I had read 80% of the post and loved it. Then I came to see few comments - Saw yours and now having difficulty reading further. That means:
1. AI has gotten better - or eventually most people would like reading AI generated content
2. Author is just using AI to post-process - content is original
I wanted to build this for myself. Could never figure out how to get audio output from Mac. Tried almost all audio loopback driver (Blackhole, Soundflower ...). There was problem everywhere wrt security.
Even tried making a teams meeting bot. But Teams doesn't give live audio to developer unless you are a special partner.
One of the things I would want to do is - As the meeting is going on - I would like to ask a LLM what questions I could ask at that point in time. Especially if it's a subject I am not expert in.
Would I be able to create an extension that could do this?
Image in the readme would really be helpful.
In fact anytime there is a visual output it makes sense to put an image.
Thanks for creating this though - Will give it a try for an upcoming project.