Model Releases

Microsoft Releases MAI-Voice-2 Speech Synthesis Model with 15 Languages and Zero-Shot Voice Cloning

Original title:Introducing MAI-Voice-2

AI summary

Microsoft released the text-to-speech model MAI-Voice-2, which it says significantly improves on its predecessor in fidelity, language coverage, speaker consistency, and emotional range, and outperforms MAI-Voice-1 in 72% of scenarios in side-by-side preference tests.

Key Takeaways

  • Microsoft released the text-to-speech model MAI-Voice-2,which it says significantly improves on…
  • language coverage
  • speaker consistency,and emotional range,and outperforms MAI-Voice-1 in 72% of scenarios in…

Quick Facts

Published
Updated
Source
Microsoft AI:官方博客(RSS)
Category
Model Releases
AI score
61
Read the original Read the full article at the original source
Why it matters

原文给出语言扩展、情感控制、零样本克隆与偏好测试数据,读者可以据此评估它在语音产品里的实际可用性。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Microsoft Releases MAI-Voice-2 Speech Synthesis Model with 15 Languages and Zero-Shot Voice Cloning. June 3, 2026. https://new.nat6.net/en/news/cms3g8wjy01i3rondiwooj3q9/

View all →