Back to models
Voxtral Mini

Voxtral is Mistral’s audio model family designed for powerful speech understanding

Model ID

mistral.voxtral-mini

Use this ID when making API calls to reference this model

Provider

Mistral

Accuracy Tier

premium

Release Date

July 15, 2025

Supported Languages

enfrdeesitptnlhi
Automatic Language Detection: Yes
Performance & Cost

Cost

$0.06000/hour

$0.00002/second

Features

Supported capabilities and functionalities

Core Features

Punctuation
Diarization
Streaming
Speaker Labels
Word Timestamps
Confidence Scores
Custom Vocabulary
Profanity Filtering
Noise Reduction
Voice Activity Detection

Subtitle Formats

SRT Support
VTT Support
Technical Specifications

Input/output formats and technical details

Subtitle Format Support

No subtitle formats supported