Model Releases

Xiaomi Releases MiMo-V2.5-TTS Series and ASR, Covering Speech Synthesis and Recognition

Original title:MiMo-V2.5-TTS-Series + ASR 正式发布

AI summary

Xiaomi officially released the MiMo-V2.5-TTS Series and MiMo-V2.5-ASR, covering both speech recognition and synthesis. The TTS series includes three models supporting style instruction following and audio tag control, among which VoiceDesign can generate new voices with zero reference audio, and VoiceClone can replicate a voice with just a few seconds of reference audio; ASR reaches industry-leading levels in Chinese-English bilingual, Chinese dialect, and strong-noise scenarios.

Key Takeaways

  • Xiaomi officially released the MiMo-V2.
  • 5-TTS Series and MiMo-V2.
  • 5-ASR,covering both speech recognition and synthesis.
  • The TTS series includes three models supporting style instruction following and audio tag…
  • ASR reaches industry-leading levels in Chinese-English bilingual,Chinese dialect,and strong-noise…

Quick Facts

Published
Updated
Source
公众号:小米 MiMo
Category
Model Releases
AI score
83
Read the original Read the full article at the original source
Why it matters

把角色演出指令从参数模板简化为导演笔记式的自然语言,对有声剧和游戏NPC等依赖声音塑造的场景,定制成本与表现自由度可能同时改善。

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: Xiaomi Releases MiMo-V2.5-TTS Series and ASR, Covering Speech Synthesis and Recognition. April 24, 2026. https://new.nat6.net/en/news/cmsdu2j0400yorofzawxe8dom/

View all →