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?
Barbing 4 minutes ago [-]
Doesn’t seem to work in Safari on iOS 26.2, iPhone 17 Pro, just about anything extra disabled.
skykooler 1 hours ago [-]
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".
starkgoose 45 minutes ago [-]
Try disabling CSP for the page
codethief 1 hours ago [-]
Same here. In Chromium I don't even see the waveform.
fragmede 49 minutes ago [-]
I had to turn off ad-block to get it to work.
tekacs 4 hours ago [-]
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.
Oras 4 hours ago [-]
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.
It can transcribe Eminem's Rap God fast sequence, really, really impressive.
rafram 3 hours ago [-]
That's almost certainly in the training data, to be fair.
keeganpoppen 2 hours ago [-]
what a great test hahah
pyprism 4 hours ago [-]
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.
derefr 3 hours ago [-]
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.
keeganpoppen 2 hours ago [-]
it must have some exposure to bengali— just not enough for them to advertise it. otherwise it would have a damn hard time.
carbocation 3 hours ago [-]
This model was able to transcribe Bad Bunny lyrics over the sound of the background music, played casually from my speakers. Impressive, to me.
sheepscreek 3 hours ago [-]
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!
4 hours ago [-]
rafram 3 hours ago [-]
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.
th0ma5 4 hours ago [-]
[dead]
adarsh2321 4 hours ago [-]
[flagged]
adarsh2321 3 hours ago [-]
[flagged]
iagooar 2 hours ago [-]
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.
lm28469 1 hours ago [-]
> 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.
Try sticking to the supported languages
tdb7893 2 hours ago [-]
Yeah, it's too bad. Apparently it only performs well in certain languages: "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"
ricardonunez 1 hours ago [-]
It did great English and Spanish, it didn't switch to Portuguese, french nor German, maybe struggle with my accent.
scotty79 39 minutes ago [-]
Try to warn it you are going to switch language to Portugese. Worked for me.
yko 2 hours ago [-]
That's a mix of Polish and Ukrainian in the transcript. Now, if I try speaking Ukrainian, I'm getting transcript in Russian every time. That's upsetting.
overfeed 41 minutes ago [-]
Oh no! The model won't translate to an unsupported language, and incorrectly reverts to one that it was explicitly trained on.
The base likely was pretrained on days that included Polish and Ukrainian. You shouldn't be surprised to learn it doesn't perform great on languages it wasn't trained on, or perhaps had the highest share of training data.
scotty79 38 minutes ago [-]
Tell it you are going to speak Polish now. It helps.
mystifyingpoi 2 hours ago [-]
TBH ChatGPT does the same, when I mix Polish and English. Generally getting some cyrillic characters and it gets super confused.
dmix 5 hours ago [-]
> At approximately 4% word error rate on FLEURS and $0.003/min
Is it 0.003 per minute of audio uploaded, or "compute minute"?
For example fal.ai has a Whisper API endpoint priced at "$0.00125 per compute second" which (at 10-25x realtime) is EXTREMELY cheaper than all the competitors.
Oras 4 hours ago [-]
I think the point is having it for real-time; this is for conversations rather than transcribing audio files.
jamilton 3 hours ago [-]
That quote was for the non-realtime model.
yko 2 hours ago [-]
Played with the demo a bit. It's really good at English, and detects language change on the fly. Impressive.
But whatever I tried, it could not recognise my Ukrainian and would default to Russian in absolutely ridiculous transcription. Other STT models recognise Ukrainian consistently, so I assume there is a lot of Russian in training material, and zero Ukrainian. Made me really sad.
breisa 2 hours ago [-]
Thats just the result of the model only supporting russian (and 12 other languages) and not urkainian. It maps to the closest words from training data.
janalsncm 3 hours ago [-]
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).
decide1000 3 hours ago [-]
I think this model proves it's very efficient and accurate.
popalchemist 2 hours ago [-]
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.
javier123454321 2 hours ago [-]
yeah, one example I run into is getting my perplexity phone assistant to play a song in spanish. I cannot for the life of me get a model to translate:
"Play señorita a mi me gusta su style on spotify" correctly
raincole 39 minutes ago [-]
Imagine if ChatGPT started like this and thought they should trim coding abilities from their language model because most people don't code.
