Handy: privacy-preserving open-source speech-to-text
(2026-03-03)Iâve recently discovered Handy, a small speech-to-text (dictation) application, that is open source and can use only local AI models on Linux, preserving the privacy of what Iâm saying out loud by not sending it to some cloud servers. I found it handy (lol), so I figured that I could share some hardships that Iâve run into while setting it up on ArchLinux.