Mistral AI
Mistral: Voxtral Mini Transcribe
mistralai/voxtral-mini-transcribe
Voxtral Mini Transcribe is Mistral's speech-to-text model, derived from the Voxtral Mini family. It accepts audio input and returns transcribed text via the standard transcription API. Suited for transcribing meetings, voice notes, podcasts, and other spoken content.
Input
$50
/ 1M tokens · Token reference
Output
$0
/ 1M tokens · Token reference
Context window
16.38K
tokens
Transcription output · Token reference fields do not establish an output-unit price.
Limits
Context
16,384
tokens
Max output
13,107
80% of the context window
Model facts
Author
Mistral AI
Tokenizer
Mistral
Modality
Audio -> Transcription
Created
May 15, 2026
Publication status
Hugging Face: not mappedLicense: not publishedParameter count: not published
Modalities
Input · AudioOutput · Transcription