keeganpoppen 2 hours ago [-]
uhhh i cast doubt on multi-language support as affecting latency. model size, maybe, but what is the mechanism for making latency worse? i think of model latency as O(log(model size))… but i am open to being wrong / that being a not-good mental model / educated guess.
kergonath 43 minutes ago [-]
Even model size, it’s modest. There is a lot of machinery that is going to be common for all languages. You don’t multiply model size by 2 when you double the number of supported languages.
make3 2 hours ago [-]
model size directly affects latency
pietz 4 hours ago [-]
Do we know if this is better than Nvidia Parakeet V3? That has been my go-to model locally and it's hard to imagine there's something even better.
m1el 2 hours ago [-]
I've been using nemotron ASR with my own ported inference, and happy about it:
I'm so amazed to find out just how close we are to the start trek voice computer.
I used to use Dragon Dictation to draft my first novel, had to learn a 'language' to tell the rudimentary engine how to recognize my speech.
And then I discovered [1] and have been using it for some basic speech recognition, amazed at what a local model can do.
But it can't transcribe any text until I finish recording a file, and then it starts work, so very slow batches in terms of feedback latency cycles.
And now you've posted this cool solution which streams audio chunks to a model in infinite small pieces, amazing, just amazing.
Now if only I can figure out how to contribute to Handy or similar to do that Speech To Text in a streaming mode, STT locally will be a solved problem for me.
The diarization is on Voxtral Mini Transcribe V2, not Voxtral Mini 4B.
sbrother 4 hours ago [-]
Do you have experience with that model for diarization? Does it feel accurate, and what's its realtime factor on a typical GPU? Diarization has been the biggest thorn in my side for a long time..
ashenke 2 hours ago [-]
You can test it yourself for free on https://console.mistral.ai/build/audio/speech-to-text
I tried it on an english-speaking podcast episode, and apart from identying one host as two different speakers (but only once for a few sentences at the start), the rest was flawless from what I could see
coder543 3 hours ago [-]
> Do you have experience with that model
No, I just heard about it this morning.
observationist 4 hours ago [-]
Ahh, yeah, and it's explicitly not working for realtime streams. Good catch!
jiehong 2 hours ago [-]
It’s nice, but the previous version wasn’t actually that great compared to Parakeet for example.
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.
I like Parakeet as well and use it via Handy on Mac. What app are you using on your phone?
jiehong 2 hours ago [-]
Spokenly has it on Mac and iOS, in both cases for free when using parakeet
mdrzn 5 hours ago [-]
There's no comparison to Whisper Large v3 or other Whisper models..
Is it better? Worse? Why do they only compare to gpt4o mini transcribe?
tekacs 5 hours ago [-]
WER is slightly misleading, but Whisper Large v3 WER is classically around 10%, I think, and 12% with Turbo.
The thing that makes it particularly misleading is that models that do transcription to lowercase and then use inverse text normalization to restore structure and grammar end up making a very different class of mistakes than Whisper, which goes directly to final form text including punctuation and quotes and tone.
But nonetheless, they're claiming such a lower error rate than Whisper that it's almost not in the same bucket.
tekacs 5 hours ago [-]
On the topic of things being misleading, GPT-4o transcriber is a very _different_ transcriber to Whisper. I would say not better or worse, despite characterizations such. So it is a little difficult to compare on just the numbers.
There's a reason that quite a lot of good transcribers still use V2, not V3.
satvikpendem 4 hours ago [-]
Different how?
GaggiX 5 hours ago [-]
Gpt4o mini transcribe is better and actually realtime. Whisper is trained to encode the entire audio (or at least 30s chunks) and then decode it.
mdrzn 5 hours ago [-]
So "gpt4o mini transcribe" is not just whisper v3 under the hood? Btw it's $0.006 / minute
For Whisper API online (with v3 large) I've found "$0.00125 per compute second" which is the cheapest absolute I've ever found.
breisa 2 hours ago [-]
Deepinfra offers Whisper V3 at 0.00045$ / minute of transcribed audio.
