MAI-Voice-2

Closed Active Audio gen

Multilingual MAI text-to-speech model with zero-shot voice prompting in 15+ languages.

Released
Jun 2, 2026
Context window
Not disclosed
Max output
Not disclosed
Parameters
Not disclosed
Input price
Not disclosed
Output price
Not disclosed

Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.

Pricing

Launch priceJun 2, 2026
Current price since Jun 2, 2026

Specifications

Developer
Microsoft
Model type
Audio gen
Architecture
Not disclosed
Parameters
Not disclosed
Input
Text
Output
Audio
Knowledge cutoff
Not disclosed
License
Proprietary
API access
First-party API