I have a conversation recorded of 2 different people, the conversation contains a gap before every sentence or person to make it easier for the algorithm recorgnise the voice. I want to try to split an audio file into two, each contains only one speaker's speech. Just wondering how would I go about this task?
I don't know of anything that will do this automatically - perhaps some advanced broadcast reporter software [Hindenburg springs to mind], but that's outside my area. Many DAWs could do it manually at playback.
Duplicate the audio file, then select & edit both at once on playback. One key command, 2 cuts each time, down the length of the tracks. You then need a second pass to mute or delete the 'other' voice in each track. You could do it all in about the time it takes to play the track 3 times.