speech recognition
Voxtral Mini 4B Realtime 2602
Multilingual real-time transcription model with under 500 ms delay, for voice assistants and live subtitles.
Levelmodel
Classspeech recognition
Parameters4.43B
Contextnot in the notes
Released21 Jan 2026
Opennessopen weights permissive
Runs onlaptop
Statusactive
R&D Topics
Identity
- Developer
- Mistral AI
- Family
- not in the notes
- Released
- 21 Jan 2026 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
- 4.43B sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- audio
- 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
- laptop
- Footprint
- Card says it is optimised for on-device deployment.
- 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
- 13 languages
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 4B Realtime 2602Mistral AI, speech recognition
Voxtral Mini 4B Realtime 2602Mistral AI, speech recognitionR&D TopicsStreaming and Low-Latency Speech RecognitionReal-Time Spoken Dialogue and Low-Latency Voice Generation
Use Casesnone recorded
Who Runs Itnone recorded
Organisations 1
R&D topics 2
Real-Time Spoken Dialogue and Low-Latency Voice GenerationModels that listen and speak with delays of a few hundred milliseconds, including full-du…produced byStreaming and Low-Latency Speech RecognitionSpeech recognition built to transcribe live audio with small delay and small compute, for…exemplar
Sources
- huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602 https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Voxtral Mini 4B Realtime 2602", https://aurion.semai.id/models/mistral-ai-voxtral-mini-4b-realtime-2602/, records of October 2026.