Home / Models / MAI-Voice-1

MAI-Voice-1

Maker: Microsoft · speech synthesis

Microsoft's first in-house speech generation model: it produces a full minute of audio in under a second on a single accelerator. It powers expressive voice experiences in Copilot Daily, podcasts and Copilot Labs. Available in Microsoft Foundry since 2 Apr 2026, priced from $22 per 1M characters.

Анонс 28.08.2025.

Understands

text

This model cannot see images or video — you can only give it text. That matters if you planned to show it screenshots or documents with pictures.

Produces

speech

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.