The linked article claims the average word error rate for Voxtral mini v2 is lower than GPT-4o mini transcribe
GaggiX 5 hours ago [-]
Gpt4o mini transcribe is better than whisper, the context is the parent comment.
fph 2 hours ago [-]
Is there an open source Android keyboard that would support it? Everything I find is based on Whisper, which is from 2022. Ages ago given how fast AI is evolving.
ccleve 34 minutes ago [-]
This looks great, but it's not clear to me how to use it for a practical task. I need to transcribe about 10 years worth of monthly meetings. These are government hearings with a variety of speakers. All the videos are on YouTube. What's the most practical and cost-effective way to get reasonably accurate transcripts?
IanCal 9 minutes ago [-]
If you use something like youtube-dlp you can download the audio from the meetings, and you could try things out in mistrals ai studio.
In the api it took 18s to do a 20m audio file I had lying around where someone is reviewing a product.
There will, I'm sure, be ways of running this locally up and available soon (if they aren't in huggingface right now) but the API is $0.003/min. If it's something like 120 meetings (10 years of monthly ones) then it's roughly $20 if the meetings are 1hr each. Depending on whether they're 1 or 10 hours (or if they're weekly or monthly but 10 parallel sessions or something) then this might be a price you're willing to pay if you get the results back in an afternoon.
edit - their realtime model can be run with vllm, the batch model is not open
isoprophlex 4 minutes ago [-]
- get an API key for this service
- make sure you have a list of all these YouTube meeting URLs somewhere
- ask your preferred coding assistant to write you up a script that downloads the audio for these videos with yt-dlp & calls Mixtrals' API
- ????
- profit
jimmy76615 31 minutes ago [-]
If they are on Youtube, try Gemini 3 Flash first. Use AI studio, it lets you insert YouTube videos into context.
satvikpendem 4 hours ago [-]
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.
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.
cootsnuck 3 hours ago [-]
The error rate for human transcription can be as high as 5%.
XCSme 3 hours ago [-]
Oh wow, I thought humans are like 0.1% error rate, if they are native speakers and aware of the subject being discussed.
zipy124 2 hours ago [-]
I was skepitcal upon hearing the figure but various sources do indeed back it up and [0] is a pretty interesting paper (old but still relevant human transcibers haven't changed in accuracy).
I think it's actually hard to verify how correct a transcription is, at scale. Curious where those error rate numbers come from, because they should test it on people actually doing their job.
serf 5 hours ago [-]
things I hate:
"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.
What's the cheapest device specs that this could realistically run on?
kamranjon 4 hours ago [-]
I haven't quite figured out if the open weights they released on huggingface amount to being able to run the (realtime) model locally - i hope so though! For the larger model with diarization I don't think they open sourced anything.
IanCal 6 minutes ago [-]
The HF page suggests yes, with vllm.
> We've worked hand-in-hand with the vLLM team to have production-grade support for Voxtral Mini 4B Realtime 2602 with vLLM. Special thanks goes out to Joshua Deng, Yu Luo, Chen Zhang, Nick Hill, Nicolò Lucchesi, Roger Wang, and Cyrus Leung for the amazing work and help on building a production-ready audio streaming and realtime system in vLLM.
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.
consumer451 58 minutes ago [-]
Try it out! I read various papers full of jargon at high speed, and it is stunning.
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.
nindalf 3 hours ago [-]
I love seeing people from other countries share their own folk tales about what makes their countries special and unique. I've seen it up close in my country and I always cringed when I heard my fellow countrymen came up with these stories. In my adulthood I'm reassured that it happens everywhere and I find it endearing.
On the information density of languages: it is true that some languages have a more information dense textual representation. But all spoken languages convey about the same information in the same time. Which is not all that surprising, it just means that human brains have an optimal range at which they process information.
