Voxtral Mini 3B 2507
Mistral's Voxtral Mini 3B 2507 is a speech-to-text model that excels at speech transcription, translation, and audio understanding, leveraging its dedicated transcription mode and long-form context window of 131,072 tokens to handle lengthy audios. With its open-source license, it offers a highly capable and natively multilingual solution, automatically detecting languages and supporting state-of-the-art performance in widely used languages.
Input
Output
Context
131K
Max Output
33K
Parameters
4.7B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Estimated GPU Requirements for Voxtral Mini 3B 2507
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Mistral
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jul 17, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.