Voxtral

Mistral's audio model, feeding speech straight into a multimodal model for transcription and spoken question answering across languages.

Vendor: Mistral
Modality: audiotext
Tools using this model: 1

Aliases and versions

Voxtral

Used by these tools

MistralEuropean open models and Le Chat assistant

Where it is used in this directory

Everything below is derived from tools already listed in this directory: 1 tools note Voxtral, covering the media types, platforms, and output formats on this page. Check each tool's official documentation for capabilities and integration details.

Media types covered: ✍️ Text Generation
Platforms of the tools that use it: WebAPI
Output formats of the tools that use it: TXTPDFCSV

Related models

Other models from the same vendor or modality.

Mistral Large 3Mistral Mistral LargeMistral Mistral SmallMistral CodestralMistral

FAQ

What is Voxtral?

Mistral's audio model, feeding speech straight into a multimodal model for transcription and spoken question answering across languages.

Who develops Voxtral?

Voxtral is developed by Mistral. Versions and capabilities may change with official updates; check the vendor documentation for current details.

Which tools use Voxtral?

Tools in this directory that use Voxtral include Mistral. See each tool's official docs for integration details.