AI Model
MAI Voice
Text-to-speech models for expressive, low-latency speech with multilingual voice matching and long-form stability.
Latest version:2 FlashAnnounced
Every shipped version of this model. Click a marker to open its release page.
Hollow markers open release pages. Scroll horizontally for older releases; labels stay fixed on the left.
Text-to-speech models for expressive, low-latency speech with multilingual voice matching and long-form stability.