Mistral has released Voxtral TTS, the first frontier-quality open-weight text-to-speech model designed for enterprise use. The 3B-parameter model runs on any laptop or smartphone and achieves a 69.9% listener preference over ElevenLabs in voice customization. It supports nine languages with zero-shot cross-lingual voice adaptation, letting enterprises run voice AI entirely on their own infrastructure. https://venturebeat.com/orchestration/mistral-ai-just-released-a-text-to-speech-model-it-says-beats-elevenlabs-and #AIagent #AI #GenAI