I likely know the answer here, but especially with AI now, is there any way to separate two voices in a recording? Not a long passage (just a word or two) but I’m working on the audio from a Zoom session (a wedding) and someone had an open mike. I’ve cleaned out most parts, but there’s one or two words that have 2 voices simultaneously and I just can’t pick out enough of the unwanted voice to clean it out. I know its a very long shot, but thought I’d ask.
Alternatively, a way (or program) to create a word or two in a particular voice using a typed word or the word spoken by someone else. I don’t play much with AI stuff, but maybe someone out there has?
