MAI-Voice-2
Notable release: A meaningful new model: a new size or version, a strong open model, or a new image, video or audio model from a known lab.
Microsoft's new voice model turns written text into speech in a custom voice, for people building voice products.
Key facts
- Released
- Nov 11, 2026
- What it does
- Makes sound: Creates speech, music or other audio.
Can I use it?
Not yet
In an app
No app mentioned so far.
Not yet
For developers
No developer access mentioned so far.
No
Download
Not downloadable: it runs on the maker's own servers.
Compare MAI-Voice-2 with
It came out 41 days after MAI-Voice-2.1-Flash, the lab's previous model.
The details
Microsoft AI has published a page for MAI-Voice-2, a model that generates custom voices from text. The post text was not available, so launch details are unconfirmed.
Timeline
/Microsoft AIOfficialFirst signal
Get alerts like this the moment they happen.
From Microsoft and every other major lab.
Free, no account needed. Push, Telegram, Discord, email or RSS.