Further reading: Coupé, Christophe, et al. "Different Languages, Similar Encoding Efficiency: Comparable Information Rates across the Human Communicative Niche." Science Advances. https://doi.org/10.1126/sciadv.aaw2594
antirez 3 hours ago [-]
Different representations at the same bitrate may have features that make one a lot more resilient to errors. This thing about Italian, you fill find in any benchmark of vastly different AI transcribing models. You can find similar results also on the way LLMs mostly trained on English generalize usually very well with Italian. All this despite Italian accounting for marginal percentage of the training set. How do you explain that? I always cringe when people refute evidence.
testdelacc1 2 hours ago [-]
Where is this evidence you’ve cited for your claims?
Archelaos 4 hours ago [-]
This is largely due to the fact that modern Italian is a systematised language that emerged from a literary movement (whose most prominent representative is Alessandro Manzoni) to establish a uniform language for the Italian people. At the time of Italian unification in 1861, only about 2.5% of the population could speak this language.
gbalduzzi 4 hours ago [-]
The language itself was not invented for the purpose: it was the language spoken in Florence, than adopted by the literary movement and than selected as the national language.
It seems like the best tradeoff between information density and understandability actually comes from the deep latin roots of the language
gbalduzzi 4 hours ago [-]
I was honestly surprised to find it in the first place, because I assumed English to be at first place given the simpler grammar and the huge dataset available.
I agree with your belief, other languages have either lower density (e.g. German) or lower understandability (e.g. English)
riffraff 4 hours ago [-]
English has a ton of homophones, way more sounds that differ slightly (long/short vowels), and major pronunciation differences across major "official" languages (think Australia/US/Canada/UK).
Italian has one official italian (two, if you count IT_ch, but difference is minor), doesn't pay much attention to stress and vowel length, and only has a few "confusable" sounds (gl/l, gn/n, double consonants, stuff you get wrong in primary school). Italian dialects would be a disaster tho :)
NewsaHackO 4 hours ago [-]
The only knowledge I have about how difficult Italian is comes from Inglourious Basterds.
hackyhacky 3 hours ago [-]
> the most phonetically advanced human language
That's interesting. As a linguist, I have to say that Haskell is the most computationally advanced programming language, having the best balance of clear syntax and expressiveness. I am qualified to say this because I once used Haskell to make a web site, and I also tried C++ but I kept on getting errors.
/s obviously.
Tldr: computer scientists feel unjustifiably entitled to make scientific-sounding but meaningless pronouncements on topics outside their field of expertise.
mmooss 3 hours ago [-]
At least some relatively well-known research finds that all languages have similar information density in terms of bits/second (~39 bits/second based on a quick search). Languages do it with different amounts of phonetic sound / syllables / words per bit and per second, but the bps comes out the same.
I don't know how widely accepted that conclusion is, what exceptions there may be, etc.
atentaten 36 minutes ago [-]
Nice. Can this be ran on a mobile device?
Archelaos 5 hours ago [-]
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.
What estimates do others use?
siddbudd 3 hours ago [-]
Wired advertises this as "Ultra-Fast Translation"[^1]. A bit weird coming from a tech magazine. I hope it's just a "typo".
It might be capable of translation; OpenAI Whisper was a transcription model that could do it.
tallesborges92 1 hours ago [-]
I added it to my bot agent,let’s see how it performs
numbers 1 hours ago [-]
does anyone know if there's any desktop tools I can use this transcription model with? e.g. something where like Wisper Flow/WillowVoice but with custom model selection
tietjens 1 hours ago [-]
There is Handy, an open source project meant to be a desktop tool, but I haven’t installed it yet to see how you pick your model.
Impressive results, tested on crappy audio files (in french and english)...
yewenjie 3 hours ago [-]
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.
ashenke 2 hours ago [-]
I don't know if that will change, but right now only the Voxtral Mini Transcribe V2 supports diarization and it's not open-weight.
The Voxtral Realtime model doesn't support diarization, but is open-weight.
vojto11 2 hours ago [-]
WhisperX ?
scotty79 27 minutes ago [-]
Do you know anything better for Polish language, low quality audio than Whisper large-v3 through WhisperX?
This combo has almost unbeatable accuracy and it rejects noises in the background really well. It can even reject people talking in the background.
