Verified project record

pipecat-ai/pipecat

pipecat is an open-source Python framework for building real-time voice and multimodal conversational agents, from a single agent to multi-agent systems. It orchestrates audio/video, AI services, transports and conversation pipelines so developers can focus on what makes their agents unique.

Project overview

It addresses a well-defined pain point in assembling real-time conversational agents—wiring together audio/video, AI services, transports and pipelines—by providing orchestration as a framework, with pluggable speech-to-text, text-to-speech and LLM services added as optional extras.

Project type: AI Agent · Audio & Speech
Use cases: Knowledge Q&A · Automation
Deployment: Refer to project documentation
License: BSD-2-Clause

Best for

Developers who want to build real-time voice and multimodal conversational agents in Python and prefer a framework that orchestrates the pipeline components.

Key capabilities

Python framework for building real-time voice and multimodal conversational agents, from a single agent to multi-agent systems.
Supports many AI services including speech-to-text, text-to-speech and LLM providers, added as optional extras.

Limitations and risks

Building agents with pipecat requires coding.
Speech-to-text, text-to-speech and LLM providers are third-party services integrated via optional extras, not bundled capabilities; using them involves external services.

Getting started

Install uv with `curl -LsSf https://astral.sh/uv/install.sh | sh`, run `uv tool install "pipecat-ai[cli]"`, then run `pipecat init` to interactively scaffold a runnable bot project.

Evidence and sources

README: **Pipecat** is an open-source Python framework for building real-time voice and multimodal conversational agents.
README: | Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/api-reference/server/services/stt/assemblyai)
README: only the core framework is included by default. If you need support for third-party AI services, you can add the necessary dependencies with:
README: Run `pipecat init` to start a project: it sets you up so an AI coding assistant (Claude Code, Codex) builds it for you, and can scaffold a runnable bot in under a minute.
README: - **Voice-first**: Integrates speech recognition, text-to-speech, and conversation handling

Source updated at: 2026-11-08T18:09:25Z

Open original GitHub project