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

Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue

github.com

Post reply on HN
Print view View original

131–139 of 139 posts

Re: Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue

#131

Post by elxr »

sathish316 wrote: post #49

To build your own STT (speech-to-text) with a local model and and modify it, just ask Claude code to build it for you with this workflow. F12 -> sox for recording -> temp.wav -> faster-whisper -> pbcopy -> notify-send to know what’s happening https://github.com/sathish316/soupawhisper I found a Linux version with a similar workflow and forked it to build the Mac version. It look less than 15 mins to ask Claude to mod…

> F12 Press → arecord (ALSA) → temp.wav → faster-whisper → xclip + xdotool

Okay starting point, but that last two only works on X11. Considering it's 2026, I really don't think a guide for someone wanting to make a speech-to-text app should be recommending X11.

Re: Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue

#132

Post by jimmySixDOF »

hackernewds wrote: post #102
jimmySixDOF wrote: post #96

Earlier quoted context omitted.

I didn't try Handy but been using Whisper-Key its super simple get out of your way all local single file executable (portable so zero install too) -- thats for Windows idk about the Mac version [1] https://github.com/PinW/whisper-key-local

the astroturfing here off topic of op post is unbearable

think you need to refresh your understanding of 'off topic' and 'astroturfing'

Re: Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue

#134

Post by lxe »

BatteryMountain wrote: post #125
lxe wrote: post #69

I built something similar for Linux (yapyap — push-to-talk with whisper.cpp). The "local is too slow" argument doesn't hold up anymore if you have any GPU at all. whisper large-v3-turbo with CUDA on an RTX card transcribes a full paragraph in under a second. Even on CPU, parakeet is near-instant for short utterances.The "deep context" feature is clever, but screenshotting and sending to a cloud LLM feels like massive…

I also built one.. mine is called whispy. I use mine to pump commands to claude. So far a bit hit & miss, still tweaking it.

Yeah, that's exactly what I started to do with mine. It runs local Whisper on a CUDA, on a graphics card. Whisper is actually better than any other model that I've seen, even things like Parakeet. It can do language detection. It automatically removes all the ahs and all the ohms unless I specifically enter them in my speech. I think this whole paragraph is going to take maybe half a second to process and paste without any issues.

(and it did it perfectly without any edits required for me at all.)

Re: Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue

#135

Post by xavpoon »

Another free option: Mellon (voice.mellon.chat) — fully local on Mac, no cloud, BYOK. Custom dictionary + phonetic corrections so it actually gets your technical terms right.

Also has an OpenClaw integration if anyone's using that for AI agents.

Full disclosure: I built it.

Re: Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue

#136

Post by tomashm »

k9294 wrote: post #97

I'm building in the same space, Workin on https://ottex.ai - It's a free STT app, with local models and BYOK support (OpenRouter, Groq, Mistral, and more). The top feature is the per-app custom settings - you can peak different models and instructions for different apps and websites. - I use the Parakeet fast model when working with Claude Code (VS Code app). - And I use a smart one when I draft notes in Obsidian. I…

Interesting, but I quickly uninstalled it after (1) it asked for permission to record keystrokes across all application and (2) registered global keyboard shortcut Option+Space without asking me.

Re: Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue

#138

Post by 0x457 »

Wowfunhappy wrote: post #80
lxe wrote: post #69

I built something similar for Linux (yapyap — push-to-talk with whisper.cpp). The "local is too slow" argument doesn't hold up anymore if you have any GPU at all. whisper large-v3-turbo with CUDA on an RTX card transcribes a full paragraph in under a second. Even on CPU, parakeet is near-instant for short utterances.The "deep context" feature is clever, but screenshotting and sending to a cloud LLM feels like massive…

> The "local is too slow" argument doesn't hold up anymore if you have any GPU at all. By "any GPU" you mean a physical, dedicated GPU card, right? That's not a small requirement, especially on Macs.

On macs you actually don't need it as long as you have enough RAM.

I run 120M Parakeet model formt STT thing. Even that tiny model works much better than macos dictation these days.

Re: Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue

#139

Post by rafanocode »

lxe wrote: post #134
BatteryMountain wrote: post #125

Earlier quoted context omitted.

I also built one.. mine is called whispy. I use mine to pump commands to claude. So far a bit hit & miss, still tweaking it.

Yeah, that's exactly what I started to do with mine. It runs local Whisper on a CUDA, on a graphics card. Whisper is actually better than any other model that I've seen, even things like Parakeet. It can do language detection. It automatically removes all the ahs and all the ohms unless I specifically enter them in my speech. I think this whole paragraph is going to take maybe half a second to process and paste witho…

I did the same, called hapi. I also added meeting recordings + automations so i can use those voice notes to trigger stuff or repurpose them, or just save them anywhere i want.
Post reply on HN