How to isolate/figure out whispers in audio clip?

[Douglas Lucas]

Hey cypherpunks,

I have an .MP4 clip of Joe Biden whispering to 13-year-old Maggie Coons
before trying to kiss her:
https://douglaslucas.com/blog/wp-content/uploads/2021/02/JoeBiden_ChrisCoons_6Jan2015.mp4

The relevant portion of the clip begins at approx 1:05.

Biden whispers: "By the way, if you want to know how important it is,
being thirteen" and then I can't make out the rest, I think due to the
loud camera shutter.

Can anyone suggest an audio program (preferably for Linux) that can help
isolate Biden's voice? Computery techniques I could use, or you could
use, to help figure out what he's whispering?

For reference, the event this clip is from took place on January 6,
2015, and the full video is here:
https://www.c-span.org/video/?323601-1/senate-ceremonial-swearing-vice-president-biden

Doug