Voice Synthesis API Documentation
Advantages of ZmeetAI speech synthesis
- Up to thousands of model pronunciation models, each with different emotional tone styles
- Version distinction
- The fast version can return voice within 100 milliseconds , supports 2014 model pronunciations, supports emotional customization
- Lightweight version with delicate emotions and delicate voice
- The ssml version supports custom ssml syntax
Version
Speedy version
Lightweight version
[gpt version]
