I'm working in a small fun project where I put my voice to read someone else speech, with the cadence, rythm and confidence (or doubt) of the speech itself. I know there are tools where with some sample audio from a person, something like a voice profile is created for later using it with text-to-speech apps, but I would like to use it more for speech-to-speech, if that makes sense.
Any info you guys could give me about this space? Thanks
[link] [comments]