Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS • Hacker News Board

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#41

Post by LuxBennu » Mon, Apr 06, 2026, 9:47 PM UTC

goodroot wrote: post #21

LuxBennu wrote: post #12

Earlier quoted context omitted.

I've been running whisper large-v3 on an m2 max through a self-hosted endpoint and honestly the accuracy is good enough that i stopped bothering with cleanup models. The bigger annoyance for me was latency on longer chunks, like anything over 30 seconds starts feeling sluggish even with metal acceleration. Haven't tried whisperkit specifically but curious how it handles longer audio compared to the full model.

Ah yeah, longform is interesting. Not sure how you're running it, via whichever "app thing", but... On resource limited machines: "Continuous recording" mode outputs when silence is detected via a configurable threshold. This outputs as you speak in more reasonable chunks; in aggregate "the same output" just chunked efficiently. Maybe you can try hackin' that up?

Yeah that makes sense, chunking on silence would sidestep the latency issue pretty cleanly. I've been running it through a basic fastapi wrapper so it just takes whatever audio blob gets thrown at it, no chunking logic on the server side. Might be worth adding a vad pass before sending to whisper though, would cut down on processing dead air too.

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#42

Post by semiquaver » Mon, Apr 06, 2026, 9:48 PM UTC

purplehat_ wrote: post #36

Hi Matt, there's lots of speech-to-text programs out there with varying levels of quality. 100% local is admirable but it's always a tradeoff and users have to decide for themselves what's worth it. Would you consider making available a video showing someone using the app?

Slop

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#43

Post by douglaswlance » Mon, Apr 06, 2026, 9:49 PM UTC

does it input the text as soon as it hears it? or does it wait until the end?

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#44

Post by serf » Mon, Apr 06, 2026, 9:49 PM UTC

chrisweekly wrote: post #40

hephaes7us wrote: post #8

Earlier quoted context omitted.

Thanks for sharing! I was literally getting ready to build, essentially, this. Now it looks like I don't have to! Have you ever considered using a foot-pedal for PTT? Apple incidentally already has native STT, but for some reason they just don't use a decent model yet.

sorry, PTT?

push-to-talk.

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#45

Post by romeroej » Mon, Apr 06, 2026, 9:51 PM UTC

always mac. when windows? why can you just make things multios

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#46

Post by vunderba » Mon, Apr 06, 2026, 9:52 PM UTC

konaraddi wrote: post #5

That’s awesome! Do you know how it compares to Handy? Handy is open source and local only too. It’s been around a while and what I’ve been using. https://github.com/cjpais/handy

I’d also be interested to know what the impetus was for developing ghost-pepper, which looks relatively recent, given that Handy exists and has been pretty well received.

Extra bonus is that Handy lets add an automatic LLM post-processor. This is very handy for the Parakeet V3 model, which can sometimes have issues where it repeats words or makes recognition errors for example, duplicating the recognition of a single word a dozen dozen dozen dozen dozen dozen dozen dozen times.

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#47

Post by primaprashant » Mon, Apr 06, 2026, 9:53 PM UTC

Speech-to-text has become integral part of my dev flow especially for dictating detailed prompts to LLMs and coding agents.

I have collected the best open-source voice typing tools categorized by platform in this awesome-style GitHub repo. Hope you all find this useful!

https://github.com/primaprashant/awesome-voice-typing

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#48

Post by rcarmo » Mon, Apr 06, 2026, 9:53 PM UTC

Not sure why I should use this instead of the baked-in OS dictation features (which I use almost daily--just double-tap the world key, and you're there). What's the advantage?

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#49

Post by qq66 » Mon, Apr 06, 2026, 9:56 PM UTC

rcarmo wrote: post #48

Not sure why I should use this instead of the baked-in OS dictation features (which I use almost daily--just double-tap the world key, and you're there). What's the advantage?

I haven't used this one but WisprFlow is vastly better than the built-in functionality on MacOS. Apple is way behind even startups, even for fundamental AI functionality like transcribing speech

Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS

#50

Post by MattHart88 » Mon, Apr 06, 2026, 9:57 PM UTC

ttul wrote: post #28

guzik wrote: post #18

Sadly the app doesn't work. There is no popup asking for microphone permission. EDIT: I see there is an open issue for that on github

And many people are mailing in Codex and Claude Code generated PRs - myself included. Fingers crossed, I suppose.

Thanks to everyone who submitted PRs! The fix is merged, new version is up.