AI Summary20 Oct 202610 Jumada I 1448 AH
AI Summary
20 Oct 202610 Jumada I 1448 AH
Ant Group Launches Ming-3.0-tts Speech Generation Model
Ant Group has announced the launch of the Ming-3.0-tts speech generation model, designed to provide fine-grained voice control through small models suitable for local deployment. The release includes two models: Ming-3.0-tts-0.5b with about half a billion parameters, and Ming-3.0-tts-tiny based on the Ling V3 architecture, featuring a total of 7.9 billion parameters.
The model allows users to clone a reference voice, create a new voice from a text description, and choose from over 100 built-in Chinese voices and five English ones. Output can be directed using natural language instructions, with direct adjustments for emotion, speed, pitch, and volume.
Follow these topics
Sign in to follow the topics that matter to you
This summary is generated with AI and receives periodic editorial review. Refer to the original source for full details.
Ant Group Launches Ming-3.0-tts Speech Generation Model
Ant Group has announced the launch of the Ming-3.0-tts speech generation model, designed to provide fine-grained voice control through small models suitable for local deployment. The release includes two models: Ming-3.0-tts-0.5b with about half a billion parameters, and Ming-3.0-tts-tiny based on the Ling V3 architecture, featuring a total of 7.9 billion parameters.
The model allows users to clone a reference voice, create a new voice from a text description, and choose from over 100 built-in Chinese voices and five English ones. Output can be directed using natural language instructions, with direct adjustments for emotion, speed, pitch, and volume.
Follow these topics
Sign in to follow the topics that matter to you
This summary is generated with AI and receives periodic editorial review. Refer to the original source for full details.
0
0 reading now
Insight Score
Rate to unlock
You have not rated yet.
Sign in to react, rate, and save. Sign In
