Pipecat
Python framework for real-time voice and multimodal AI agents
What it is
A Python framework for building conversational agents that handle live audio and video. It orchestrates speech, LLM and transport services in pipelines and supports multi-agent setups with hand-offs, with a CLI that scaffolds a starter project. For developers building phone bots, voice assistants and similar real-time products.
Good for
- Build a streaming voice assistant
- Wire speech-to-text, an LLM and TTS together
- Scaffold a voice agent project from the CLI
Install or run
uv tool install "pipecat-ai[cli]"Command as given in the project README. Read the repository before you run anything on your machine.
What you need
Python 3.11 to 3.14 with uv; keys for the speech and LLM services you use
Sources
- https://github.com/pipecat-ai/pipecat (project README, read 10 Nov 2026)
- https://api.github.com/repos/pipecat-ai/pipecat (GitHub API, read 13 Nov 2026)
The summary is ours, written from the README. Spotted an error? See how we work.