AITechNodeabout 2 hours ago
Ant Group Releases Ming-3.0 Speech Models
1 min read
On October 20, Ant Group released the Ming-3.0 speech model family, making five models available for speech synthesis, audio understanding, conversation, and speech recognition. The suite supports voice cloning from reference recordings and voice design through natural-language descriptions, allowing users to specify emotion, emphasis, and pacing for direct delivery.
Level
Hype check
Tap to vote and see what everyone thinks.
