Open source framework for building voice and multimodal conversational AI agents
Pipecat is an open source Python framework for building real-time voice and multimodal AI agents. It orchestrates speech-to-text, language models, text-to-speech and vision services in streaming pipelines, with 200+ integrated providers, interruption handling, turn detection, multi-agent workflows via Pipecat Flows, and transports including WebRTC, SIP and PSTN. Pipecat was created and maintained by Daily; on October 29, 2026 Deepgram announced that the Daily team is joining Deepgram, with Pipecat staying open source under its BSD-2 license and vendor neutral.
For people
For agents
Nothing listed yet.