pnkvalavala/digitaltwin

Using a single image and just 10 seconds of sample audio, our project enables you to create a video where it appears as if you're speaking the desired text.

语言：Jupyter Notebook · GitHub 星标：41 · Fork：13

话题：audio-driven-talking-face · deep-fake · talking-face-generation · text-to-speech · voice-cloning

在 GitHub 上查看原仓库