Mistral Voxtral

“the voice samples on the page are much better than the one in the video”

“Translation is atrocious, and sometimes incorrect, in the part where they showcase their 35-language pronunciations”

“First of all, this is great for sovereignty. Sad that the model is not open.”

“the german is also hilariously bad if it's supposed to sound native”

“sounds so much more artificial and AI as compared to the old Voxtral 1”

“These models are filling some gaps we see for the kinds of things we tend to work on.”

“Good transcription and diarization which is the primary personal use-case”

“Closed model unfortunately, continues the theme of TTS / STT being really not great for local deployments.”

“In my tests with other languages Voxtral was better then Whisper.”

“something like Voxtral (real-time and transcribe) is neat, and efficient.”

“Seems to understand/infer all the technobabble I use at work.”

“I've found Voxtral to be the best combination of price/speed/accuracy.”

“I think in this category, Voxtral by Mistral is a lot better. It also happens to be small enough to run on webGPU”

“especially liked their voice Model voxtral, which is supposed to be better than whisper”

“They are making some very good specialised models, like Voxtral”

“has timestamps and diarization and does a good job for German”

“the UX difference between streaming and offline STT is night and day”

“you see text appearing while you're still mid-sentence”

“I have to wait 10 minutes at a time for the 2+ hour long transcriptions I've uploaded to Voxstral to process”

“their new model is good and half the price if you can live without streaming”

“I personally switched to it as my main default fast model - it's really good.”

“This exciting, especially after 11 labs very expensive model”

“The language support is a little lacking for my use cases”

“It performs well on Mandarin audio transcription, considering it's an European company.”

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

“the graph suggests that it's not going to perform as good as openai model I have been using”

“their multilingual performance in general has usually been below average”

“If I speak clearly it seems to work very well even with background noise.”

“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.”

“In the api it took 18s to do a 20m audio file I had lying around where someone is reviewing a product.”

“I read various papers full of jargon at high speed, and it is stunning.”

“It did great English and Spanish, it didn't switch to Portuguese, french nor German”

“if I try speaking Ukrainian, I'm getting transcript in Russian every time. That's upsetting.”

“it could not recognise my Ukrainian and would default to Russian in absolutely ridiculous transcription”

“It's nice, but the previous version wasn't actually that great compared to Parakeet”

“But talk to it in Polish, and suddenly it thinks you speak Russian?”

“This model was able to transcribe Bad Bunny lyrics over the sound of the background music”

“It missed or mixed up a lot of words when I was speaking quickly”

“It can transcribe Eminem's Rap God fast sequence, really, really impressive.”

“I spoke fast and dropped in some jargon and it got it all right”