search

LuckyBian / EMOTTS

This is a TTS model based on VITS that can control the output speech emotion through natural language and control the speaker through reference audio.
4 stars 1 forks source link

Is there a demo? #1

Open RZJM opened 1 week ago

RZJM commented 1 week ago

Are there demos and pre-trained models?

thewh1teagle commented 1 week ago

Looking for samples too

LuckyBian commented 1 day ago

The model is still being improved and emotional control is being enhanced