

Powered By RTX 4090
Input a photo and text, and you can get a digital human that broadcasts the text.
You can also combine it with the following workflow to clone the voice, so you can create a digital human with highly customized "voice," "text," and "appearance."
Epsilon
2024-09-20 Update
Epsilon
2024-09-20 Update
Workflow introduction
Input a photo and text, and you can get a digital human that broadcasts the text.
You can also combine it with the following workflow to clone the voice, so you can create a digital human with highly customized "voice," "text," and "appearance."
Nodes Information
9
LoadImage
CosyVoiceNode
Echo_LoadModel
Echo_Sampler
JWImageResizeToSquare
PreviewAudio
SaveAudio
TextNode
VHS_VideoCombine