As a rule of thumb for software that I use regularly, it is very useful to consider the costs over a 10-year period in order to compare it with software that I purchase for lifetime to install at home. So that means 1,798.80 $ for the Pro version.
Italian represents, I believe, the most phonetically advanced human language. It has the right compromise among information density, understandability, and ability to speech much faster to compensate the redundancy. It's like if it had error correction built-in. Note that it's not just that it has the lower error rate, but is also underrepresented in most datasets.
I have seen the same impressive performance about 7 months ago here: https://kyutai.org/stt
If I look at the architecture of Voxtral 2, it seems to take a page from Kyutai’s delayed stream modeling.
The reason the delay is configurable is that you can delay the stream by a variable number of audio tokens. Each audio token is 80 ms of audio, converted to a spectrogram, fed to a convnet, passed through a transformer audio encoder, and the encoded audio embedding is passed, with a history of 1 audio embedding per 80 ms, into a text transformer, which outputs text embedding, then converted to a text token (which is thus also worth 80ms, but there is a special [STREAMING_PAD] token to skip producing a word).
There is no cross-attention in either Kyutai's STT nor in Voxtral 2, unlike Whisper's encoder-decoder design!
Looks like this model doesn't do realtime diarization, what model should I use if I want that? So far I've only seen paid models do diarization well. I heard about Nvidia NeMo but haven't tried that or even where to try it out.
Parakeet is really good imo too, and it's just 0.6B so it can actually run on edge devices. 4B is massive, I don't see Voxtral running realtime on an Orin or fitting on a Hailo. An Orin Nano probably can't even load it at BF16.
I’m curious about this too. On my M1 Max MacBook I use the Handy app on macOS with Parakeet V3 and I get near instant transcription, accuracy slightly less than slower Whisper models, but that drop is immaterial when talking to CLI coding agents, which is where I find the most use for this.
Pseudo related -- am I the only one uncomfortable using my voice with AI for the concern that once it is in the training model it is forever reproducible? As a non-public person it seems like a risk vector (albeit small),
I noticed that this model is multilingual and understands 14 languages. For many use cases, we probably only need a single language, and the extra 13 are simply adding extra latency. I believe there will be a trend in the coming years of trimming the fat off of these jack of all trades models.
STT services that have been around for longer, like Azure, Google and Amazon, generally require you to request a specific language, and their quality is a lot higher than models that advertise themselves as LLMs (even though I believe the clouds are also using the same types of models now).
It’s a little bit like asking for everything to be included in the Standard Library. Sure, it sounds nice at first, but now you need to maintain tons of dependencies. And any time you want to do one thing, you bring along the baggage of every other thing.
Languages are similar. They also change over time. So now if you want to release a v2 you need an updated corpus for all languages. Or if you get access to an updated corpus for a small language, it might not merit a new model version since it’s only one out of the 14.
honestly the inability to correctly transcribe the 4 language mix i use in my everyday life is one of the major blockers for adopting ASR tech in my own tooling. this coming from someone who literally works in that field.
turns out, outside the US, many people speak more than one language. :)
edit: I should say was a major blocker, because the last iterations of open-weight models actually work better and better. it's often the UX that's not thought for these usecases.
Engineering is about tradeoffs. If the model is being used in an English-only context then tacking on 13 other languages might not be worth the cost.
You are also implicitly choosing worse performance in English by adding extra languages. So you could have a better monolingual model for the same number of weights.
A single language modèle wouldn't make any sense except for English: there's simply too much English intertwined with any other language nowadays (corporate jargon, brands, tech, etc.)
One week ago I was on the hunt for an open source model that can do diatization and I had to literally give up because I could not find any easy to use setup.
I really wish those offering speech-to-text models provided transcription benchmarks specific to particular fields of endeavor. I imagine performance would vary wildly when using jargon peculiar to software development, medicine, physics, and law, as compared to everyday speech. Considering that "enterprise" use is often specialized or sub-specialized, it seems like they're leaving money on Dragon's table by not catering to any of those needs.
In English it is pretty good. But talk to it in Polish, and suddenly it thinks you speak Russian? Ukranian? Belarus? I would understand if an American company launched this, but for a company being so proud about their European roots, I think it should have better support for major European languages.
I tried English + Polish:
> All right, I'm not really sure if transcribing this makes a lot of sense. Maybe not. A цьому nie mówisz po polsku. A цьому nie mówisz po polsku, nie po ukrańsku.
They don't claim to support Polish, but they do support Russian.
> The model is natively multilingual, achieving strong transcription performance in 13 languages, including English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch. With a 4B parameter footprint, it runs efficiently on edge devices, ensuring privacy and security for sensitive deployments.
I wonder how much having languages with the same roots (e.g. the romance languages in the list above or multiple Slavic languages) affects the parameter count and the training set. Do you need more training data to differentiate between multiple similar languages? How would swapping, for example, Hindi (fairly distinct from the other 12 supported languages) for Ukrainian and Polish (both share some roots with Russian) affect the parameter count?
