Voxtral Small Transcribe 3
Voxtral Small Transcribe 3 is Mistral's flagship transcription and diarization model, released October 20, 2026 in public preview.
Provider
Mistral AI
Model family
Mistral AI
Speech transcription
Cost tier
Voxtral Small Transcribe
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 changelog describes the launch as offline transcription and diarization. The model card lists the extra speech tasks.
Benchmarks
No independent or vendor benchmark scores in this catalog entry.
Technical specs
- Inputs
- audio
- Outputs
- text
- License
- Proprietary API
- Status
- public preview
- Context tokens
- 32,000
- Input Usd Per Minute
- 0.004
- Capabilities
- Transcription and diarization with timestamps
- Translation, speech Q&A, summarization, and function calling on the model card
- 32k context
Sourcehttps://docs.mistral.ai/models/voxtral-small-transcribe-3-0
Mistral AI family lineup
Current models
Related models
Voxtral Small Transcribe 3 FAQ
What is Voxtral Small Transcribe 3?
Voxtral Small Transcribe 3 is Mistral's flagship transcription and diarization model, released October 20, 2026 in public preview. API names are voxtral-small-transcribe-3-0, voxtral-small-transcribe-3, and voxtral-small-transcribe-latest. It takes audio and returns text, with a 32k context window and timestamps. The model card also lists translation, speech question answering, summarization, and function calling. The published price is $0.004 per minute. Mistral says it leads Microsoft AI Transcribe 2, Whisper large-v3, GPT-Transcribe, Scribe v2, and Gemini 3.5 Transcribe on transcription. The changelog describes the release as offline transcription and diarization.
When does Voxtral Small Transcribe 3 fit best?
High-accuracy transcription
What should teams watch out for with Voxtral Small Transcribe 3?
The changelog describes the launch as offline transcription and diarization. The model card lists the extra speech tasks.
Explore next
Models, tools, and comparisons that connect to this reference.