||||
|
||||
Key techniques shown:
|
||||
|
||||
- ``TTSSpeakFrame(text, append_to_context=True)`` — the TTS service commits
|
||||
the spoken text to the assistant aggregator after the audio drains, so
|
||||
turn ordering in the transcript matches the audio.
|
||||
- ``pause_frame_processing=True`` on the TTS service — stops the TTS from
|
||||
processing the next LLM response while the filler is still speaking,
|
||||
which is what keeps the audio and the transcript aligned during tool
|
||||
calls.
|
||||
- A system-prompt nudge asking the LLM not to acknowledge before a tool
|
||||
call, so you don't get double acknowledgements (one from the LLM, one
|
||||
from ``on_function_calls_started``).
|
||||
|
||||
Notes:
|
||||
|
||||
- Do NOT call ``asyncio.sleep`` to add pauses around TTS. Use
|
||||
``FrameProcessorPauseFrame`` / ``FrameProcessorResumeUrgentFrame`` if you
|
||||
need a synthetic gap. ``asyncio.sleep`` does not interact with the
|
||||
frame-processing system and will desync audio and transcript.
|
||||
- The base ``TTSService`` defaults ``pause_frame_processing`` to ``False``.
|
||||
Many wrappers (ElevenLabs, Rime, Deepgram, Groq, Azure, ...) hardcode it
|
||||
to ``True`` in their ``super().__init__()`` calls, so you don't need to
|
||||
opt in. ``OpenAITTSService`` inherits the base default (``False``), so we
|
||||
pass it explicitly below.
|
||||
- ``CartesiaTTSService`` is the odd one: it hardcodes
|
||||
``pause_frame_processing=False`` AND does not accept the kwarg via the
|
||||
constructor (you'll get ``TypeError: got multiple values for keyword
|
||||
argument 'pause_frame_processing'``). If you're on Cartesia, set it after
|
||||
construction: ``tts._pause_frame_processing = True``.
|
||||
|
||||
Requirements:
|
||||
- OpenAI API key
|
||||
|
||||
Environment variables (.env):
|
||||
OPENAI_API_KEY=...
|
||||
"""
|
||||
|
||||
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 LLMRunFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.llm_service import FunctionCallParams
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.openai.stt import OpenAISTTService
|
||||
from pipecat.services.openai.tts import OpenAITTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
SYSTEM_INSTRUCTION = """You are a helpful assistant in a voice conversation. Your \
|
||||
responses will be spoken aloud, so avoid emojis, bullet points, or other formatting \
|
||||
that can't be spoken. Keep responses brief.
|
||||
|
||||
IMPORTANT: When you are about to call a tool, do NOT say an acknowledgement like \
|
||||
"Let me check on that" or "One moment" before the call. The system plays its own \
|
||||
filler audio while the tool runs, so if you also acknowledge you will be heard twice."""
|
||||
|
||||
|
||||
async def fetch_weather_from_api(params: FunctionCallParams):
|
||||
await params.result_callback({"conditions": "sunny", "temperature": "75"})
|
||||
|
||||
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_in_enabled=True, audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_in_enabled=True, audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_in_enabled=True, audio_out_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info("Starting TTSSpeakFrame timing demo")
|
||||
|
||||
stt = OpenAISTTService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
# pause_frame_processing=True keeps filler audio and the post-tool LLM
|
||||
# response from overlapping. OpenAI TTS inherits the base default of False,
|
||||
# so we opt in explicitly here.
|
||||
tts = OpenAITTSService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAITTSService.Settings(voice="ballad"),
|
||||
pause_frame_processing=True,
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(system_instruction=SYSTEM_INSTRUCTION),
|
||||
)
|
||||
|
||||
llm.register_function("get_current_weather", fetch_weather_from_api)
|
||||
|
||||
# Tool-call filler. Fires once per function-call batch. append_to_context=True
|
||||
# makes the filler text show up in the transcript in the correct turn order,
|
||||
# because the TTS service commits it only after the audio drains.
|
||||
@llm.event_handler("on_function_calls_started")
|
||||
async def on_function_calls_started(service, function_calls):
|
||||
await tts.queue_frame(TTSSpeakFrame("Gotcha, one sec.", append_to_context=True))
|
||||
|
||||
weather_function = FunctionSchema(
|
||||
name="get_current_weather",
|
||||
description="Get the current weather for a location",
|
||||
properties={
|
||||
"location": {
|
||||
"type": "string",
|
||||
"description": "The city and state, e.g. San Francisco, CA",
|
||||
},
|
||||
},
|
||||
required=["location"],
|
||||
)
|
||||
tools = ToolsSchema(standard_tools=[weather_function])
|
||||
|
||||
context = LLMContext(tools=tools)
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
user_aggregator,
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
assistant_aggregator,
|
||||
]
|
||||
)
|
||||
|
||||
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("Client connected")
|
||||
|
||||
# Intro / pre-roll. append_to_context=True makes this line land in the
|
||||
# LLM context before the first user message, in the correct turn order.
|
||||
# No LLMFullResponseStart/End wrap needed.
|
||||
await tts.queue_frame(
|
||||
TTSSpeakFrame(
|
||||
"Hi, I'm Paul, your virtual agent. Ask me about the weather anywhere.",
|
||||
append_to_context=True,
|
||||
)
|
||||
)
|
||||
|
||||
# Kick off the LLM so it's ready to respond to the first user turn.
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info("Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -60,13 +60,13 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
# Cartesia offers a `<spell></spell>` tags that we can use to ask the user
|
||||
# to confirm the emails.
|
||||
# (see https://docs.cartesia.ai/build-with-sonic/formatting-text-for-sonic/spelling-out-input-text)
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
@@ -84,7 +84,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
# )
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You need to gather a valid email or emails from the user. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. If the user provides one or more email addresses confirm them with the user. Enclose all emails with <spell> tags, for example <spell>a@a.com</spell>.",
|
||||
),
|
||||
|
||||
@@ -52,22 +52,22 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
)
|
||||
classifier_llm = OpenAILLMService(api_key=os.environ["OPENAI_API_KEY"])
|
||||
classifier_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
voicemail = VoicemailDetector(llm=classifier_llm)
|
||||
|
||||
|
||||
@@ -57,21 +57,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(
|
||||
api_key=os.environ["DEEPGRAM_API_KEY"],
|
||||
api_key=os.getenv("DEEPGRAM_API_KEY"),
|
||||
settings=DeepgramSTTService.Settings(
|
||||
keyterm=["pipecat"],
|
||||
),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.environ["OPENAI_API_KEY"],
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
|
||||
@@ -107,17 +107,17 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.environ["ANTHROPIC_API_KEY"],
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
enable_async_tool_cancellation=True,
|
||||
settings=AnthropicLLMService.Settings(
|
||||
system_instruction=(
|
||||
|
||||
@@ -66,17 +66,17 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.environ["ANTHROPIC_API_KEY"],
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
enable_async_tool_cancellation=True,
|
||||
settings=AnthropicLLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
|
||||
@@ -86,10 +86,10 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
@@ -97,7 +97,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
# Anthropic for vision analysis
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.environ["ANTHROPIC_API_KEY"],
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
settings=AnthropicLLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way. You are able to describe images from the user camera.",
|
||||
),
|
||||
|
||||
@@ -65,17 +65,17 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.environ["CARTESIA_API_KEY"],
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.environ["ANTHROPIC_API_KEY"],
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
settings=AnthropicLLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user