File: 8 hours long.
Task: Let's say I recorded my training shift at work. I want to remove anything but human speech from 8-hour long file, in order to create checklists/flow diagrams based on what was said in my training.
Output: I'd like the output to be a shorter audio file, which contains only speech (some/normal level of background noise is not a problem).
Question: What's the most efficient/fastest way to do that?
Potentially (not a necessity) it would be useful if I could plug the output into speech-to-text software if that's supported by audacity.