Open-source framework for building real-time voice and multimodal conversational AI agents.
Pipecat is an open-source framework for building real-time voice and multimodal conversational AI agents. It provides a pipeline architecture for connecting speech-to-text, LLMs, and text-to-speech in a low-latency streaming setup. Transport-agnostic with SDKs for JavaScript, React, Swift, and Kotlin. Built by Daily (the WebRTC company), it handles the complex real-time infrastructure so you can focus on building your agent logic.