Skip to main content
Pipecat provides a complete ecosystem of client SDKs, developer tools, and AI service integrations to build voice and multimodal applications for any platform.

​
Client SDKs

The client SDKs connect users to your bot via mobile or web applications. They handle real-time audio transport (using Daily WebRTC, SmallWebRTC, etc.) and provide built-in messaging and events to build responsive voice AI interfaces—tracking when your bot is speaking, what it’s saying, and more. Build client applications for any platform with our official SDKs:

JavaScript

Build web applications with vanilla JavaScript

React

Create React applications with hooks and components

React Native

Build mobile apps with React Native

Swift

Native iOS applications

Kotlin

Native Android applications

C++

High-performance native applications

​
Tools & Frameworks

​
Pipecat CLI

Command-line tool for scaffolding new projects, deploying to Pipecat Cloud, and monitoring live sessions.

CLI Overview

Learn about scaffolding, deployment, and monitoring commands

​
Pipecat Flows

A conversation and context management library designed to help you handle complex, structured conversations with state management.

Pipecat Flows

Build structured conversation flows

​
Voice UI Kit

Pre-built React components and custom hooks that accelerate building voice AI applications on top of the JavaScript and React SDKs.

Voice UI Kit

Ready-to-use components for voice interfaces

​
Tail

A terminal dashboard for monitoring your Pipecat sessions in real-time with logs, conversations, metrics, and audio levels.

Tail

Real-time monitoring dashboard

​
AI Services

Pipecat is a modular system where you can plug in different AI services without changing your code. This flexibility is one of Pipecat’s core strengths—swap Deepgram for Azure Speech, OpenAI for Anthropic, or Cartesia for ElevenLabs with minimal changes. The framework integrates with 70+ services across:
  • Speech-to-Text (STT) - Deepgram, Azure, Google, Whisper, and more
  • Language Models (LLM) - OpenAI, Anthropic, Gemini, Groq, and more
  • Text-to-Speech (TTS) - Cartesia, ElevenLabs, Azure, Google, and more
  • Vision - Image and video analysis capabilities
  • Transports - WebRTC, WebSockets, telephony providers
  • And more - Image generation, memory systems, analytics

View All Services

Browse the complete list of 70+ supported AI services
⌘I