pipecat-ai/pipecat

Project overview

It addresses the complexity of wiring together audio/video, AI services, transports, and conversation pipelines, and ships with a CLI that can scaffold a runnable bot in under a minute, official client SDKs across major platforms, and structured conversation support built in.

Project type

AI Agent · Workflow · Audio & Speech

Use cases

Automation

Deployment

Refer to project documentation

License

BSD-2-Clause

Best for

• Developers and AI engineers building real-time voice or multimodal conversational agents in Python, who are able to write Python agent code.
• Teams that need multi-agent orchestration with handoff, parallel fan-out, sidecar workers, or distributed deployments.

Key capabilities

• An open-source Python framework for building real-time voice and multimodal conversational agents, orchestrating audio and video, AI services, transports, and conversation pipelines.
• Each pipeline is an agent; compose them with handoff, parallel fan-out, sidecar workers, or distributed deployments.
• Supports many AI services and tools via optional extras; available services include speech-to-text providers (e.g. Deepgram, ElevenLabs) and LLM providers (e.g. Anthropic, OpenAI).
• Ultra-low latency interaction with different transports such as WebSockets or WebRTC.
• Predefined or dynamic conversation paths with state management, built into Pipecat.
• Ships with pipecat-ai; pipecat init starts a project set up so an AI coding assistant builds it and can scaffold a runnable bot in under a minute; the CLI can also monitor and deploy the agent to production.
• Official SDKs (JavaScript, React, React Native, Swift, Kotlin, C++, ESP32) to connect client applications to Pipecat from any platform.

Limitations and risks

• Only the core framework is included by default; support for third-party AI services requires adding optional extras.
• Requires Python 3.11 minimum (>= 3.12 recommended).
• Some extras (local, gstreamer) require system dependencies and may cause build errors; check these dependencies before adopting those extras.

Getting started

• Install uv (curl -LsSf https://astral.sh/uv/install.sh | sh), then run uv tool install "pipecat-ai[cli]" and pipecat init, which starts a project set up so an AI coding assistant builds it and can scaffold a runnable bot in under a minute; follow the quickstart to run the first bot. Setup difficulty is medium: it requires installing uv and Python 3.11+, writing Python agent code, and installing service-specific extras separately.

Evidence and sources

• GitHub project description: Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.
• README: **Pipecat** is an open-source Python framework for building real-time voice and multimodal conversational agents.
• README: Build a single voice agent or a full multi-agent system where specialists hand off, fan out in parallel, and coordinate over a shared bus, locally or distributed across processes…
• README: **Voice-first**: Integrates speech recognition, text-to-speech, and conversation handling
• README: You can connect to Pipecat from any platform using our official SDKs

Source updated at: 2026-09-22T18:55:14Z

Open original GitHub project