livekit-examples/agent-starter-react

A complete voice AI frontend app for LiveKit Agents with Next.js

What it solves

This project provides a ready-made frontend template for developers to quickly build voice-based AI agents. It eliminates the need to build a voice interface from scratch by providing pre-built UI components for real-time interaction, audio visualization, and media streaming.

How it works

Built with Next.js and the LiveKit JavaScript SDK, the template connects a web frontend to a LiveKit Agent. It uses a specialized set of UI components (Agents UI) to handle the complex parts of a voice session, such as managing audio tracks, displaying chat transcripts, and rendering audio visualizers. Developers can connect the app to either a default LiveKit agent or their own custom agent via a token server for authentication.

Who it’s for

Frontend developers and AI engineers who want to integrate real-time voice, video, and avatar capabilities into their web applications without spending time on the basic UI and session management logic.

Highlights

  • Real-time Voice Interaction: Direct integration with LiveKit Agents for low-latency voice AI.
  • Custoimzable Visualizers: Five different audio visualizer styles including bar, grid, radial, wave, and aura.
  • Media Support: Built-in support for camera video streaming and screen sharing.
  • Virtual Avatars: Integration for displaying AI-driven virtual avatars.
  • Theming: Support for light and dark modes with system preference detection.

Related

  • 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
    livekit/agents-js

    A Node.js framework for building real-time, multi-modal voice agents that can see, hear, and understand using WebRTC.

  • Project
    langchain-ai/langchain-nextjs-template

    A starter template for building AI applications with LangChain.js and Next.js, featuring implementations for streaming chat, RAG, and agentic workflows.

  • Project
    livekit/agents

    LiveKit Agents is a Python SDK for building real‑time, multimodal voice agents (LLM‑driven assistants) that run on LiveKit servers. It provides unified adapters for STT/LLM/TTS, job scheduling, WebRTC/telephony integration, turn detection, MCP tool support, and a built‑in test framework.

  • 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.