Mistral
Voxtral Small 24B 2507
Open audio-language model for speech transcription, audio understanding, and voice-driven tool use
mistral/voxtral-small-24b-2507
Context
32.8K
Output
32.8K
Released
2025-07-15
Knowledge cutoff
—
Types
InputTextAudio
OutputText
Reasoning
—
Tool use
Supported
Structured output
—
Attachments
Supported
Open weights
Supported
Provider pricing
No providers currently list this model.
From the same lab
Mistral Large 4
mistral/mistral-large-4
Mistral Medium 3.5
mistral/mistral-medium-3-5
Mistral Medium 3.5
mistral/mistral-medium-2604
Mistral Medium (latest)
mistral/mistral-medium-latest
Mistral Small 4
mistral/mistral-small-2603
Mistral Small (latest)
mistral/mistral-small-latest
Devstral 2
mistral/devstral-2512
Devstral Small 2
mistral/devstral-small-2