FilterHN

Show HN: OpenWhisper – free, local, and private voice-to-text macOS app

35 points

by rwu1997

1 day ago

| past

| 8 comments

| github.com

| HN

I wanted a voice-to-text app but didn't trust any of the proprietary ones with my privacy.

So I decided to see if I could vibe code it with 0 macOS app & Swift experience.

It uses a local binary of whisper.cpp (a fast implementation of OpenAI's Whisper voice-to-text model in C++).

Github: https://github.com/richardwu/openwhisper

I also decided to take this as an opportunity to compare 3 agentic coding harnesses:

Cursor w/ Opus 4.6: - Best one-shot UI by far - Didn't get permissioning correct - Had issues making the "Cancel recording" hotkey being turned on all the time

Claude Code w/ Opus 4.6: - Fewest turns to get main functionality right (recording, hotkeys, permissions) - Was able to get a decent UI with a few more turns

Codex App w/ Codex 5.3 Extra-High: - Worst one-shot UI - None of the functionality worked without multiple subsequent prompts

▲

stavros

1 day ago

[-]

I really like https://handy.computer for this.

▲

venusenvy47

22 hours ago

[-]

I'm looking for something to transcribe .m4a recordings that I make for my genealogy efforts. Do you know of anything that can take a file as input?

▲

stavros

17 hours ago

[-]

Whisper.cpp will do it, and you can also use Parakeet v2, though I haven't tried running that one specifically.

▲

purrcat259

21 hours ago

[-]

If you're familiar with CLI you could use ffmpeg to extract audio then pipe the audio into whatever transcriber

▲

venusenvy47

19 hours ago

[-]

I use ffmpeg a lot, but I'm curious if anyone can recommend a transcribe tool.

▲

whinvik

1 day ago

[-]

Another vote for handy. I am using with Parakeet and its pretty good.

Now its mostly about models getting better.

▲

aanet

23 hours ago

[-]

Thanks for the Handy info. (New to me)

Haven’t used Parakeet, but noting it too.

Commenting here so I come back to it.

▲

podlp

15 hours ago

[-]

Pretty nice to have menu bar integration. For macOS 26+, why not use the already-installed on-device speech transcription models?

▲

zenapollo

1 day ago

[-]

I thought i had tried this but no it’s a massively crowded app name. I’ll check this out soon, but honestly this one has been great.

https://github.com/Starmel/OpenSuperWhisper

Though it seems like the dev stopped work on it

▲

PhilippGille

1 day ago

[-]

That's a very similar name as https://github.com/OpenWhispr/openwhispr

Which is a voice to text app as well.

▲

kristianp

1 day ago

[-]

MacWhisper has been around for a while and it says no data leaves your machine.

https://goodsnooze.gumroad.com/l/macwhisper

▲

dcsan

1 day ago

[-]

how does it compare to wispr flow?

which beats the pants off android or iphone transcription...

▲

umtksa

1 day ago

[-]

the video on github is not working

▲

eduction

1 day ago

[-]

Requiring microphone access is a dealbreaker. I transcribe audio files I’ve recorded on other equipment. You don’t need my mic for that.

I clicked hoping it would leverage whisper’s translation capabilities as well, since MacWhisper does not do that (it leverages Apple’s subpar built in translation). It doesn’t do that either.

(Maybe you’re using this for dictation? That’s a very specific subset of transcription. I’d suggest using a name that leans into that.)