Pipecat is an open-source framework for building real-time voice and multimodal conversational AI applications, providing the audio/video infrastructure needed to create applications like AI phone agents, voice assistants, and video calling bots. Pipecat handles the complex real-time data flow between speech-to-text, LLM processing, and text-to-speech, with built-in support for turn detection, interruption handling, and low-latency streaming. It integrates with popular AI services including Deepgram, ElevenLabs, OpenAI, and major voice and video platforms.