The only better thing I've seen is Ursa model from Speechmatics. Not open weights unfortunately.
jszymborski 3 hours ago [-]
I'm guessing I won't be able to finetune this until they come out with a HF tranformers model, right?
2 hours ago [-]
derac 3 hours ago [-]
Any chance Voxtral Mini Transcribe 2 will ever be an open model?
ewuhic 3 hours ago [-]
Can it translate in real time?
boringg 4 hours ago [-]
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),
ffsm8 3 hours ago [-]
It's a real issue, but why do you only see it in ai? It's true for any case where you're speaking into a microphone
Depending on the permissions granted to apps on your mobile device, it can even be passively exfiltrated without you ever noticing - and that's ignoring the video clips people take and put online. Like your grandma uploading to Facebook a short moment from a Christmas meet or similar
There have already been successful scams - eg calls from "relatives" (AI) calling family members needing money urgently and convincing them to send the money...
dumpstate 3 hours ago [-]
I'm on voxtral-mini-latest and that's why I started seeing 500s today lol
varispeed 5 hours ago [-]
[flagged]
Empact 5 hours ago [-]
Many people speak Russian, including many who do not live in Russia, e.g. about 30% of Ukranians.
Beyond that, I don't see how we stand to durably reduce military action by making languages mutually unintelligible.
Don't they have a partnership with the French Armed Forces? I am sure they are interested in automating Russian Audio or Text (-> Russian Text) -> French text.
varispeed 3 hours ago [-]
Fair point.
gostsamo 4 hours ago [-]
They've chosen languages which would help them to cover the highest percentage of human population..
2 hours ago [-]
Rendered at 20:50:22 GMT+0000 (Coordinated Universal Time) with Vercel.
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?
And open weight too! So grateful for this.
I tried speaking in 2 languages at once, and it picked it up correctly. Truly impressive for real-time.
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.
Try sticking to the supported languages
The base likely was pretrained on days that included Polish and Ukrainian. You shouldn't be surprised to learn it doesn't perform great on languages it wasn't trained on, or perhaps had the highest share of training data.
Amazons transcription service is $0.024 per minute, pretty big difference https://aws.amazon.com/transcribe/pricing/
For example fal.ai has a Whisper API endpoint priced at "$0.00125 per compute second" which (at 10-25x realtime) is EXTREMELY cheaper than all the competitors.
But whatever I tried, it could not recognise my Ukrainian and would default to Russian in absolutely ridiculous transcription. Other STT models recognise Ukrainian consistently, so I assume there is a lot of Russian in training material, and zero Ukrainian. Made me really sad.
https://aclanthology.org/2025.findings-acl.87/
https://huggingface.co/nvidia/nemotron-speech-streaming-en-0...
https://github.com/m1el/nemotron-asr.cpp https://huggingface.co/m1el/nemotron-speech-streaming-0.6B-g...
I used to use Dragon Dictation to draft my first novel, had to learn a 'language' to tell the rudimentary engine how to recognize my speech.
And then I discovered [1] and have been using it for some basic speech recognition, amazed at what a local model can do.
But it can't transcribe any text until I finish recording a file, and then it starts work, so very slow batches in terms of feedback latency cycles.
And now you've posted this cool solution which streams audio chunks to a model in infinite small pieces, amazing, just amazing.
Now if only I can figure out how to contribute to Handy or similar to do that Speech To Text in a streaming mode, STT locally will be a solved problem for me.
[1] https://github.com/cjpais/Handy
https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-26...
~9GB model.
No, I just heard about it this morning.
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.
Is it better? Worse? Why do they only compare to gpt4o mini transcribe?
The thing that makes it particularly misleading is that models that do transcription to lowercase and then use inverse text normalization to restore structure and grammar end up making a very different class of mistakes than Whisper, which goes directly to final form text including punctuation and quotes and tone.
But nonetheless, they're claiming such a lower error rate than Whisper that it's almost not in the same bucket.
There's a reason that quite a lot of good transcribers still use V2, not V3.
