SadTalker

SadTalker

SadTalker,AI virtual digital human,one image plus one audio clip,synthesizes a face speaking that audio into video

Visit Site →

SadTalker Official Website, AI Virtual Digital Human, Create a video with a face speaking this voice from a picture and audio

SadTalker creates a video with a face speaking the voice from a picture and audio. It can be used directly with Stable Diffusion.
Open Source Address:https://github.com/OpenTalker/SadTalker
This is an open-source project corresponding to a CVPR 2023 paper, jointly released by Xi'an Jiaotong University, Tencent AI Lab, and Ant Group.