Voxtral Mini Transcribe Realtime 3
Voxtral Mini Transcribe Realtime 3 is Mistral's streaming transcription model, released October 20, 2026 in public preview.
Provider
Mistral AI
Model family
Mistral AI
Speech transcription
Cost tier
Voxtral Mini Transcribe Realtime
Status
Current
Release Oct 20, 2026
Why teams choose it
Complex reasoning
Useful for workflows that require structured thinking, multi-step logic, and deeper analysis than lightweight models provide.
Long-context analysis
Helps teams summarize, compare, and extract insights from long documents without losing important nuance.
Mistral AI roadmap vigilance
Use published model pages—not stale marketing blurbs—for modalities, quotas, pricing, and policy; schedule revalidation tied to vendor release notes.
Cost-efficient routing
Useful as part of a routing stack where cheap models handle drafts and confirmations and this tier handles genuinely hard passages.
Tradeoffs to know
- Public preview.
- The model card leaves context length blank.
Benchmarks
No independent or vendor benchmark scores in this catalog entry.
Technical specs
- Inputs
- audio
- Outputs
- text
- License
- Proprietary API
- Status
- public preview
- Latency Ms
- 80, 2,400
- Input Usd Per Minute
- 0.008
- Capabilities
- Realtime transcription
- Configurable latency from 80 ms to 2,400 ms
- End-of-turn detection and diarization
Sourcehttps://docs.mistral.ai/models/voxtral-mini-transcribe-realtime-3-0
Mistral AI family lineup
Current models
Related models
Voxtral Mini Transcribe Realtime 3 FAQ
What is Voxtral Mini Transcribe Realtime 3?
Voxtral Mini Transcribe Realtime 3 is Mistral's streaming transcription model, released October 20, 2026 in public preview. API names are voxtral-mini-transcribe-realtime-3-0, voxtral-mini-transcribe-realtime-3, and voxtral-mini-transcribe-realtime-latest. It takes audio and returns text over a WebSocket session, with configurable latency from 80 ms to 2,400 ms, end-of-turn detection, context biasing, and speaker diarization. The published price is $0.008 per minute. The model card does not list a context length.
When does Voxtral Mini Transcribe Realtime 3 fit best?
Voice-agent turn detection
What should teams watch out for with Voxtral Mini Transcribe Realtime 3?
The model card leaves context length blank.
Explore next
Models, tools, and comparisons that connect to this reference.