Mistral's new AI model can generate your custom voice
French AI company Mistral just launched Voxtral TTS, a new open-source text-to-speech model.
Designed for things like voice assistants and customer support bots, it works in nine languages and lets companies build their own custom voice agents, putting Mistral in the same league as ElevenLabs and OpenAI.
It can adapt a custom voice from a sample
Voxtral can adapt a custom voice from a sample of less than five seconds, even picking up on accents and intonation.
It smoothly switches between languages without changing how the voice sounds, making it great for dubbing or real-time translation.
It's fast too (It has a time-to-first-audio (TTFA) of 90 ms for a 10-second sample of 500 characters) and works on everything from smartwatches to laptops.
As Mistral's vice president, Pierre Stock, puts it: The company built a small-sized speech model that can fit on a smartwatch, a smartphone, a laptop, or other edge devices and costs a fraction of anything else on the market while offering state-of-the-art performance.