Microsoft AI: MAI-Voice-2.1
microsoft/mai-voice-2.1- Modalities
- text->speech
- In / out price
- $22 / $0
- Context
- —
- Released
- Oct 1, 2026
- Knowledge cutoff
- —
per 1M
The playground sends chat/completions only. This model outputs Speech, so a chat turn may not return what you expect.
MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-speech model. It produces natural, studio-grade speech across 23 languages, with detailed prosody, nuanced expressiveness, and speaker consistency over long-form content. It is...
AudioSpeech
Supported parameters
This model does not publish a parameter list.