I've been using Scene Edit Detection and finding it very helpful.
I'm wondering, however, if there is a feature that could be built into it...
What if AI could detect when a speaker starts and stops talking. Then give us 'Cuts' on every 'In and Out' of what someone is saying.
Let's say it's a two minutes of talking.
Could an AI distinguish points at which the speaker starts and stops their sentences?
It would be difficult because it would have to look for specific pauses, not just every single sentence.
But sometimes I'm pulling out Question and Answers from an interview.
Could an AI find every time a subject answers a question and create a Cut point for it?