TechNode1 min read
Ant Group open-sources Ming-3.0 speech models with voice design and audio understanding
Ant Group released its Ming-3.0 speech model family on October 20, making five models available across speech synthesis, audio understanding and conversation, and speech recognition. Developers can use individual models or combine them into voice-based applications.
By TechNode FeedTechNode - China AI

Read the full story
Originally published by TechNode - China AI on Oct 20, 2026.
Comments
Sign in to join the discussion.