zlacker

This demo is really impressive: https://huggingface.co/spaces/mistralai/Voxtral-Mini-Realtim...

Don't be confused if it says "no microphone", the moment you click the record button it will request browser permission and then start working.

I spoke fast and dropped in some jargon and it got it all right - I said this and it transcribed it exactly right, WebAssembly spelling included:

> Can you tell me about RSS and Atom and the role of CSP headers in browser security, especially if you're using WebAssembly?

>>simonw+(OP)
Thank you for the link! Their playground in Mistral does not have a microphone. it just uploads files, which does not demonstrate the speed and accuracy, but the link you shared does.

I tried speaking in 2 languages at once, and it picked it up correctly. Truly impressive for real-time.

>>simonw+(OP)
Having built with and tried every voice model over the last three years, real time and non-real time... this is off the charts compared to anything I've seen before.

And open weight too! So grateful for this.

>>simonw+(OP)
404 on https://mistralai-voxtral-mini-realtime.hf.space/gradio_api/... for me (which shows up in the UI as a little red error in the top right).

>>simonw+(OP)
It can transcribe Eminem's Rap God fast sequence, really, really impressive.

>>simonw+(OP)
Wow, that’s weird. I tried Bengali, but the text transcribed into Hindi!I know there are some similar words in these languages, but I used pure Bengali that is not similar to Hindi.

>>jagged+T9
That's almost certainly in the training data, to be fair.

>>simonw+(OP)
Not terrible. It missed or mixed up a lot of words when I was speaking quickly (and not enunciating very well), but it does well with normal-paced speech.

>>pypris+hd
Well, on the linked page, it mentions "strong transcription performance in 13 languages, including [...] Hindi" but with no mention of Bengali. It probably doesn't know a lick of Bengali, and is just trying to snap your words into the closest language it does know.

>>simonw+(OP)
I’ve been using AquaVoice for real-time transcription for a while now, and it has become a core part of my workflow. It gets everything, jargon, capitalization, everything. Now I’m looking forward to doing that with 100% local inference!

>>simonw+(OP)
This model was able to transcribe Bad Bunny lyrics over the sound of the background music, played casually from my speakers. Impressive, to me.

>>Oras+61
According to the announcement blog Le Chat is powered by the new model as well: https://chat.mistral.ai/chat

>>jagged+T9
what a great test hahah

>>derefr+Zk
it must have some exposure to bengali— just not enough for them to advertise it. otherwise it would have a damn hard time.

>>simonw+(OP)
Doesn't seem to work for me - tried in both Firefox and Chromium and I can see the waveform when I talk but the transcription just shows "Awaiting audio input".

>>skykoo+NG
Same here. In Chromium I don't even see the waveform.

>>codeth+OI
I had to turn off ad-block to get it to work.

>>skykoo+NG
Try disabling CSP for the page

>>simonw+(OP)
Doesn’t seem to work in Safari on iOS 26.2, iPhone 17 Pro, just about anything extra disabled.

>>simonw+(OP)
It's really nice although I've got a sentence in French when I was speaking Italian but I corrected myself in the middle of a word.

But I'm definitely going to keep an eye on this for local-only TTS for Home Assistant.

>>simonw+(OP)
Here European Multilingual-Intelligence truly shines!

>>simonw+(OP)
is this demo running fully in the browser?

>>rafram+4h
Yeah it messed up a bit for me too when I didn't enunciate well. If I speak clearly it seems to work very well even with background noise. Remember Dragon Naturally Speaking? Imagine having this back then!

>>colord+Rd1
No, it's server-side.

Model is around 7.5 GB - once they get above 4 GB running them in a browser gets quite difficult I believe.

>>Oras+61
> Truly impressive for real-time.

Impressive indeed. Works way better than the speech recognition I first got demo'ed in... 1998? I remember you had to "click" on the mic everytime you wanted to speak and, well, not only the transcription was bad, it was so bad that it'd try to interpret the sound of the click as a word.

It was so bad I told several people not to invest in what was back then a national tech darling:

https://en.wikipedia.org/wiki/Lernout_%26_Hauspie

That turned out to be a massive fraud.

But ...

> I tried speaking in 2 languages at once, and it picked it up correctly.

I'm a native french speaker and I tried with a very simple sentence mixing french and english:

"Pour un pistolet je prefere un red dot mais pour une carabine je prefere un ACOG" (aka "For a pistol I prefer a red dot but for a carbine I prefer an ACOG")

And instead I got this:

"Je prépare un redote, mais pour une carabine, je préfère un ACOG."

"Je prépare un redote ..." doesn't mean anything and it's not at all what I said.

I like it, it's impressive, but literally the first sentence I tried it got the first half entirely wrong.

>>simonw+(OP)
I can't get that demo to work. Tried with both Firefox and Chrome.

>>tekacs+Y4
This past month Parakeet v3 dropped with a streaming ASR model that is 0.6B params, can run on a CPU and is super good.

>>Tactic+kq1
I used sell the Mac Voice Navigator (from Articulate Systems) in the 90s, which was a SCSI based hardware box that you plug into a Mac, Mac SE or Mac II. It used to use the same L&H speech recognition tech (if I recall correctly) and was called the "User Interface" of the future.

Horrible speech recognition rate and very glitchy. Customers hated it, and lots of returns/complaints.

A few years later, L&H went bankrupt. And so did Articulate Systems.

https://applerescueofdenver.com/products-page/macintosh-to-p...

>>daemon+D6
Same here

>>simonw+nh1
Because it's a 4gb download?

>>Barbin+AY
No long with Firefox or Edge or Chrome on either macOS or Android for me, either. Same issue on all.

>>dcl+PY1
I think that web browsers only allow up to 4GB of memory per tab.

>>GolDDr+ly1
Same here; the voice waveform animates as expected but the model doesn't do anything when I click on the microphone. It just says "Error" in the upper-right corner.

Also tried downloading and running locally, no luck. Same behavior.

>>carboc+Hp
Wow, so it has surpassed humans.

>>draken+MI1
Do you mean https://huggingface.co/nvidia/nemotron-speech-streaming-en-0... ?