Speech to text, Voice typing is cool.
F-droid lists opensource apps that support Whisper and Vosk models.
Futo voice is not opensource, but is source available.
It’s good for English. For my mother tongue, Malayalam, the support seems to be underdeveloped currently.
Handy seems to be good for Windows, but have not used it much.
Then for Translations:
https://f-droid.org/packages/dev.davidv.translator/
Using Mozilla’s translation Models. A good enough offline and Open source alternative to GTranslate.
Are there other cool uses of offline ML/AI that you know?
I was always fascinated by declarative Linux distros like NixOS and tiling managers, but the thing that always stopped me is it’s time consume aspect. Everything had to be written by hand, et cetera.
Now it’s as simple as “Hey buddy ChatGPT, install this and that, make these keyboard shortcuts, turn off logs on startup, switch DM, debug this”. Some can say that’s not a true way - punch me, it’s the most easy way to configure your OS.