Model
Voxtral Small Transcribe 3
A speech transcription model in the Mistral Voxtral 3 family, whose word error rate places it among the leading tier in standardized evaluation by Artificial Analysis.
Timeline (last 90 days)
Oct 21
Voxtral Small Transcribe 3 has an AA-WER of 2.1%.
Unverified50%
Oct 21
In Artificial Analysis's evaluation, Voxtral Small Transcribe 3 ranked third.
Unverified50%