Open Source

Voice, dictation & realtime

pipecat-ai/pipecat

Open-source framework to orchestrate voice agents

  • 14k
  • BSD-2-Clause
  • Python

What it is and why it matters

Pipecat is an open-source framework for voice agents, multimodal apps and realtime AI, maintained by Daily and the community. In the video it is described as the orchestrator that manages everything related to voice: it takes the microphone input (the transport), runs it through stations like speech-to-text and text-to-speech, and routes each piece of the conversation to the right destination. They pick it for being open source, hackable and flexible, and mention LiveKit as an alternative.

Key points

  • Orchestrates the voice flow: transport, STT, TTS and routing
  • Open source and hackable, for building custom voice agents
  • Serves realtime AI and multimodal apps

Where we saw it

Same category