Skip to content
  1. Home
  2. AI tools
  3. Pipecat

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

Worth knowingA framework, not a finished app; a working agent needs several external speech and model services.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for design & media

See the topic →
  • ComfyUI

    Comfy-Org/ComfyUI

    Node-graph interface for image, video, audio and 3D generation

    ToolGitHub stars: 147k
  • OpenDesign

    nexu-io/open-design

    Local-first design workspace that coding agents drive via skills and MCP

    ToolGitHub stars: 107k
  • HyperFrames

    heygen-com/hyperframes

    Framework that renders HTML, CSS and animations to MP4 video

    ToolGitHub stars: 84k
  • OpenMontage

    OpenMontageInc/OpenMontage

    Agent-run video production pipelines from research to final render

    ToolGitHub stars: 80k