AI Model

MAI Voice 2

Released on June 2, 2026

Changes from previous version

Expands from English-only MAI-Voice-1 to 15 languages with multilingual voice cloning at the same per-character price.

Release Summary

Multilingual text-to-speech with 15 languages, instant voice matching from short reference clips, expressive emotion control, and stable long-form output for audiobooks, podcasts, and lectures. Built-in guardrails require authorized, consented voices. Priced at $0.22 per 1M characters via MAI Playground and Azure Speech.

Timeline

June 2, 2026

MAI-Voice-2 announced

Microsoft AI launches expressive low-latency speech generation with multilingual voice adaptation.