Mistral AI Product
Voxtral TTS
Voxtral TTS is a text-to-speech model from Mistral AI, released in March 2026 and licensed under CC BY-NC 4.0. It supports zero-shot voice cloning and nine languages, and it can stream audio with a time to first audio of about 90 milliseconds. Voice prompts do not need a transcript.
Voxtral TTS is a Mistral AI product filed under Generative AI Software. Lifecycle: versioned, 1 version listed, latest 26.03 (voxtral-tts-2603) (23 Mar 2026).
Source: Voxtral TTS - Mistral AI | Mistral Docs, retrieved 15 Oct 2026
Releases and Lifecycle
All Mistral AI productsRelease and support dates as published by Mistral AI; dates within the next 12 months are highlighted, past dates dimmed. Retrieved 2026-10-14.
Sources 2
- Changelog | Mistral Docs retrieved 2026-10-14
- Models Overview | Mistral Docs retrieved 2026-10-14