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

Handy – Free open source speech-to-text app

github.com

Post reply on HN
Print view View original

101–110 of 118 posts

Re: Handy – Free open source speech-to-text app

#103

Post by sipjca »

mixtureoftakes wrote: post #69
sipjca wrote: post #61

Earlier quoted context omitted.

It’s all local

Which model would be the best to use for mandarin? Are there any models on par with Parakeet that are just as fast but also understand Chinese?

I believe sensevoice, I’ll hopefully be implementing it soon enough

Re: Handy – Free open source speech-to-text app

#104

Post by SkyPuncher »

d4rkp4ttern wrote: post #95
SkyPuncher wrote: post #94

Earlier quoted context omitted.

But, OSX does come back and fix things.

You mean, after displaying each word as it is spoken, then OSX goes back and fixes what’s been displayed? I think I’ve seen it fix one or two recent words, but I guess you’re saying it could fix the entire sentence as well. I didn’t know that

Yea, I use it daily for getting my thoughts into Claude. I often see it rewriting sentences it’s confused on.

Re: Handy – Free open source speech-to-text app

#106

Post by vismit2000 »

thethimble wrote: post #90
d4rkp4ttern wrote: post #63

I’ve tried several, including this one, and I’ve settled on VoiceInk (local, one-time payment), and with Parakeet V3 it’s stunningly fast (near-instant) and accurate enough to talk to LLMs/code-agents, in the sense that the slight drop in accuracy relative to Whisper Turbo3 is immaterial since they can “read between the lines” anyway. My regular cycle is to talk informally to the CLI agent and ask it to “say back to…

I wish one of these models was fine tuned for programming. I want to be able to say things like "cd ~/projects" or "git push --force".

You can try VSCode Speech to Text extension that works decently well in Github Copilot chat as part of Microsoft accessibility suite.

Re: Handy – Free open source speech-to-text app

#108

Post by frankdilo »

tin7in wrote: post #9
frankdilo wrote: post #8

This looks great! What’s missing for me to switch from something like Wispr Flow is the ability to provide a dictionary for commonly mistaken words (name of your company, people, code libraries).

It has something called "Custom Words" which might be what you are describing. Haven't tested this feature yet properly.

So is this already in Handy or you are referring to a feature of the underlying models you are still not actively using?

Re: Handy – Free open source speech-to-text app

#110

Post by tin7in »

frankdilo wrote: post #108
tin7in wrote: post #9

Earlier quoted context omitted.

It has something called "Custom Words" which might be what you are describing. Haven't tested this feature yet properly.

So is this already in Handy or you are referring to a feature of the underlying models you are still not actively using?

This is already in Handy in Advanced > Custom Words.

There is also Post Processing where you can rerun the output through an LLM and refine it, which is the closest to what Wispr Flow is doing.

This can be found in the debug menu in the GUI (Cmd + Shift + D).

Post reply on HN