Skip to content
AI IntelligenceMar 26, 2026AI Intelligence
Article

Mistral AI releases its first open-weight text-to-speech model 'Voxtral'.

It can clone voices from just three seconds of audio across nine languages, setting a new standard for accessible and powerful speech synthesis.

Data Cube AI EditorialSource: The Decoder
01

Source Brief

Mistral AI releases its first open-weight text-to-speech model 'Voxtral'. It can clone voices from just three seconds of audio across nine languages, setting a new standard for accessible and powerful speech synthesis.

02