ae8b9f0756
This fix addresses an issue where the on_client_disconnected callback would not fire in approximately 5% of calls when using FastAPIWebsocketTransport. The problem was caused by a race condition introduced after v0.0.86 when event handlers were changed to run in parallel. When stop() or cancel() initiated the disconnect, the _closing flag would be set, preventing trigger_client_disconnected() from being called in _receive_messages(). Now disconnect() always calls trigger_client_disconnected() when closing the WebSocket, ensuring the event fires reliably whether the disconnect is initiated by the transport or the remote client. Fixes the same issue as commit 019c1a6d from origin/fastapi_disconnect_issue branch.
🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
Pipecat is an open-source Python framework for building real-time voice and multimodal conversational agents. Orchestrate audio and video, AI services, different transports, and conversation pipelines effortlessly—so you can focus on what makes your agent unique.
Want to dive right in? Try the quickstart.
🚀 What You Can Build
- Voice Assistants – natural, streaming conversations with AI
- AI Companions – coaches, meeting assistants, characters
- Multimodal Interfaces – voice, video, images, and more
- Interactive Storytelling – creative tools with generative media
- Business Agents – customer intake, support bots, guided flows
- Complex Dialog Systems – design logic with structured conversations
🧭 Looking to build structured conversations? Check out Pipecat Flows for managing complex conversational states and transitions.
🔍 Looking for help debugging your pipeline and processors? Check out Whisker, a real-time Pipecat debugger.
🧠 Why Pipecat?
- Voice-first: Integrates speech recognition, text-to-speech, and conversation handling
- Pluggable: Supports many AI services and tools
- Composable Pipelines: Build complex behavior from modular components
- Real-Time: Ultra-low latency interaction with different transports (e.g. WebSockets or WebRTC)
📱 Client SDKs
You can connect to Pipecat from any platform using our official SDKs:
JavaScript
|
React
|
React Native
|
Swift
|
Kotlin
|
C++
|
🎬 See it in action
🧩 Available services
| Category | Services |
|---|---|
| Speech-to-Text | AssemblyAI, AWS, Azure, Cartesia, Deepgram, ElevenLabs, Fal Wizper, Gladia, Google, Groq (Whisper), NVIDIA Riva, OpenAI (Whisper), SambaNova (Whisper), Soniox, Speechmatics, Ultravox, Whisper |
| LLMs | Anthropic, AWS, Azure, Cerebras, DeepSeek, Fireworks AI, Gemini, Grok, Groq, Mistral, NVIDIA NIM, Ollama, OpenAI, OpenRouter, Perplexity, Qwen, SambaNova Together AI |
| Text-to-Speech | Async, AWS, Azure, Cartesia, Deepgram, ElevenLabs, Fish, Google, Groq, Inworld, LMNT, MiniMax, Neuphonic, NVIDIA Riva, OpenAI, Piper, PlayHT, Rime, Sarvam, XTTS |
| Speech-to-Speech | AWS Nova Sonic, Gemini Multimodal Live, OpenAI Realtime |
| Transport | Daily (WebRTC), FastAPI Websocket, SmallWebRTCTransport, WebSocket Server, Local |
| Serializers | Plivo, Twilio, Telnyx |
| Video | HeyGen, Tavus, Simli |
| Memory | mem0 |
| Vision & Image | fal, Google Imagen, Moondream |
| Audio Processing | Silero VAD, Krisp, Koala, ai-coustics |
| Analytics & Metrics | OpenTelemetry, Sentry |
📚 View full services documentation →
⚡ Getting started
You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you're ready.
-
Install uv
curl -LsSf https://astral.sh/uv/install.sh | shNeed help? Refer to the uv install documentation.
-
Install the module
# For new projects uv init my-pipecat-app cd my-pipecat-app uv add pipecat-ai # Or for existing projects uv add pipecat-ai -
Set up your environment
cp env.example .env -
To keep things lightweight, only the core framework is included by default. If you need support for third-party AI services, you can add the necessary dependencies with:
uv add "pipecat-ai[option,...]"
Using pip? You can still use
pip install pipecat-aiandpip install "pipecat-ai[option,...]"to get set up.
🧪 Code examples
- Foundational — small snippets that build on each other, introducing one or two concepts at a time
- Example apps — complete applications that you can use as starting points for development
🛠️ Contributing to the framework
Prerequisites
Minimum Python Version: 3.10 Recommended Python Version: 3.12
Setup Steps
-
Clone the repository and navigate to it:
git clone https://github.com/pipecat-ai/pipecat.git cd pipecat -
Install development and testing dependencies:
uv sync --group dev --all-extras \ --no-extra gstreamer \ --no-extra krisp \ --no-extra local \ --no-extra ultravox # (ultravox not fully supported on macOS) -
Install the git pre-commit hooks:
uv run pre-commit install
Note
: Some extras (local, gstreamer) require system dependencies. See documentation if you encounter build errors.
Running tests
To run all tests, from the root directory:
uv run pytest
Run a specific test suite:
uv run pytest tests/test_name.py
Setting up your editor
This project uses strict PEP 8 formatting via Ruff.
Emacs
You can use use-package to install emacs-lazy-ruff package and configure ruff arguments:
(use-package lazy-ruff
:ensure t
:hook ((python-mode . lazy-ruff-mode))
:config
(setq lazy-ruff-format-command "ruff format")
(setq lazy-ruff-check-command "ruff check --select I"))
ruff was installed in the venv environment described before, so you should be able to use pyvenv-auto to automatically load that environment inside Emacs.
(use-package pyvenv-auto
:ensure t
:defer t
:hook ((python-mode . pyvenv-auto-run)))
Visual Studio Code
Install the
Ruff extension. Then edit the user settings (Ctrl-Shift-P Open User Settings (JSON)) and set it as the default Python formatter, and enable formatting on save:
"[python]": {
"editor.defaultFormatter": "charliermarsh.ruff",
"editor.formatOnSave": true
}
PyCharm
ruff was installed in the venv environment described before, now to enable autoformatting on save, go to File -> Settings -> Tools -> File Watchers and add a new watcher with the following settings:
- Name:
Ruff formatter - File type:
Python - Working directory:
$ContentRoot$ - Arguments:
format $FilePath$ - Program:
$PyInterpreterDirectory$/ruff
🤝 Contributing
We welcome contributions from the community! Whether you're fixing bugs, improving documentation, or adding new features, here's how you can help:
- Found a bug? Open an issue
- Have a feature idea? Start a discussion
- Want to contribute code? Check our CONTRIBUTING.md guide
- Documentation improvements? Docs PRs are always welcome
Before submitting a pull request, please check existing issues and PRs to avoid duplicates.
We aim to review all contributions promptly and provide constructive feedback to help get your changes merged.