MAI-Voice-2

Microsoft · June 2, 2026 · 49 days after MAI-Image-2-Efficient

Verified

1 of 1 published values traced to a source1 primary source, 1 archived1 not researched yet

Why this status

Cited to the lab's own announcement, and every value it asserts was found there. Capabilities evidenced from the primary sources: speech_generation: “com LinkedIn Instagram X Off Accessibility Mode Off Accessibility Mode Copilot --> Models Introducing MAI-Voice-2 Superintelligence team June 2, 2026 Models Superintelligence team ”.

What these states mean · How records are judged · Has this record changed?

Multilingual text-to-speech with voice cloning.

speech generation

Details

Released	June 2, 2026 stated in microsoft.ai MAI-Voice-2 was released on June 2, 2026. Official announcement Primary read July 12, 2026 microsoft.ai archived
Company	Microsoft
Family	MAI-Voice
Lineage	before MAI-Voice-2.1
Era	Agentic systems
Type	Audio
Modalities	Not recorded
Capabilities	Speech generation
Weights	Proprietary
Licence	Not applicable — proprietary

Current information, elsewhere

This record is a historical one: every figure above is traced to a dated primary source. For what is true today — live pricing, current rankings, availability — these are better maintained than anything here could be.

Current price and providers OpenRouter ↗
Current benchmark scores Artificial Analysis ↗

Sources

Record status: verified · confidence 90/100 · 1 of 1 primary

microsoft.ai Official announcement Primary archived

Primary means published by the organisation that made the model. Verified records require at least one.

MAI-Voice family

MAI-Voice-2 June 2, 2026
MAI-Voice-2-Flash July 23, 2026
MAI-Voice-2.1 October 1, 2026
MAI-Voice-2.1-Flash October 1, 2026

Compare MAI-Voice-2 with another model →
See MAI-Voice-2 on the interactive timeline →