FoundrList

About
Voxtral TTS, powered by Mistral AI's open-source 4B parameter model, offers studio-quality speech generation with zero-shot voice cloning from just 2–3 seconds of audio. It supports 9 languages including English, French, German, Spanish, Dutch, Portuguese, Italian, Hindi, and Arabic, allowing for cross-lingual voice cloning and code-mixing. Users can type or paste text, choose or clone a voice, and generate and download audio without complicated setups or vendor lock-in. Voxtral TTS is available for free online with no signup required, and it is released under a CC BY NC 4.0 license, enabling users to inspect weights and self-host on their own infrastructure.
Community Support
No voters yet
No comments yet. Be the first to comment!