Is there a plugin or tool that you can recommend that can reliably separate speaking voices into separate tracks? For example, for a conversation recorded from a Zoom call that’s in one mono audio track, where there’s a requirement to position the separate participants into different places in the stereo field, or to separately edit out um’s, ahs and the like.
Googling around just keeps coming back with musical voices separation, which isn’t what I’m looking for.
Thanks!
Spectralayers pro version
Thanks, I’ll try that (my SL pro version was still on v7, have upgraded).
Shown by Dom Sigalas in a YT Video
Am I understanding this right: You have a mono audio file with X number of individuals speaking and you’re hoping to get X number of audio files out - one for each individual?
I don’t think there is such a tool out there that does not require you to train it on each of the individual’s voices before you can have it automatically separate them from each other.
Spectralayers. It’s hit-or-miss, but sometimes it works wonders.
Am I understanding this right: You have a mono audio file with X number of individuals speaking and you’re hoping to get X number of audio files out - one for each individual?
Yes, that’s the problem to be solved. It looks like there’s an ‘unmix multiple voices’ feature in SL 12 pro that supports being trained on each voice in isolation before attempting to separate them, which ought to do what I want. In my case, it’ll always be two or three voices. I’ll get a chance to try it out on some recordings later this week, and will report back on whether it worked well enough to use.
The thing with Spectralayers is you can use tools to get into more detail if it can’t get it perfect automatically. Trouble is if you need to do this a lot. Let us know how well it works.