Have you seen how granola.ai solve it?
“Works on all platforms, no meeting bots Granola transcribes your Mac's audio directly, with no meeting bots joining your call”
Yes, we do have this feature too, that's either way you prefer.
Is this via Recall too? Or something you've had to roll yourself? I've been curious at how much of this can happen on device vs being constantly streamed to the cloud and back (which often has significant latency implications given I'm based in Australia).
Also, very interesting idea for a product! As someone who has previously led sales teams at early stage startup I can totally relate to this challenge.