Hi, nice project! Quick question, when I speak Chinese language, why it output English as translated output? I was using the multilingual (small) model. Do I need to use the Parakeet model to have Chinese output? Thx.
Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS
201–210 of 233 posts
Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS
#202I really like the project and am eager to try and fit this into some of my workflows. However, this bothered me a bit:
"All models run locally, no private data leaves your computer. And it's spicy to offer something for free that other apps have raised $80M to build."
I’d straight up drop the comparison to big AI labs. This isn’t rebellious or subversive, it’s downstream of a ton of already-funded work. Calling it “spicy” is a bit misframed.
Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS
#203This got me thinking that the smaller these local first LLMs get - the more they're gonna looking the next bread and butter of app dev. Reminds me how Electron gained a lot of traction for making it easy to package prettier apps. At the measly cost of gigabytes of RAM, give or take.
Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS
#204This 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…
macOS and iOS can do that to with the baked in dictation. Globe key + D on Mac
Nothing comes close to LLM transcription though.
I just tried this. I said "globe key dictation, does this work?". Here's the transcription, verbatim:
"Fucking dictation, does this work"
Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS
#205This got me thinking that the smaller these local first LLMs get - the more they're gonna looking the next bread and butter of app dev. Reminds me how Electron gained a lot of traction for making it easy to package prettier apps. At the measly cost of gigabytes of RAM, give or take.
Exactly, everything will become ClaudeVM https://jperla.com/blog/the-future-is-claudevm
Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS
#206This thread is a support group for people who have each independently built the same macOS speech-to-text app.
NGL had me chuckling a bit there when I remembered I had one of these to code on my backlog
Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS
#207This got me thinking that the smaller these local first LLMs get - the more they're gonna looking the next bread and butter of app dev. Reminds me how Electron gained a lot of traction for making it easy to package prettier apps. At the measly cost of gigabytes of RAM, give or take.
Exactly, everything will become ClaudeVM https://jperla.com/blog/the-future-is-claudevm
[dead]
Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS
#208[dead]
Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS
#209Earlier quoted context omitted.
Thank you, I have added localvoxtral[0] and fixed FluidVoice 0. https://github.com/T0mSIlver/localvoxtral
Awesome, thanks. Now it looks like five features are table stakes and there's no need to filter for, for example, speech to text. So, it would be interesting to see the differentiation, the why would I choose which one. I see promise trying to get a bit more into curating by showing the top one or two or three picks for a given standout feature.
[dead]
Re: Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS
#210Earlier quoted context omitted.
When you activate it you agree that your voice input is sent to Apple. As far as I understand this project runs fully locally. Up to you to decide for whatever suits your needs best.
Where did you get from that the voice input is sent to Apple / the cloud? As far as I understand Apple’s voice model runs locally for most languages. Siri commands can be used for training, but is also executed locally and sent to Apple separately (and this can be disabled).
I couldn't believe it either but when you enable it the settings of macOS you get this popup:
> When you dictate text, information like your voice input and contact names are sent to Apple to help your Mac recognize what you’re saying.