Voxtral Mini Transcribe 3
voxtral-mini-transcribe-3-0Transcribe recorded speech with automatic language detection, segment timestamps, and optional speaker diarization. Accepts recordings up to 10 minutes, with direct uploads up to 4 MB or audio URLs up to 25 MB. Returns a completed transcript; word timestamps and translation are unavailable.
- Speech to text
Pricing
Includes our margin. Charged per request from your balance.
- Per minute
- $0.0042
Details
- Provider
- Mistral
- Added
- Nov 5, 2026
Options
Parameters this model accepts.
- Features
- Automatic language detection, Segment timestamps, Speaker diarization, Recordings up to 10 minutes
- Response formats
- json
- text
- verbose_json
- Input formats
- MP3, WAV, FLAC, OGG, M4A, AAC
- Max file size
- 25 MB
- Max upload in the request
- 4 MB
- File URLs
- Supported
- Timestamps
- segment