Pipecat’s documentation is currently work in progress. Whilst we aim to have this done soon, we have a lot to write! Please refer to the project source code in the meantime.

Pipecat is a framework for building voice (and multimodal) conversational agents. Things like personal coaches, meeting assistants, story-telling toys for kids, customer support bots, intake flows, and snarky social companions.

You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you’re ready. You can also add a 📞 telephone number, 🖼️ image output, 📺 video input, use different LLMs, and more.

We are actively releasing changes based on your feedback, so please join our community and share your ideas, demos and questions: Discord.