Mistral AI · Transcription
Voxtral Small Transcribe 3
Our most accurate transcription model, with state-of-the-art multilingual transcription, diarization and context-biasing in 40+ languages.
- Maker's price
- $0.004 /min
- Max context
- 66K
- Listings
- 4
- Providers
- 4
Evidence and sources
Released 20 Oct 2026Maker HQ: FR (according to Mistral AI's own website)
All rankings:
#375 on OpenRouter today
#439 on OpenRouter this week
#522 on OpenRouter this monthSources: Mistral API data, Models.dev data, LiteLLM data, llminfo researchPrimary data from Mistral API
from Models.dev: name, weights availability
from LiteLLM: variant
from llminfo research: release date
Advantages and trade-offs
Compared with 10 representative transcription models
Advantages
Trade-offs
No open weights
The weights aren't public, so you can't run it yourself.
Input & output
as stated by the model's providersText
Audio
Text
Also known as: mistral/voxtral-small-transcribe-3, mistral/voxtral-small-transcribe-3-0, voxtral-small-transcribe-3-0
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works