this post was submitted on 29 Aug 2025
164 points (99.4% liked)

Open Source

40238 readers
299 users here now

All about open source! Feel free to ask questions, and share news, and interesting stuff!

Useful Links

Rules

Related Communities

Community icon from opensource.org, but we are not affiliated with them.

founded 6 years ago
MODERATORS
Cloak@lemmy.ml
kevincox@lemmy.ml
CrypticCoffee@lemmy.ml
Lettuceeatlettuce@lemmy.ml
164
Meet Jambi - a blazing-fast voice transcription application built with Rust (lemmy.ml)
submitted 18 hours ago* (last edited 18 hours ago) by guttermonk@lemmy.ml to c/opensource@lemmy.ml
10 comments fedilink hide all child comments
 

Jambi’s mission is to transcribe audio to your clipboard, as quickly and accurately as possible, while staying privacy-focused and open-source.

Jambi aims to help computer users with disabilities, such as vision or physical impairments, by providing real-time transcription of their speech. It’s also a great tool for anyone who wants to transcribe audio quickly and easily.

This is the alpha release and the project is still in early development. Currently looking for feedback and contributors. If you are a developer, you can contribute to the project by submitting pull requests or reporting issues.

If you like the project, please show your support by leaving a star. Thanks! https://github.com/guttermonk/jambi

top 10 comments
sorted by: hot top controversial new old
[–] marighost@piefed.social 24 points 18 hours ago (1 children)

I'm not a developer but I see this being immensely useful for a lot of people. Good luck to you! :)

[–] guttermonk@lemmy.ml 13 points 18 hours ago

That means a lot to me. Thanks so much for your kind words!

[–] black_flag@lemmy.dbzer0.com 7 points 17 hours ago (3 children)

Is there any reason you chose vosk over whisper.c++?

[–] guttermonk@lemmy.ml 13 points 16 hours ago

I'm not familiar with whisper.c++ but I did try faster-whisper. Unfortunately, the transcriptions took upward of 40sec and it didn't offer live transcription, which is a nice feature of vosk. There's a comparison in the readme with other differences. That said, it should be relatively modular. It shouldn't take much to swap it back to whisper if that's what you prefer to use. Whisper is in the nix flake as optional, and the program allows you to change models but i haven't bothered trying to switch back to Whisper since Vosk has been more performant.

[–] guttermonk@lemmy.ml 6 points 15 hours ago

I should also add that if you don't want to reconfigure Jambi to use Whisper, you can try WhisperNow, which is built in Python and uses Whisper. I saw similar transcription performance when I used Whisper with Jambi and decided to move forward with Vosk after testing Whisper in both programs.

[–] FailBetter@crust.piefed.social 1 points 16 hours ago

Probably just playing it safe since vosk has been around longer iirc Is kinda weird to rust and not choose the more performant whisper tho

[–] pfr@piefed.social 4 points 16 hours ago (1 children)

Looks cool, I'll definately try it out.

Any plans for an Android APK?

[–] guttermonk@lemmy.ml 10 points 16 hours ago (1 children)

I use the Futo Keyboard on Android which already has this feature. It's also opens source, and I've had a really good experience with it so far.

[–] pfr@piefed.social 2 points 10 hours ago (1 children)

Nice, I'll check it out

[–] Cris_Color@lemmy.world 3 points 6 hours ago

I believe futo keyboard might be more "source available" than open source, but it's still a great app! (I'm typing with it now and it's my favorite more open keyboard app I've used :)

If you want to use another keyboard app like the fantastic FOSS Heliboard, you can also just use the futo voice input app as a voice input provider :)

Futo apps are available through their own f-droid repo if you wanna install/update through an f-droid client- I figured I'd mention that just in case you go searching for it and don't see it since it's not in one of the common repos