Voxtral is Mistral AI’s open-weight speech-and-text model family. The Voxtral series handles transcription, translation, and audio understanding through a unified speech-LLM stack.
See all models from Mistral AIModels in family
2
Open weight
2
API only
0
Avg score
61.2
Top benchmark
—
Total HF downloads
623.3K
Primary modality
Audio
First release
Jul 2025
Latest release
Jul 2025
Every release in the Voxtral family, ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | audio | BB65.0 | 3B | Jul 2025 | |
| 2 | audio | BB57.4 | 24B | Jul 2025 |
When each release shipped, newest first. Useful for tracking version cadence.
Jul 15
Jul 15
Composite grades across this family. Higher is better, blending benchmarks, popularity, and efficiency.
Models with downloadable weights, ranked by composite score.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | audio | BB65.0 | 3B | Jul 2025 | |
| 2 | audio | BB57.4 | 24B | Jul 2025 |
Spin up an instance in the cloud, or pick local hardware that fits.
Full Directory
Open the full directory to filter by hardware, capability, license, and benchmark score.
Or Browse by Provider
See every model from a lab side by side, with aggregate stats. Useful when you want a cross-family view of one provider.