Pipecat is an open-source Python framework for building real-time voice and multimodal conversational agents. Build a single voice agent or a full multi-agent system where specialists hand off, fan out in parallel, and coordinate over a shared bus, locally or distributed across processes and machines. Orchestrate audio and video, AI services, transports, and conversation pipelines effortlessly, so you can focus on what makes your agents unique.
Want to dive right in? Run
pipecat init quickstartor follow the quickstart guide.
- Voice Assistants – natural, streaming conversations with AI
- Multi-Agent Systems – specialists that hand off, fan out in parallel, or run as sidecars over a shared bus
- 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
- 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
- Multi-Agent Ready: Each pipeline is an agent. Compose them with handoff, parallel fan-out, sidecar workers, or distributed deployments
- Real-Time: Ultra-low latency interaction with different transports (e.g. WebSockets or WebRTC)
Building client applications? You can connect to Pipecat from any platform using our official SDKs:
JavaScript | React | React Native | Swift | Kotlin | C++ | ESP32
Need predefined or dynamic conversation paths with state management? Pipecat Flows is built into Pipecat. Browse the examples to see it in action.
Want to build beautiful and engaging experiences? Check out Pipecat UI, a shadcn registry of components for building voice AI applications. Browse the documentation for component previews and installation guides.
The Pipecat CLI ships with pipecat-ai — install it with uv tool install "pipecat-ai[cli]". Run pipecat init to start a project: it sets you up so an AI coding assistant (Claude Code, Codex) builds it for you, and can scaffold a runnable bot in under a minute. Then use the CLI to monitor and deploy your agent to production.
Looking for help debugging your pipeline and processors? Check out Whisker, a real-time Pipecat debugger.
Love terminal applications? Check out Tail, a terminal dashboard for Pipecat.
Use Pipecat Skills with Claude Code to scaffold projects, deploy to Pipecat Cloud, and more. Install the marketplace with:
claude plugin marketplace add pipecat-ai/skills
and install any of the available plugins.
Build and share your own Pipecat service integrations! Browse existing community integrations or check out our guide to create your own.
Catch new features, interviews, and how-tos on our Pipecat TV channel.
| Example | What it shows |
|---|---|
| 📞 Phone agent | Answers incoming calls and places outbound calls. Examples for Twilio, Telnyx, Plivo, Exotel, Vonage, Genesys and Daily PSTN and SIP. |
| 🧠 Voice LLM with a tool-calling backend | LLMWithBackend pairs a fast voice model with a slower backend model that runs the tools, and the voice keeps talking while the backend works. |
| 🎭 Expressive conversation | The LLM writes emotion and sound tags such as laughter into its replies, and the TTS performs them. The tags follow the Real-time Context Standard, with examples for ten TTS providers. |
| 🔢 IVR navigation | IVRNavigator dials out and works through a phone menu with DTMF keypad tones and speech until it reaches a person. |
| 🍽️ Pipecat Flows: restaurant reservation | A booking conversation defined in YAML, where FlowManager moves through each step and branches on table availability. |
| 📝 Multi-agent UI control | A UIWorker lets voice commands read and act on a web page, and runs two reviewer agents in parallel as a job group. |
📚 View full services documentation →
Run Pipecat on your local machine, then move your agent processes to the cloud when you're ready. Either way, you'll need uv — install it first:
curl -LsSf https://astral.sh/uv/install.sh | shThe quickest path: install the Pipecat CLI and scaffold a new phone or web/mobile bot interactively.
uv tool install "pipecat-ai[cli]"
pipecat initFollow the quickstart guide to get your very first bot running, or dive a little deeper into bootstrapping a project.
uv add pipecat-aiTo keep things lightweight, only the core framework is included by default. Add extras for the third-party AI services you use:
uv add "pipecat-ai[option,...]"Using pip?
pip install pipecat-aiandpip install "pipecat-ai[option,...]"work too.
Pipecat runs on Python 3.11 through 3.14. Python 3.15 is not supported yet, because onnxruntime publishes no wheels for it. Pin your project to a supported version, for example with uv python pin 3.14.
From here, the code examples below are the best way to learn — agents you can run, read, and adapt.
- Focused examples — small agents that each illustrate one or two specific services or concepts
- Example apps — complete applications you can use as starting points for development
Minimum Python Version: 3.11 Recommended Python Version: >= 3.12
-
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 local -
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.
Install development workflow skills for contributing to Pipecat with Claude Code:
claude plugin marketplace add pipecat-ai/pipecat
claude plugin install pipecat-dev@pipecat-dev-skills
To run all tests, from the root directory:
uv run pytestTests run in parallel, one worker per CPU core. Pass -n 0 to run them in a single process.
Run a specific test suite:
uv run pytest tests/test_name.pyWe 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.
➡️ Enterprise support for consulting and support agreements