Rocket - Think it. Type it. Launch it.
Mini toolsVoxtral TTS
By Mistral AI
Voxtral TTS is Mistral’s open-source speech generation model aimed at voice assistants, customer support, sales, dubbing, and multilingual voice agents. TechCrunch reports it supports English, French, German, Spanish, Dutch, Portuguese, Italian, Hindi, and Arabic, and is based on Ministral 3B. Mistral says it can adapt a custom voice from a sample shorter than 5 seconds while retaining accent, intonation, and speech irregularities, and can switch languages without losing voice identity. It is positioned for real-time performance, with reported 90 ms time-to-first-audio for a 500-character sample and a 6x real-time factor.
New
Audio
Gen 3
Overview
Voxtral TTS is Mistral’s new open-source text-to-speech model for building voice agents and enterprise speech applications. According to TechCrunch, it supports 9 languages, can clone a voice from under 5 seconds of audio, preserves accents and speaking style, and is optimized for real-time use on edge devices like phones, laptops, and wearables.
About Mistral AI
Mistral AI is a company that specializes in artificial intelligence and machine learning solutions.
View Company ProfileTools using Voxtral TTS
No tools found for this model yet.
Last updated: March 26, 2026
