Voxtral TTS by Mistral AI
Multilingual TTS model with realistic and expressive speech. Voxtral TTS is Mistral AI's first text-to-speech model with state-of-the-art multilingual text-to-speech with realistic, emotionally expressive voices.
Reactions (1)
Similar products
by description similarity
Mistral Voxtral 3
mistral.aiMistral’s speech models for transcription, TTS and agents
Voxtral
mistral.aiFrontier open source speech understanding models
Voxtral Transcribe 2 by Mistral
mistral.aiReal-time speech-to-text with speaker diarization
VoxCPM2
github.comOpen-source 48kHz TTS with voice design and cloning
Microsoft MAI-Voice-2
microsoft.aiExpressive TTS with voice cloning in 15 languages