Wouldn't that mean actually more work than even watching the video? The point of such a helper tool is to spare time, not to have fun with toys. I mean nothing wrong with toys but hardly a help in this case.
I'm interested in 1-2h long videos of people talking about interesting stuff. But I don't have time to watch them all.
It'd be great to have a tool to get accurate transcripts. The YouTube subtitles can be easily downloaded, but aren't readable on their own. They often lack even basic punctuation or sentence structure.
It'd be even more great to get good condensed transcripts, or event targeted condensed transcripts of the things I'm interested in in that particular video.