← All models
Voxtral Small 24B 2507
voxtral
Open audio-language model for speech transcription, audio understanding, and voice-driven tool use
- Family
- voxtral
- Providers
- 4
- Context
- 32,768
- Output
- 32,768
- Knowledge
- -
- Weights
- Open
- Input
- textaudio
- Output
- text
- Release date
- 2025-07-15
- Updated
- 2025-07-15
Providers
Source: models.dev