I’ve seen a couple automated lip sync programs out there, but i was wondering how one would go about creating his own? I’ve thought about doing speech to text, then somehow convert that to visemes and work from there.
But for one, do i use a voice interpreter i fond already? Or is it possible to make one with code. And suppose i use voice to text, is there a way or a good program to map that to a time key instead of just printing out a paragraph?
I know auto lip sync looks horrible, but i really want to try to make my own.