Sounds like there's plenty of interest in those kind of tools. I'm not a huge fun API transcriptions given great local models.
I build https://github.com/bwarzecha/Axii to keep EVERYTHING locally and be fully open source - can be easily used at any company. No data send anywhere.
Could you make it use Parakeet? That's an offline model that runs very quickly even without a GPU, so you could get much lower latency than using an API.
I love this idea, and originally planned to build it using local models, but to have post-processing (that's where you get correctly spelled names when replying to emails / etc), you need to have a local LLM too.
If you do that, the total pipeline takes too long for the UX to be good (5-10 seconds per transcription instead of <1s). I also had concerns around battery life.
Since many are asking about apps with simillar capabilities I’m very happy with MacWhisper. Has Parakeet, near instant transcription of my lengthy monologues. All local.
Edit: Ah but Parakeet I think isn’t available for free. But very worthwhile single purchase app nonetheless!
Handy appears to keep the audio clips, It does have a section in the settings to limit how many of those it keeps and there does not appear to be an upper limit, but it does have to be manually set. (I set mine to 99,999).
It would be nice if below 0 it had a -1 option to keep all recordings.
I created Voibe which takes a slightly different direction and uses gpt-4o-transcribe with a configurable custom prompt to achieve maximum accuracy (much better than Whisper). Requires your own OpenAI API key.
For those using something like this daily, what key combinations do you use to record and cancel. I’m using my capslock right now but was curious about others
I just vibe coded a my own NaturalReader replacement. The subscription was $110/year... and I just canceled it.
Chatterbox TTS (from Resemble AI) does the voice generation, WhisperX gives word-level timestamps so you can click any word to jump, and FastAPI ties it all together with SSE streaming so audio starts playing before the whole thing is done generating.
There's a ~5s buffer up front while the first chunk generates, but after that each chunk streams in faster than realtime. So playback rarely stalls.
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 modify it as per my needs.
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.
for me it strikes the balance of good, fast, and cheap for everyday transcription. macwhisper is overkill, superwhisper too clever, and handy too buggy. hex fits just right for me (so far)
60 comments
[ 2.9 ms ] story [ 82.2 ms ] threadI build https://github.com/bwarzecha/Axii to keep EVERYTHING locally and be fully open source - can be easily used at any company. No data send anywhere.
If you do that, the total pipeline takes too long for the UX to be good (5-10 seconds per transcription instead of <1s). I also had concerns around battery life.
Some day!
It’s free and offline
[0] https://github.com/EpicenterHQ/epicenter
https://news.ycombinator.com/item?id=36460246
https://blazingbanana.com/work/whistle
https://github.com/Beingpax/VoiceInk
Edit: Ah but Parakeet I think isn’t available for free. But very worthwhile single purchase app nonetheless!
It would be nice if below 0 it had a -1 option to keep all recordings.
https://handy.computer/
https://github.com/corlinp/voibe
I do see the name has since been taken by a paid service... shame.
Chatterbox TTS (from Resemble AI) does the voice generation, WhisperX gives word-level timestamps so you can click any word to jump, and FastAPI ties it all together with SSE streaming so audio starts playing before the whole thing is done generating.
There's a ~5s buffer up front while the first chunk generates, but after that each chunk streams in faster than realtime. So playback rarely stalls.
It took about 4 hours today... wild.
My take for X11 Linux systems. Small and low dependency except for the model download.
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 modify it as per my needs.
F12 Press → arecord (ALSA) → temp.wav → faster-whisper → xclip + xdotool
https://github.com/ksred/soupawhisper
Thanks to faster-whisper and local models using quantization, I use it in all places where I was previously using Superwhisper in Docs, Terminal etc.
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.
https://github.com/kitlangton/Hex
for me it strikes the balance of good, fast, and cheap for everyday transcription. macwhisper is overkill, superwhisper too clever, and handy too buggy. hex fits just right for me (so far)