Voxtral Transcribe 2 • Hacker News Board

Re: Voxtral Transcribe 2

#201

Post by whimblepop » Thu, Feb 05, 2026, 3:43 AM UTC

fragmede wrote: post #116

codethief wrote: post #112

Earlier quoted context omitted.

Same here. In Chromium I don't even see the waveform.

I had to turn off ad-block to get it to work.

I can see the waveform but it still doesn't work for me. Switched to Edge, disabled all adblocking and privacy extensions, built-in tracking prevention, and "enhanced site security" (whatever that is), and still no dice. I'd love to try it and be impressed, but it seems impossible. :(

Re: Voxtral Transcribe 2

#202

Post by whimblepop » Thu, Feb 05, 2026, 3:48 AM UTC

Barbing wrote: post #131

simonw wrote: post #20

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 At…

Doesn’t seem to work in Safari on iOS 26.2, iPhone 17 Pro, just about anything extra disabled.

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

Re: Voxtral Transcribe 2

#203

Post by subset » Thu, Feb 05, 2026, 3:50 AM UTC

dcl wrote: post #196

simonw wrote: post #155

Earlier quoted context omitted.

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.

Because it's a 4gb download?

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

Re: Voxtral Transcribe 2

#204

Post by Obertr » Thu, Feb 05, 2026, 3:53 AM UTC

Very nice! The thing I am missing is turn detection. In real time audio we need the turn detection to understand when AI should speak. Unfortunately this makes it not a complete deepgram replacement yet!

Re: Voxtral Transcribe 2

#205

Post by mottiden » Thu, Feb 05, 2026, 3:57 AM UTC

krick wrote: post #199

Is there some well established independent benchmark where I can easily (looking at a couple of graphs) compare all popular (especially self-hosted) transcription models?

Not that I am aware of unfortunately

Re: Voxtral Transcribe 2

#206

Post by nostrebored » Thu, Feb 05, 2026, 4:00 AM UTC

Obertr wrote: post #204

Very nice! The thing I am missing is turn detection. In real time audio we need the turn detection to understand when AI should speak. Unfortunately this makes it not a complete deepgram replacement yet!

Is deepgram really performing better than open source turn detection models for you? In our tests it is not.

Re: Voxtral Transcribe 2

#207

Post by CamperBob2 » Thu, Feb 05, 2026, 4:08 AM UTC

GolDDranks wrote: post #176

simonw wrote: post #20

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 At…

I can't get that demo to work. Tried with both Firefox and Chrome.

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.

Re: Voxtral Transcribe 2

#208

Post by bytesandbits » Thu, Feb 05, 2026, 4:17 AM UTC

wow Mistral really cooked

Re: Voxtral Transcribe 2

#209

Post by elboru » Thu, Feb 05, 2026, 4:21 AM UTC

carbocation wrote: post #72

simonw wrote: post #20

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 At…

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

Wow, so it has surpassed humans.

Re: Voxtral Transcribe 2

#210

Post by popalchemist » Thu, Feb 05, 2026, 4:28 AM UTC

janalsncm wrote: post #172

popalchemist wrote: post #78

Earlier quoted context omitted.

It doesn't make sense to have a language-restricted transcription model because of code switching. People aren't machines, we don't stick to our native languages without failure. Even monolingual people move in and out of their native language when using "borrowed" words/phrases. A single-language model will often fail to deal with that.

Everything is a tradeoff, and different use cases require different tradeoffs: Option A: this model Option B: faster model, only 1 language Option C: same size model, only 1 language but higher quality My point is that option A isn’t always best. And on the borrowed words bit, there’s no rule that we cannot add borrowed words into the vocab. But you don’t need the whole language. I know what deja voux means but I don…

that depends entirely on how common the borrowed thing is. And anyway, option A is always going to be insufficient for my code-switching example -- as another commenter pointed out, it is very common to want to refer to a foreign work (song, movie, book) by its foreign language title. Monolingual ASR solutions break over this all the time. Try asking Alexa to play a Spanish language track on Spotify. It fails frequently.

The real world is like that.