Tag

#TTS

3 articles

Closing the ‘Expressivity Gap’: How Mistral’s Voxtral TTS is Redefining Multilingual Voice Cloning with a Hybrid Autoregressive and Flow-Matching Architecture

Mistral AI's new TTS model, Voxtral, tackles the 'expressivity gap' in voice AI by combining autoregressive and flow-matching techniques for more emotionally expressive, multilingual speech synthesis.

May 510

Google AI Launches Gemini 3.1 Flash TTS: A New Benchmark in Expressive and Controllable AI Voice

Google introduces Gemini 3.1 Flash TTS, a new text-to-speech model that enhances speech quality, expressive control, and multilingual generation. This release marks a shift toward more controllable and natural AI voice outputs.

Apr 1580

Mistral's first open-weight TTS model Voxtral clones voices from three seconds of audio across nine languages

French AI startup Mistral has released Voxtral, its first open-weight text-to-speech model that supports nine languages and can clone voices from just three seconds of audio.

Mar 2648