7 comments

[ 4.5 ms ] story [ 28.7 ms ] thread
I love on-device transcription apps, but this looks like yet another AI generated whisper wrapper. I'm put off by the readme which is clearly LLM generated, with emdash all over the place and bits that smell of user questions turned into talking points.

> Why not the Fn / key? It's the obvious one-finger choice, but on macOS the Fn key emits no real keypress — only a hidden hardware flag — so

And

> macOS permissions (read this if the hotkey "does nothing")

Sorry but I can't see a reason to use this over something tried and tested like Handy, which is free, open source, on-device, does post capture correction and isn't limited to whisper (you can use parakeet v3 which I find way better than whisper)

[flagged]
If you think that's bad, you should learn how modern TTS and STT engines work
My current fav STT is Hex, MacOS only:

https://github.com/kitlangton/Hex

Near-instant accurate-enough transcription using local Parakeet V3.

Handy is multi-platform, also great:

https://github.com/cjpais/Handy

Every time a new STT model or app is announced, I see if it displaces Hex for me but so far none have.

I’ll check out Yap though.

I use handy and it does the job very well, is there a difference with hex or any other transcription app if we are using the same underlying model? Or just UI/UX stuff?
I was also a fan of Hex, but development has stalled. I tried FluidVoice (found it buggy) and Handy (had problems with hotkey) before eventually landing on TypeWhisper[0].

It works very well, and has a few more bells and whistles without feeling bloated.

[0] https://www.typewhisper.com