[bootload]

" it would be interesting to have a diff tool for videos"

    videoA -> transcriptionA
                |
                V
    videoB -> transcriptionB
                |
                V
               diff

[rahimnathwani]

That seems too granular, as an additional 'uh' or 'and' would cause a sentence to be seen as different.

It might work well if you can first pair up the similar sentences from A and B, using word-level edit distance, or mapping to a lower-dimensional space using sentence embedding?

[bootload]

"seems too granular,"

Probably right. I used the term diff as a concept not implementation.