Editing Video

Your tool does a wonderful job of separating out who is talking at which timestamp within YouTube.  Do you know a way I could feed this into an editing tool or some sort of ai program that could then edit the original YouTube video into two videos: one is just when speaker 1 talks. the other is when speaker 2 talks.  This would be killer for me since I want to study interviewers, and I could then isolate their footage.