Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

github.com

Post reply on HN
Print view View original

181–190 of 233 posts

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

#181

Post by taffydavid »

cootsnuck wrote: post #84
arkensaw wrote: post #77

This is great, and I'm not knocking it, but every time I see these apps it reminds me of my phone. My 2021 Google Pixel 6, when offline, can transcribe speech to text, and also corrects things contextually. it can make a mistake, and as I continue to speak, it will go back and correct something earlier in the sentence. What tech does Google have shoved in there that predates Whisper and Qwen by five years? And why do…

Interesting. My Pixel 7 transcription is barely usable for me. Makes way too many mistakes and defeats the purpose of me not having to type, but maybe that's just my experience. The latest open source local STT models people are running on devices are significantly more robust (e.g. whisper models, parakeet models, etc.). So background noise, mumbling, and/or just not having a perfect audio environment doesn't trip u…

I've built my own tts apps testing whisper and while it's good it does hallucinate quite a bit if there's noise, or just sometimes when the audio is perfectly clear.

It often gives the illusion of being very good but I could record a half hour of me speaking and discover some very random stuff in the middle that I did not say

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

#182

Post by sipjca »

xyos wrote: post #174
sipjca wrote: post #154

Earlier quoted context omitted.

I just don't have the bandwidth to run another project, maintaining Handy is hard enough on it's own, especially for free! I didn't just dismiss for no reason, I am a human! I have needs and I can't just sleeplessly stay in front of the computer putting out code. If I had more time I would, but alas. Someone could easily vibe code an iOS version in a few hours. I could do the same but I do not have time to support it…

Thank you for your work, I highly appreciate it!

Thank you!!

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

#183

Post by primaprashant »

ArlenBales wrote: post #147
primaprashant wrote: post #47

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

Can you explain how exactly dictation is used for development? I type about 120 WPM so typing is always going to be way faster for me than talking. Aside for accessibility, is dictation development for slower typers or is it more so you can relax on a couch while vibe coding? If this comes off as condescension it's not intended, I am genuinely out of the loop here.

For me personally, it's not really about typing speed. While I can type pretty fast and most likely I speak faster than typing, but typing and dictating are just different way of doing things for me. While the end result of both is same, but for me it's just like different way of doing things and it's not a competition between the two.

I regularly just sit down and often just describe whatever I'm trying to do in detail and I speak out loud my entire thought process and what kind of trade-offs I'm thinking, all the concerns and any other edge cases and patterns I have in my mind. I just prefer to speak out loud all of those. I regularly speak out loud for 5 to 10 minutes while sometimes taking some breaks in between as well to think through things.

I am not doing it just for vibe coding, I'm using it for everything. So obviously for driving coding agents, but also for in general, describing my thoughts for brainstorming or having some kind of like a critique session with LLMs for my ideas and thoughts. So for everything, I'm just using dictation.

One other benefit I think for me personally is that since I'm interacting with coding agents and in general LLMs a lot again and again every day, I end up giving much more context and details if I'm speaking out loud compared to typing. Sometimes I might feel a little bit lazy to type one or two extra sentences. But while speaking, I don't really have that kind of friction.

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

#184

Post by theturtletalks »

earthnail wrote: post #175
theturtletalks wrote: post #109

Earlier quoted context omitted.

I'm tracking them all here: https://opensource.builders/alternatives/superwhisper Just added Ghost Pepper, and you can actually create a skill.md with the features you need to build your own

Please add wordbird as well: https://github.com/tillahoffmann/wordbird It has all the usual features, plus you can add project specific vocabulary in your repo. It detects the working folder based on the active window, reads a WORDBIRD.md file in that folder and corrects terms accordingly. (My friend Till built it)

Added Wordbird and its features

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

#185

Post by theturtletalks »

zgougou123 wrote: post #176
theturtletalks wrote: post #109

Earlier quoted context omitted.

I'm tracking them all here: https://opensource.builders/alternatives/superwhisper Just added Ghost Pepper, and you can actually create a skill.md with the features you need to build your own

You could add foxsay, a great one : https://github.com/skulkworks/foxsay

Added Foxsay and its features

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

#186

Post by theturtletalks »

Barbing wrote: post #157
theturtletalks wrote: post #109

Earlier quoted context omitted.

I'm tracking them all here: https://opensource.builders/alternatives/superwhisper Just added Ghost Pepper, and you can actually create a skill.md with the features you need to build your own

Very nice. Two great features I'd suggest highlighting in two apps, one app of which you have listed. 1: livestream transcript directly into the cursor in real time (just like native macOS dictation) 2: show realtime transcript live in an overlay (still has to paste when done, unlike #1, but can still read live while dictating) 1- localvoxtral, 2- FluidVoice (bumping it to 7 features on your list)

Thank you, I have added localvoxtral[0] and fixed FluidVoice

0. https://github.com/T0mSIlver/localvoxtral

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

#187

Post by theturtletalks »

dnlzro wrote: post #124
theturtletalks wrote: post #109

Earlier quoted context omitted.

I'm tracking them all here: https://opensource.builders/alternatives/superwhisper Just added Ghost Pepper, and you can actually create a skill.md with the features you need to build your own

Another one to add (1.5k stars on GitHub): https://github.com/kitlangton/Hex

Added Hex and its features

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

#188

Post by theturtletalks »

v4nn4 wrote: post #165
theturtletalks wrote: post #109

Earlier quoted context omitted.

I'm tracking them all here: https://opensource.builders/alternatives/superwhisper Just added Ghost Pepper, and you can actually create a skill.md with the features you need to build your own

The filters selection seems to return a union not an intersection which is a bit confusing, at least to me.

I’ve fixed this issue, please try it again when you get a chance
Post reply on HN