Primary use stated or inferred cautiously from official documentation.
M
MISTRAL / voxtral-small-transcribe-3-0
Voxtral Small Transcribe 3
Mistral transcriber presented on October 20, 2026, in public preview. It accepts audio files and returns text, with diarization and contextual bias for specialized vocabulary. The language guide declares 50 languages for offline transcription. Small and Mini are different variants with their own rates; this profile uses the versioned identifier voxtral-small-transcribe-3-0, not a moving alias.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | voxtral-small-transcribe-3-0 |
|---|---|
| Model type | Voice and audio |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 20 OCT 2026 |
| Knowledge cutoff | Not published |
| Entrance | Audio |
| Exit | Text |
| Context window | Check limits by modality |
| maximum output | Transcribed text |
| Reasoning | Not published |
| Published tools | |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | Mistral API |
Multilingual transcription with speaker identification and domain vocabulary via context_bias. Offline and real-time versions are distinct models, not interchangeable modes of the same identifier. Preserve the exact model name and check project access during the preview. Commercial availability does not imply open weights nor rights over third-party recordings.
Offline model cards indicate 32k context, while the audio limits guide documents 65,536 shared tokens: we do not present either as a universal guarantee. Validate the limit of the contracted endpoint. Available timestamps are segment-level, not word-level. At launch, general chat about audio still uses Voxtral 2; we do not attribute that API to these transcribers. Review consent, privacy, and errors in proper names.
03 / CAPABILITIES
What it can do
Orientation
Multilingual transcription with speaker identification and domain vocabulary via context_bias. Offline and real-time versions are distinct models, not interchangeable modes of the same identifier. Preserve the exact model name and check project access during the preview. Commercial availability does not imply open weights nor rights over third-party recordings.
Context
Check limits by modality · Transcribed text
Tools and integration
Not published
Access
Mistral API
Input modalities
Audio
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 0.004 USD / min | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Included in the audio rate | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Public rates in dollars per minute of audio or per million characters, depending on the variant; they are not token prices. Numerical fields per million tokens are left blank to avoid false comparisons. Confirm billing conditions and availability before integrating. Private enterprise deployment requires a specific agreement; no downloadable weights have been published for these variants.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
Mistral evaluates transcription on an intersection of 45 FLEURS languages, with WER or CER depending on the script, and separates forced language from inferred language. For diarization, it publishes cpWER on several corpora. We do not transfer Small's results to Mini nor convert unverified graphs into scores. Evaluate accents, noise, and speaker changes with authorized recordings.
i Provider evaluation; numerical scores not verified by Inferama.
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Voxtral Small Transcribe 3
Version added to Inferama's verified catalog.
ANALYSIS
Related analysis
07 / SOURCES