
Description
A talking avatar for support or streaming costs per minute on commercial platforms and means handing over your face and voice. AI Avatar System is an open source, self-hosted digital human platform: upload a photo, clone a voice and talk to that face in real time.
It combines Claude, Whisper, Chatterbox and MuseTalk for speech recognition, conversation, TTS and lip-synced video.
Photo-driven:One image.
Voice cloning:Chatterbox.
Real time:Low latency.
Lip sync:MuseTalk video.
It combines Claude, Whisper, Chatterbox and MuseTalk for speech recognition, conversation, TTS and lip-synced video.
Features
Photo-driven:One image.
Voice cloning:Chatterbox.
Real time:Low latency.
Lip sync:MuseTalk video.
