Pipecat: Open-Source Python Framework for Real-Time Voice & Multimodal AI Agents

Open-source framework for building real-time voice AI agents!
Pipecat is a Python framework for orchestrating audio, video, AI services, transports, and conversation pipelines. Voice-first architecture with pluggable components.
What you can build: voice assistants, AI companions, multimodal interfaces, interactive storytelling, business agents (customer support, intake), and complex dialog systems.
The framework handles speech recognition, text-to-speech, conversation logic, and real-time interaction. WebRTC and WebSocket transport built in. Ultra-low latency for natural conversations.
Why Pipecat:
• Voice-first: Integrates STT, TTS, and conversation handling in one framework • Pluggable: Supports multiple AI service providers for each capability 
• Composable pipelines: Build complex behavior from modular components 
• Real-time: Low-latency interaction with streaming audio/video
Supported services:
• Speech-to-Text: Deepgram, AssemblyAI, OpenAI Whisper, Groq, Azure, AWS, Google, and more 
• LLMs: OpenAI, Anthropic, Gemini, Groq, Mistral, Ollama, AWS, Azure, and more 
• Text-to-Speech: OpenAI, ElevenLabs, Deepgram, Cartesia, Azure, AWS, Google, and more
• Speech-to-Speech: OpenAI Realtime, Gemini Multimodal Live, AWS Nova Sonic, Ultravox, Grok Voice Agent
I've shared link to the repo in the comments!

Pipecat is an open-source Python framework (BSD-2 license) for building real-time voice and multimodal conversational AI agents. It orchestrates audio, video, AI services, transports, and conversation pipelines through a frame-based, pluggable architecture.
What you can build: voice assistants, multi-agent systems, AI companions, multimodal interfaces, interactive storytelling, business agents (customer support, intake), and complex dialog systems. Core capabilities: The framework handles speech-to-text (STT), large language models (LLMs), text-to-speech (TTS), turn detection, voice activity detection (VAD), interruption handling, and real-time streaming audio/video pipelines. It supports WebRTC and WebSocket transports. Why Pipecat:

• Voice-first: Integrates STT, TTS, and conversation handling in one framework
• Pluggable: Supports 68+ AI service integrations across STT, LLM, TTS, speech-to-speech, vision, image generation, and more
• Composable pipelines: Frame-based architecture where every piece of data (audio chunks, transcriptions, LLM tokens, synthesized speech) is a typed frame, enabling modular, reusable components
• Multi-agent ready: Each pipeline is an agent; compose them with handoff, parallel fan-out, sidecar workers, or distributed deployments
• Real-time: Designed for low-latency streaming interaction