pipecat-ai/pipecat-examples

Pipecat example applications. Use and learn from these patterns to build your own voice AI applications.

What it solves

This repository provides a comprehensive collection of intermediate and advanced implementation examples for developers using the Pipecat framework to build voice and multimodal AI applications. It bridges the gap between basic quickstarts and production-ready deployments by providing reference architectures for common real-world use cases.

How it works

The project organizes a variety of pre-built bot examples into categories based on their delivery method or functionality. These examples demonstrate how to integrate Pipecat with various communication protocols (WebRTC, WebSockets, MoQ), telephony providers (Twilio, Telnyx, Plivo, Exotel), and AI services (OpenAI, Deepgram, Cartesia, Gemini Live).

Who it’s for

Developers building real-time, voice-driven AI agents that need to integrate with phone systems, web clients (React, Swift, Kotlin), or specialized multimodal interfaces.

Highlights

  • Telephony Integration: Production-ready examples for multiple PSTN/SIP providers including Twilio and Telnyx.
  • Web & Client Support: Reference implementations for React, JavaScript, Swift, and Kotlin clients.
  • Multimodal Capabilities: Examples for interactive storytelling and multi-language conference calls.
  • Production Tooling: Demos for deployment on Pipecat Cloud, Fly.io, and Modal, as well as observability via OpenTelemetry (Langfuse, LangSmith).
  • Advanced Logic: Implementations for smart conversation turn-taking and pipeline state management testing.

Related

  • Project
    livekit-examples/python-agents-examples

    A collection of runnable Python examples and full-stack applications for building voice, video, and telephony AI agents using the LiveKit Agents framework.

  • Project
    pipecat-ai/pipecat

    Pipecat is an open‑source Python framework for building real‑time voice‑first and multimodal AI agents. It offers plug‑and‑play support for dozens of speech‑to‑text, LLM, and text‑to‑speech services, composable pipelines, and built‑in multi‑agent orchestration. The ecosystem includes client SDKs (JS, React, Swift, Kotlin, C++, ESP32), a CLI for scaffolding projects, a UI component library, a debugger (Whisker), and many example bots. Ideal for developers and researchers who want to prototype or deploy voice‑centric conversational systems quickly.

  • Project
    pipecat-ai/voice-ui-kit

    A React-based UI kit providing components and templates for quickly building and deploying user interfaces for Pipecat AI voice applications.

  • Project
    pipecat-ai/pipecat-client-web

    A web client SDK and React library for connecting to and interacting with voice and multimodal AI applications built with the Pipecat framework.

  • Project
    google-gemini/gemini-live-api-examples

    A collection of examples for the Gemini Live API, enabling developers to build low-latency, real-time voice and video AI agents with multimodal input.