For Whisper API online (with v3 large) I've found "$0.00125 per compute second" which is the cheapest absolute I've ever found.
Why it should be Whisper v3? They even released an open model: https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-26...
You could use their api (they have this snippet):
```curl -X POST "https://api.mistral.ai/v1/audio/transcriptions" \ -H "Authorization: Bearer $MISTRAL_API_KEY" \ -F model="voxtral-mini-latest" \ -F file=@"your-file.m4a" \ -F diarize=true \ -F timestamp_granularities="segment"```
In the api it took 18s to do a 20m audio file I had lying around where someone is reviewing a product.
There will, I'm sure, be ways of running this locally up and available soon (if they aren't in huggingface right now) but the API is $0.003/min. If it's something like 120 meetings (10 years of monthly ones) then it's roughly $20 if the meetings are 1hr each. Depending on whether they're 1 or 10 hours (or if they're weekly or monthly but 10 parallel sessions or something) then this might be a price you're willing to pay if you get the results back in an afternoon.
edit - their realtime model can be run with vllm, the batch model is not open
- make sure you have a list of all these YouTube meeting URLs somewhere
- ask your preferred coding assistant to write you up a script that downloads the audio for these videos with yt-dlp & calls Mixtrals' API
- ????
- profit
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.
[0] https://www.microsoft.com/en-us/research/wp-content/uploads/...
"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.
> We've worked hand-in-hand with the vLLM team to have production-grade support for Voxtral Mini 4B Realtime 2602 with vLLM. Special thanks goes out to Joshua Deng, Yu Luo, Chen Zhang, Nick Hill, Nicolò Lucchesi, Roger Wang, and Cyrus Leung for the amazing work and help on building a production-ready audio streaming and realtime system in vLLM.
https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-26...
https://docs.vllm.ai/en/latest/serving/openai_compatible_ser...
https://huggingface.co/spaces/mistralai/Voxtral-Mini-Realtim...
On the information density of languages: it is true that some languages have a more information dense textual representation. But all spoken languages convey about the same information in the same time. Which is not all that surprising, it just means that human brains have an optimal range at which they process information.
Further reading: Coupé, Christophe, et al. "Different Languages, Similar Encoding Efficiency: Comparable Information Rates across the Human Communicative Niche." Science Advances. https://doi.org/10.1126/sciadv.aaw2594
It seems like the best tradeoff between information density and understandability actually comes from the deep latin roots of the language
I agree with your belief, other languages have either lower density (e.g. German) or lower understandability (e.g. English)
Italian has one official italian (two, if you count IT_ch, but difference is minor), doesn't pay much attention to stress and vowel length, and only has a few "confusable" sounds (gl/l, gn/n, double consonants, stuff you get wrong in primary school). Italian dialects would be a disaster tho :)
That's interesting. As a linguist, I have to say that Haskell is the most computationally advanced programming language, having the best balance of clear syntax and expressiveness. I am qualified to say this because I once used Haskell to make a web site, and I also tried C++ but I kept on getting errors.
/s obviously.
Tldr: computer scientists feel unjustifiably entitled to make scientific-sounding but meaningless pronouncements on topics outside their field of expertise.
I don't know how widely accepted that conclusion is, what exceptions there may be, etc.
What estimates do others use?
[^1]: https://www.wired.com/story/mistral-voxtral-real-time-ai-tra...
Handy – Free open source speech-to-text app https://github.com/cjpais/Handy
This combo has almost unbeatable accuracy and it rejects noises in the background really well. It can even reject people talking in the background.
The only better thing I've seen is Ursa model from Speechmatics. Not open weights unfortunately.
Depending on the permissions granted to apps on your mobile device, it can even be passively exfiltrated without you ever noticing - and that's ignoring the video clips people take and put online. Like your grandma uploading to Facebook a short moment from a Christmas meet or similar
There have already been successful scams - eg calls from "relatives" (AI) calling family members needing money urgently and convincing them to send the money...
Beyond that, I don't see how we stand to durably reduce military action by making languages mutually unintelligible.
https://simple.wikipedia.org/wiki/Russian_language#/media/Fi...