Skip to main content
This feature is currently in public preview. This preview is provided without a service-level agreement, and isn’t recommended for production workloads. Certain features might not be supported or might have constrained capabilities. For more information, see Supplemental Terms of Use for Microsoft Azure Previews.
MAI-Voice is a family of text-to-speech models available through Azure Speech in Foundry Tools in public preview. Built on Microsoft’s in-house speech foundation models, MAI-Voice models produce expressive, natural speech output with consistent voice persona quality. Speech offers the following MAI-Voice models:

Model details

MAI‑Voice‑2‑Flash is a text‑to‑speech model built for fast, low‑latency generation. It produces high‑fidelity, natural, and expressive speech across 15 languages and supports gated instant voice cloning, all while being optimized for real‑time responsiveness. Its human‑like intonation, rhythm, and emotional nuance make it ideal for voice agents, assistants, and other interactive scenarios where latency and cost are critical.You can integrate with MAI-Voice-2-Flash using the Azure Speech SDK via SSML, and also via Voice Live.

Key features

Prerequisites

To use MAI related models, complete the following steps:

SSML examples

The examples use the following voices.Basic SSML Example (Harper):
Basic SSML Example (Ethan):
Expressive Control with SSML mstts:express-as

Prebuilt voices

MAI-Voice-2 provides locale-specific prebuilt voices across multiple languages.
The voices listed in the preceding table are the currently published MAI-Voice-2 prebuilt voices. The model card indicates support across 10+ languages. Microsoft adds more locales and voices as they become generally available.
Usage: Available for third-party developers. Microsoft holds full licensing rights for commercial use.

Use MAI-Voice models

MAI-Voice models use the same Azure Speech APIs and SDKs as other Azure neural and HD voices. Use the voice name in the name attribute of the SSML <voice> element. See the prebuilt voice tables in the preceding sections for available names.

Next steps