We use essential cookies to make our site work. With your consent, we may also use non-essential cookies to improve user experience and analyze website traffic…

🚀 New model available: DeepSeek-V3.1 🚀

mistralai logo

mistralai/

Voxtral-Small-24B-2507

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.

Public
$0.00300 / minute
bf16
ProjectPaperLicense
mistralai/Voxtral-Small-24B-2507 cover image

Input

Please upload an audio file

Settings

task to perform 2

optional text to provide as a prompt for the first window.. (Default: empty)

temperature to use for sampling (Default: 0)

language that the audio is in; uses detected language if None; use two letter language code (ISO 639-1) (e.g. en, de, ja) 101

chunk level, either 'segment' or 'word' 2

Chunk Length S

chunk length in seconds to split audio (Default: 30, 1 ≤ chunk_length_s ≤ 30)

Output

Model Information