speech recognition
Voxtral Mini 3B 2507
Ministral 3B with audio input, for speech transcription, translation and audio understanding.
Levelmodel
Classspeech recognition
Parameters4.68B
Contextnot in the notes
Released1 Jul 2025
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Identity
- Developer
- Mistral AI
- Family
- not in the notes
- Released
- 1 Jul 2025 sourcesregistry date
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- dense transformer
- Total parameters
- 4.68B sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- Built on Ministral 3B; 4.68B in the Hugging Face safetensors count.
- Context length
- not in the notes
- Input
- audio, text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- Apache License 2.0 sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperMistral AIstartup, France
Mistral AIstartup, FranceModelVoxtral Mini 3B 2507Mistral AI, speech recognition
Voxtral Mini 3B 2507Mistral AI, speech recognitionUse Casesnone recorded
Who Runs Itnone recorded
Organisations 1
Sources
- huggingface.co/mistralai/Voxtral-Mini-3B-2507 https://huggingface.co/mistralai/Voxtral-Mini-3B-2507
- mistral.ai/news/voxtral https://mistral.ai/news/voxtral
- arxiv.org/abs/2507.13264 https://arxiv.org/abs/2507.13264
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Voxtral Mini 3B 2507", https://aurion.semai.id/models/mistral-ai-voxtral-mini-3b-2507/, records of October 2026.