This is the sovits 4.0 model of the female announcer (default announcer) from game Battlefield 1.

Since the language of orginal dataset is English, so use English as input to get the best results.

If the user's voice is male, it is recommended to turn up just 6~8 pitches. Don't pitch too high.

This model is only used for speech conversion and not for singing, but you can still give a try.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no library tag.