A real-time voice/call AI agent UI that lets you talk to a LangGraph agent over LiveKit — similar to "voice mode" experiences in ChatGPT Voice, OpenAI Realtime API sessions, and Gemini Live. This repo demonstrates adapting a LangGraph agent into a full-duplex, low-latency voice assistant using LiveKit's real-time communication infrastructure.
# LangGraph Voice Call Agent Web A real-time voice/call AI agent UI that lets you talk to a LangGraph agent over LiveKit — similar to "voice mode" experiences in Gemini Voice, OpenAI Realtime API sessions, and Gemini Live. This repo demonstrates adapting a LangGraph agent into a full-duplex, low-latency voice assistant using LiveKit's real-time communication infrastructure. This frontend provides a seamless interface for both text chat and voice calls with your LangGraph agent, built with Next.js and LiveKit's real-time communication platform. ### Features - Real-time voice interaction with LangGraph agents - Audio visualization and level monitoring - Light/dark theme switching with system preference detection - Customizable branding, colors, and UI text via configuration This application is built with Next.js and LiveKit's real-time communication platform, providing a production-ready interface for your LangGraph voice agent. ### Project structure ``` langgraph-voice-call-agent-web/ ├── app/ │ ├── (app)/ │ │ ├── layout.tsx │ │ └── page.tsx │ ├── api/ │ │ └── connection-details/ │ │ └── route.ts │ ├── globals.css │ └── layout.tsx ├── components/ │ ├── livekit/ │ │ ├── agent-control-bar/ │ │ │ ├── agent-control-bar.tsx │ │ │ └── hooks/ │ │ │ ├── use-agent-control-bar.ts │ │ │ └── use-publish-permissions.ts │ │ ├── agent-tile.tsx │ │ ├── avatar-tile.tsx │ │ ├── chat/ │ │ │ ├── chat-entry.tsx │ │ │ └── chat-message-view.tsx │ │ ├── device-select.tsx │ │ ├── media-tiles.tsx │ │ ├── track-toggle.tsx │ │ └── video-tile.tsx │ ├── app.tsx │ ├── provider.tsx │ ├── session-view.tsx │ ├── theme-toggle.tsx │ └── welcome.tsx ├── hooks/ │ ├── useChatAndTranscription.ts │ ├── useConnectionDetails.ts │ ├── useDebug.ts │ └── useLangGraphChat.ts ├── lib/ │ ├── types.ts │ └── utils.ts ├── public/ └── package.json ``` ## Getting started This applica
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.