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

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

#1

Post by MattHart88 » Mon, Apr 06, 2026, 7:50 PM UTC

I built this because I wanted to see how far I could get with a voice-to-text app that used 100% local models so no data left my computer. I've been using a ton for coding and emails. Experimenting with using it as a voice interface for my other agents too. 100% open-source MIT license, would love feedback, PRs, and ideas on where to take it.

Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS
github.com

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

#2

Post by charlietran » Mon, Apr 06, 2026, 8:00 PM UTC

Thank you for sharing, I appreciate the emphasis on local speed and privacy. As a current user of Hex (https://github.com/kitlangton/Hex), which has similar goals, what are your thoughts on how they compare?

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

#3

Post by ipsum2 » Mon, Apr 06, 2026, 8:06 PM UTC

Parakeet is significantly more accurate and faster than Whisper if it supports your language.

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

#4

Post by goodroot » Mon, Apr 06, 2026, 8:08 PM UTC

Nice one! For Linux folks, I developed https://github.com/goodroot/hyprwhspr.

On Linux, there's access to the latest Cohere Transcribe model and it works very, very well. Requires a GPU though. Larger local models generally shouldn't require a subordinate model for clean up.

Have you compared WhisperKit to faster-whisper or similar? You might be able to run turbov3 successfully and negate the need for cleanup.

Incidentally, waiting for Apple to blow this all up with native STT any day now. :)

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

#5

Post by konaraddi » Mon, Apr 06, 2026, 8:13 PM UTC

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

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

#6

Post by yeutterg » Mon, Apr 06, 2026, 8:26 PM UTC

ipsum2 wrote: post #3

Parakeet is significantly more accurate and faster than Whisper if it supports your language.

Are you running Parakeet with VoiceInk[0]?

[0]: https://github.com/beingpax/VoiceInk

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

#7

Post by treetalker » Mon, Apr 06, 2026, 8:26 PM UTC

ipsum2 wrote: post #3

Parakeet is significantly more accurate and faster than Whisper if it supports your language.

I have been using Parakeet with MacWhisper's hold-to-talk on a MacBook Neo and it's been awesome.

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

#8

Post by hephaes7us » Mon, Apr 06, 2026, 8:27 PM UTC

goodroot wrote: post #4

Nice one! For Linux folks, I developed https://github.com/goodroot/hyprwhspr . On Linux, there's access to the latest Cohere Transcribe model and it works very, very well. Requires a GPU though. Larger local models generally shouldn't require a subordinate model for clean up. Have you compared WhisperKit to faster-whisper or similar? You might be able to run turbov3 successfully and negate the need for cleanup. Incid…

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.

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

#9

Post by rahimnathwani » Mon, Apr 06, 2026, 8:38 PM UTC

ipsum2 wrote: post #3

Parakeet is significantly more accurate and faster than Whisper if it supports your language.

Right, and if you're on MacOS you can use it for free with Hex: https://github.com/kitlangton/Hex

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

#10

Post by goodroot » Mon, Apr 06, 2026, 8:39 PM UTC

hephaes7us wrote: post #8

goodroot wrote: post #4

Nice one! For Linux folks, I developed https://github.com/goodroot/hyprwhspr . On Linux, there's access to the latest Cohere Transcribe model and it works very, very well. Requires a GPU though. Larger local models generally shouldn't require a subordinate model for clean up. Have you compared WhisperKit to faster-whisper or similar? You might be able to run turbov3 successfully and negate the need for cleanup. Incid…

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.

They do, and they even have that nice microphone F5 key for it, and an ideal OS level API making the input experience >perfectApparently they do have a better model, they just haven't exposed it in their own OS yet!

https://developer.apple.com/documentation/speech/bringing-ad...

Wonder what's the hold up...

For footpedal:

Yes, conceptually it’s just another evdev-trigger source, assuming the pedal exposes usable key/button events.

Otherwise we’d bridge it into the existing external control interface. Either way, hooks are there. :)