met4citizen/TalkingHead
Talking Head (3D): A JavaScript class for real-time lip-sync using full-body 3D avatars.
Supports dynamic bone physics, viseme-driven lip-sync across 5+ languages (extensible via custom modules), and integrates with multiple TTS providers (Google Cloud, ElevenLabs, Microsoft Azure, Kokoro) and animation systems (Mixamo FBX). Renders GLB avatars with ThreeJS/WebGL, handling real-time audio-to-mouth synchronization through word-level timestamps or direct viseme/blend-shape output from TTS engines.
1,101 stars. Actively maintained with 1 commit in the last 30 days. Available on npm.
Stars
1,101
Forks
278
Language
JavaScript
License
MIT
Category
Last pushed
Feb 26, 2026
Commits (30d)
1
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/met4citizen/TalkingHead"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
livekit/livekit
End-to-end realtime stack for connecting humans and AI
Henry-23/VideoChat
实时交互数字人，可自定义形象与音色，支持音色克隆，对话延迟低至3s。Real-time voice interactive digital human, customizable...
dmisol/flexatar-virtual-webcam
Personalized Virtual Webcam for WebRTC
zslrmhb/Omniverse-Virtual-Assisstant
Audio2Face Avatar with Riva SDK functionality
Sgvkamalakar/Azure-Talking-Avatar
Explore the power of Azure Text-to-Speech with interactive talking avatar, Lisa 👩🏻🦱. Choose...