Model dossier

Microsoft: MAI-Voice-2

MAI-Voice-2 is an expressive text-to-speech model from Microsoft. It is suited for conversational assistants, media narration, accessibility, education, and other long-form voice applications. It supports 15 languages across 18 locales,...

ProviderMicrosoft Start comparison

Context0

Max outputn/a

Pricing viewTVP price

Identity

Microsoft: MAI-Voice-2

Model ID: microsoft/mai-voice-2
Canonical slug: microsoft/mai-voice-2
Knowledge cutoff: n/a
Created: 6/2/2026

Capabilities

textspeech

Modalities

text->speechtextspeech

Capacity

Context0

Max outputn/a

TokenizerOther