Skip to main content
Pipecat is an open source ecosystem for building voice and multimodal AI agents. It provides everything you need to create, deploy, and scale real-time AI applications that can see, hear, and speak.

The Pipecat Ecosystem

Pipecat

Open source Python framework for building voice and multimodal AI pipelines. Orchestrate 100+ AI services with ultra-low latency.

Pipecat Clients

Client SDKs for JavaScript, React, React Native, iOS, Android, and C++. Connect users to your agents via web and mobile.

Pipecat Flows

Build structured conversations with defined paths and state management. Break complex tasks into focused steps for better LLM accuracy.

Pipecat Cloud

Managed hosting platform for deploying and scaling Pipecat agents in production with built-in infrastructure.

How It All Fits Together

A typical Pipecat application has a client and a server. The client connects users via browser, mobile app, or phone. The server runs a Pipecat pipeline that processes audio, runs LLMs, and generates speech in real-time. Your hosting provider — Pipecat Cloud or self-hosted — manages deployment and scales instances to handle concurrent sessions.
Pipecat architecture

Getting Started

1

Build your first agent

Follow the Quickstart to create a voice AI bot in 5 minutes.
2

Learn core concepts

Work through the Learning Pipecat guide to understand pipelines, processors, and transports.
3

Add a client

Connect users to your agent with a Client SDK for web or mobile.
4

Deploy

Ship to production with Pipecat Cloud or self-host on your own infrastructure.

Community

Discord

Connect with other developers, share projects, and get support.

GitHub

Explore the source code, open issues, and contribute.