Audio modelPreview

MAI-Voice-2-Flash

Microsoft

Released: July 23, 2026
Data date: October 3, 2026

Model class: Low-latency speech synthesis
Access: Microsoft Foundry API

MAI-Voice-2-Flash is the faster and less expensive speech synthesis variant of MAI-Voice-2. Microsoft describes roughly twice the speed and a price of $15 per 1M characters in the Flash announcement.

The model identifier is mai-voice-2-flash, with Foundry access in preview. Voice 2 Flash is the earlier published Flash variant, separate from the later MAI-Voice-2.1-Flash generation.

Specifications and access

Specification	Value and source
Model class	Low-latency speech synthesisSource
Access	Microsoft Foundry APISource
Input	Text and reference audioSource
Output	AudioSource
API model ID	mai-voice-2-flashSource
Speed	About twice as fast as MAI-Voice-2Source
Voice cloning	Reference audio with consent guardrailsSource

Sources and data date

Every statement links to its underlying documentation or leaderboard.

Type	Evidence and data date
Research status	Research date October 4, 2026. 2 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	quality-benchmarks Original wording Voice-2 preference results and Voice-2.1-Flash latency cannot be transferred to this exact earlier Flash checkpoint.
Additional source	Microsoft MAI Voice 2 Flash announcement (retrieved October 3, 2026; October 4, 2026) · Microsoft MAI Voice 2 Flash announcement · Editorial description reviewed October 3, 2026
Additional source	Microsoft MAI Voice 2 announcement (retrieved October 3, 2026; October 4, 2026) · Microsoft MAI Voice 2 announcement · Editorial description reviewed October 3, 2026

Specifications and access

Published prices

Sources and data date