I'm not sure why but their multilingual performance in general has usually been below average. For a French company, their models are not even close to being best in French, even outdone by the likes of Qwen. I don't think they're focusing on anything but English, the rest is just marketing.
polish logically should be rendered in cyrillic as the cyrillic orthography more closely matches the sounds and consonant structure of slavic languages like polish and russian, although this has never been done for church reasons . maybe this is confusing ai
Cracking non-English or accented / mispronounced English is the white whale of text-to-speech I think; I don't know about you, but in our day to day chats there's a lot of jargon, randomly inserted English words, etc. And when they speak in English it's often what I call expat-English which is what you get when non-native speakers only speak the language with other non-native speakers.
Add poor microphone quality (using a laptop to broadcast a presentation to a room audience isn't very good) and you get a perfect storm of untranscribeable presentations or meetings.
All I want from e.g. Teams is a good transcript and, more importantly, a clever summary. Because when you think about it, imagine all the words spoken in a meeting and write them down - that's pages and pages of content that nobody would want to read in full.
88 comments
[ 2.7 ms ] story [ 83.0 ms ] threadhttps://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-26...
~9GB model.
"Click me to try now!" banners that lead to a warning screen that says "Oh, only paying members, whoops!"
So, you don't mean 'try this out', you mean 'buy this product'.
Let's not act like it's a free sampler.
I can't comment on the model : i'm not giving them money.
Is it better? Worse? Why do they only compare to gpt4o mini transcribe?
Amazons transcription service is $0.024 per minute, pretty big difference https://aws.amazon.com/transcribe/pricing/
What estimates do others use?
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?
But I'm definitely going to keep an eye on this for local-only TTS for Home Assistant.
I have seen the same impressive performance about 7 months ago here: https://kyutai.org/stt
If I look at the architecture of Voxtral 2, it seems to take a page from Kyutai’s delayed stream modeling.
The reason the delay is configurable is that you can delay the stream by a variable number of audio tokens. Each audio token is 80 ms of audio, converted to a spectrogram, fed to a convnet, passed through a transformer audio encoder, and the encoded audio embedding is passed, with a history of 1 audio embedding per 80 ms, into a text transformer, which outputs text embedding, then converted to a text token (which is thus also worth 80ms, but there is a special [STREAMING_PAD] token to skip producing a word).
There is no cross-attention in either Kyutai's STT nor in Voxtral 2, unlike Whisper's encoder-decoder design!
https://github.com/cjpais/Handy
https://aclanthology.org/2025.findings-acl.87/
Languages are similar. They also change over time. So now if you want to release a v2 you need an updated corpus for all languages. Or if you get access to an updated corpus for a small language, it might not merit a new model version since it’s only one out of the 14.
For example, "here it is, voila!" "turn left on el camino real"
turns out, outside the US, many people speak more than one language. :)
edit: I should say was a major blocker, because the last iterations of open-weight models actually work better and better. it's often the UX that's not thought for these usecases.
You are also implicitly choosing worse performance in English by adding extra languages. So you could have a better monolingual model for the same number of weights.
If you transcribe a minute of conversation, you'll have like 5 words transcribed wrongly. In an hour podcast, that is 300 wrongly transcribed words.
[^1]: https://www.wired.com/story/mistral-voxtral-real-time-ai-tra...
Real time as in per-word basis? Probably not?
I tried English + Polish:
> All right, I'm not really sure if transcribing this makes a lot of sense. Maybe not. A цьому nie mówisz po polsku. A цьому nie mówisz po polsku, nie po ukrańsku.
> The model is natively multilingual, achieving strong transcription performance in 13 languages, including English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch. With a 4B parameter footprint, it runs efficiently on edge devices, ensuring privacy and security for sensitive deployments.
I wonder how much having languages with the same roots (e.g. the romance languages in the list above or multiple Slavic languages) affects the parameter count and the training set. Do you need more training data to differentiate between multiple similar languages? How would swapping, for example, Hindi (fairly distinct from the other 12 supported languages) for Ukrainian and Polish (both share some roots with Russian) affect the parameter count?
Add poor microphone quality (using a laptop to broadcast a presentation to a room audience isn't very good) and you get a perfect storm of untranscribeable presentations or meetings.
All I want from e.g. Teams is a good transcript and, more importantly, a clever summary. Because when you think about it, imagine all the words spoken in a meeting and write them down - that's pages and pages of content that nobody would want to read in full.
We need better independent comparison to see how it performs against the latest Qwen3-ASR, and so on.
I can no longer take at face value the cherry picked comparisons of the companies showing off their new models.
For now, NVIDIA Parakeet v3 is the best for my use case, and runs very fast on my laptop or my phone.