Model dossier

Microsoft AI: MAI-Voice-2.1

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...

ProviderMicrosoft Start comparison

Context0

Max output0

Pricing viewTVP price

Identity

Microsoft AI: MAI-Voice-2.1

Model ID: microsoft/mai-voice-2.1
Canonical slug: microsoft/mai-voice-2.1-20261001
Knowledge cutoff: n/a
Created: 10/1/2026

Capabilities

textspeech

Modalities

text->speechtextspeech

Capacity

Context0

Max output0

TokenizerOther