Voxtral Mini 3B 2507
Mistral AI · mistralai/Voxtral-Mini-3B-2507
Speech to textTranscribes a recording into words
- Type
- Open weightsApache License 2.0
- Languages
- 8
- Size
- 5B
Context measured in tokens
Our take
Written Aug 2, 2026Voxtral Mini is a 5-billion-parameter speech-to-text model from Mistral AI with an Apache licence. It is extremely fast on batch workloads and excellent on clean read-aloud audio, though its accuracy drops sharply in noisy real-world conditions. No hosted offers are currently tracked, so you will need to run it yourself.
Pick this for high-throughput batch transcription of clean audio, where it processes about an hour of audio in 20 seconds on benchmark hardware. Use it if you need an Apache-licensed model you can modify and redistribute, with coverage across eight languages. Skip it if you are transcribing meetings, podcasts, accented speech, or any audio with background noise, where its error rate rises several-fold.
The case for it
- Extremely fast batch transcription: 179.74 times real-time on benchmark hardware.
- Strong on clean controlled audio, with a word error rate of 1.47% on read-aloud against 6.01% overall.
- Permissive Apache 2.0 licence allows commercial use, modification and redistribution.
The case against it
- Accuracy collapses in real-world conditions: 13.56% word error rate in meetings, 9.2 times worse than on clean read-aloud.
- No hosted offers in our data; you must self-host.
- All accuracy figures are English only; no source we hold measures the other seven languages.
How good is it?
TranscriptionTurning speech into text2.5 of 5Open ASR WER · 43rd of 74
94%
Misses roughly one word in 17, averaged over nine English test sets.
180×49th of 62
an hour of audio in 20 seconds, on the board's own hardware. Your machine will differ.
8
Listed on the model card. The accuracy above is English only.
Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case, not to the board.
Which languages ↓ ↑
English · French · German · Spanish · Italian · Portuguese · Dutch · Hindi
The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 18.3 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 26.3 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 1.5 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
When we formed this view
Dates behind this page
Prices last checked 6h ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- mistralai/Voxtral-Mini-3B-2507
- Modality record
- audio->text
- Catalogue slug
- mistralai-voxtral-mini-3b-2507