Using MAI-Voice-2.1-Flash on Microsoft Foundry

Implementation guide · MAI · Microsoft AI

Serverless

Microsoft Foundry exposes MAI-Voice-2.1-Flash through model ID MAI-Voice-2.1-Flash. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-06. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Microsoft Foundry and generate an API key.
  2. 2
    Use the Microsoft Foundry SDK or REST API to call MAI-Voice-2.1-Flash — see the documentation for request format.
API PortalDocumentationPricingModel Card

Code Examples

See Microsoft Foundry documentation for integration details.

Pricing on Microsoft Foundry

Capabilities

Audio

About MAI-Voice-2.1-Flash

MAI-Voice-2.1-Flash is Microsoft AI's low-latency text-to-speech model for high-volume voice agents, launched 1 October 2026 alongside MAI-Voice-2.1. It covers the same 23 languages and cross-language voices with about 150 ms end-to-end latency and supports voice cloning. Priced at $15 per 1M characters.

Full model details →

Model Specs

Released2026-10-01
ArchitectureAudio / Speech

More Models on Microsoft Foundry

MAI-Transcribe-1MAI-Voice-1MAI-Image-2MAI-Image-2eMAI-Thinking-1MAI-Code-1
All models on Microsoft Foundry →

Also available on(1)

Vercel AI Gateway
Compare all providers →

Provider

Microsoft Foundry

Microsoft

Redmond, Washington, United States