An open-source AI voice agent platform that turns conversations into 100% accurate, user-verified data via a visual form.

TEN VAD low-latency voice activity detection for real-time streaming, integrated with livekit-agents

Livekit TTS plugin for kokoro

Crix- your personal AI voice assistant that actually does your work for you

Turn detector plugin for LiveKit Agents with external model (Triton, OpenAI)

Livekit STT plugin for openAI whisper models with faster-whisper backend

LiveKit STT plugin for NVIDIA NeMo Parakeet and Canary models

LiveKit TTS plugin with Kyutai streaming implementation

Real-time WebRTC AI Agent with Generative UI.

Frontend for a real-time AI Voice Agent built with Next.js, LiveKit, and React. It enables seamless voice conversations with either a 3D audio-reactive avatar (React Three Fiber) or a video avatar, supporting live streaming, lip sync visualization, and interactive UI.

LiveKit voice app validation skill. Use when building, debugging, or declaring working any LiveKit voice agent, Agents UI app, or React/Next.js LiveKit project. Enforces evidence-based validation before reporting a session, token endpoint, worker, transcript, or end-to-end voice interaction as complete.

LiveKit TTS plugin with Orpheus streaming support

End-to-end AI interview platform featuring live voice interaction, coding assessment, and automated feedback.

voice agent application designed to provide a seamless and intelligent customer support experience

Turn detector plugin for LiveKit Agents with Namo model

A library to run your existing livekit-agents across any text channel (chat, SMS, API) without changing code. Connect LiveKit to SMS and chat! 💬🤖

Real-time voice agent using LiveKit and Gemini Live API

Control begins here

AI voice system with LiveKit WebRTC answering pdf/docs using RAG (<95% accuracy)

A full-stack intelligent assistant inspired by J.A.R.V.I.S., featuring a Python backend and TypeScript frontend. Built with LiveKit’s AI Agent Framework and Google Gemini, it delivers real-time streaming, multimodal understanding, and advanced task automation. Its modular design makes it easy to add new tools without altering the core code logic.