Zé

!git clone https://github.com/OpenTalker/SadTalker.git
%cd SadTalker
!pip install -r requirements.txt

Depois sobe tua foto e áudio

from src.modules import SadTalkerInference
sad_talker = SadTalkerInference()
video = sad_talker.generate_from_one_img(
img_path='sua_foto.jpg',
audio_path='voz_personagem.wav'
)