48K noise-free AI gummies, adorable loli voice RVC model

The two premium noise-free models they previously produced received unanimous praise.

The facelifted model we brought here is slightly cuter than the previous two models, built according to the previous two models, with a large dataset extracted from loli voices and Ai + manual noise reduction, still performing as well as the previous two models.

48K Ai Yalin A mature RVC model with a wide vocal range

48K Ai Rimo A very clean and well-handled girly voice RVC model

In terms of inference, I haven't encountered any distortion or breath cracking sounds so far. There may be rare cases where this issue occurs. I've tried it so far and found that some original input can output noiselessly.

The model's algorithm uses RMVPE, and after optimized sampling rate, outputs 48K. The cover parts are suitable for cute and lively songs, and may require your tone tone to be more delicate and optimal.

However, this model does not optimize for features like the smile, so if you mind, please proceed with caution 🛒.

On the right is a demo of the reasoning before and after and singing parts I uploaded, but I don't guarantee you'll achieve the same effect after reasoning (it varies by user).

If mutes occur, adjust your pitch appropriately to resolve the issue.

Redesigned models may only be used for non-commercial derivative purposes, and please do not use content that violates the laws and regulations of your current country.

(The modified models can only be used for non-commercial secondary creation, and please do not use them in violation of the laws and regulations of the current country.)