A TTS voice I made then proceeded to turn into an RVC model.

I couldnt think of an image so i had to use the one attached from google.

I've learned more about the best duration for datasets to use Ov2 on, so I wanted to test it with this.

Pitch used doesnt really matter, but I would say 0 would be the best.

Obv cant be used for singing, realtime only.

Index ratio: 0.5 to 0.7.

Link: https://huggingface.co/Kryptone/RVCollection-Revamped/resolve/main/Ov2Models/HVEMND_Male.zip?download=true

Demos attached.

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/Kryptone/RVCollection-Revamped/resolve/main/Ov2Models/HVEMND_Male.zip?download=true Hosted on Hugging Face

Convert this model in EasyAIVoice