MAI Voice 2 Flash
Released on July 23, 2026
Changes from previous version
Same expressive multilingual stack as MAI Voice 2, tuned for real-time turns: 225ms to synthesize 45 seconds of audio, $15 per 1M characters, and production use in Dynamics 365 Contact Center and Azure Voice Live.
Release Summary
Public-preview Flash tier of MAI Voice 2 for low-latency agents, assistants, and call-center speech. Microsoft reports it is 2x faster than Voice 2 and 32% cheaper, at $15 per 1M characters versus $22. Model-inference latency for 45 seconds of audio is 225ms versus 1s on Voice 2. Same 15 languages, 18 locales, gated instant voice cloning, and emotion control. Live on Microsoft Foundry, Azure Speech, Azure Voice Live, MAI Playground, and Dynamics 365 Contact Center.
Timeline
MAI-Voice-2-Flash public preview
Microsoft AI opens MAI-Voice-2-Flash in public preview on Foundry, Azure Speech, Voice Live, and MAI Playground at $15 per 1M characters.
MAI-Voice-2-Flash announced
Microsoft AI teases a Flash tier for MAI-Voice-2 alongside the June 2026 model family launch.