Voxtral Small 24B 2507
Mistral AI · released Jul 1, 2025 · mistralai/Voxtral-Small-24B-2507
- Type
- Open weightsApache License 2.0
- Params
- 24.3B
- Context
- 32K
about 24K words of context
Our take
Written Sep 2, 2026Voxtral Small is a 24.3-billion-parameter speech-to-text model from Mistral AI with a permissive Apache licence. It turns audio, text and files into written output, and scores well on clean recordings and professional financial calls.
Pick this for clean read-aloud or earnings-call transcription where accuracy matters, or for multimodal pipelines needing text, file and audio inputs together. Use it when you need a permissive licence for commercial redistribution or fine-tuning. Skip it if you are transcribing meetings, podcasts or heavily accented international speech, where its error rate rises sharply.
The case for it
- 1.23% word error rate on clean read-aloud audio, among the most accurate we list.
- 1.84% on financial earnings calls and 2% on European-accented parliamentary speech.
- 100× real-time factor on the benchmark rig — an hour of audio in 36 seconds.
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
The case against it
- Meeting audio degrades badly: 13.18% word error rate, more than ten times its clean-speech rate.
- Heavily accented international speech at 10.16% word error rate, worse than most models on this condition.
- Podcast and internet audio at 8.33% word error rate, middling against peers.
How good is it?
TranscriptionTurning speech into text3.5 of 5Open ASR WER · 32nd of 76
95%
Misses roughly one word in 20, averaged over nine English test sets.
101×71st of 74
an hour of audio in 36 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; the placing beneath each rate is against every model measured on that set.
Which languages ↓ ↑
English · French · German · Spanish · Italian · Portuguese · Dutch · Hindi
EverydayGeneral questions and everyday reasoning
Not yet scored on Arena Text (overall).
CodingWriting and fixing code on its own
Not yet scored on Arena Coding.
AgenticPlanning, calling tools, staying on task
Not yet scored on Arena Agent.
WritingDrafting and rewriting prose
Not yet scored on Arena Creative Writing.
Each of these is the same transcription job on a different kind of recording, so together they say where it holds up and where it slips — not how closely it follows an instruction.
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?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 5.5 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 13.5 GB spare means a 10% error in the size would not change the answer.
Apple M2 (10-core GPU) · 24 GB
Borderline fit on an estimated size. It leaves 0.7 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.10 in / $0.30 out
- Context served
- 33K
- Throughput
- ~52 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.10 / $0.30checked 4 hours ago | 33K | not measured | Unknown | Unknown | Unknown |
| Mistral AIThrough OpenRouter | $0.10 / $0.30checked 4 hours ago | 33K26K max reply | 52 tok/s | No | Yes30 days | Confirmed |
| Mistral AIeuThrough OpenRouter | $0.11 / $0.33checked 4 hours ago | 32K26K max reply | 33 tok/s | No | Yes30 days | Confirmed |
OpenRouterAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Mistral AIThrough OpenRouter | ✓ | ✓ | ✓ |
| Mistral AIeuThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
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.
- 1 of 3 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
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-Small-24B-2507
- Architecture
- Dense
- Takes in, gives back
- Text, audio and documents in, text out
- Catalogue slug
- mistralai-voxtral-small-24b-2507