Generate exportable 3D Gaussian Splatting assets from a single image, create conversational TalkingHeads from photos, and turn audio into facial animation. Build with APIs and SDKs for Unity and Unreal Engine.
The generated 3D digital character is quite vivid. It has some basic facial expressions, can recognize users' voice questions and conduct real-time conversations. When answering questions, it can not only use the knowledge base content set by users, but also generate content intelligently through AI for replies.
What needs improvement
Wish it can dance jump and more facial movements
vs Alternatives
It can recognize your voice and chat with you. It can also generate replies with AI knowledge base