This model is a voice clone of myself created specifically for Style Bert VITS2.
It is capable of text-to-speach voice generation in English, Japanese, and Chinese.
The voice is young and neutral that can be used for various situations (including but not limited to AITuber with non-binary gender, etc.).
Samples
To use it in English or Chinese tts, make sure you run App.bat (instead of Editor.bat that specializes in Japanese tts generation, and that can modify accents when necessary).
English
Japanese
Chinese
- Downloads last month
- 14
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.