There is one feature that I do care about.
Local speech recognition is genuinely useful and much more private than server based options.
Whisper works great, even the medium model is pretty good.
But I use the 3Gb all day every day.
I built a personal voice agent
https://github.com/lawless-m/TheHand
Whisper works great, even the medium model is pretty good.
But I use the 3Gb all day every day.
I built a personal voice agent
https://github.com/lawless-m/TheHand