Audio / Speech-to-Text

Voxtral Mini Transcribe 3

Speech-to-text model from Mistral AI

2.2%AA-WER v2 (lower is better)
#7of 64 ranked
65.3×median speed factor
$3.50 / 1k minAPI price

How this is measured

AA-WER v2 (Speech-to-Text)

Word error rate, % of words transcribed incorrectly (lower is better)

Artificial Analysis Word Error Rate index for non-streaming transcription. AA-WER v2 combines three datasets: AA-AgentTalk (50%), VoxPopuli-Cleaned-AA (25%) and Earnings22-Cleaned-AA (25%). Measured independently on dedicated hardware.

Release & sources

Release
Not published

More STT models from Mistral AI