Open SourceVoice & Media9k
Pipecat
Python framework for realtime voice and multimodal conversational AI.
Pipecat is an open-source Python framework for building real-time voice and multimodal conversational AI agents. It orchestrates a pipeline of services (speech-to-text, LLM, text-to-speech, and transport) with low latency, handling interruptions, turn-taking, and streaming between vendors.
Repository
pipecat-ai/pipecatLanguage
PythonWhat you'd build with it
- Build a real-time voice agent that wires together STT, an LLM, and TTS providers
- Handle conversational concerns like interruption and turn detection in a phone or web voice bot
- Swap and compose speech/LLM vendors behind a unified streaming pipeline
Tags
voice-agentsrealtimepipeline