NNiceVois

Own the file, not the account

A Kits.ai alternative for people who need the model file itself

Train and download my RVC modelPortable .pth and .index, yours to keep.
The honest answer

These tools solve different problems. Kits.ai is a hosted studio built around licensed artist voices and in-browser conversion, which is genuinely useful if you want a cleared voice to sing on your track. NiceVois does not offer a voice library at all — it trains a model from audio you supply and hands you the files.

The question worth asking is whether you need a voice to use, or a model to own. Those lead to different products.

Which one fits

What you wantBetter fit
A cleared, licensed voice to sing on a releaseA licensed-voice studio
A model of your own voice, as a fileNiceVois
To convert audio inside a browser studioA hosted studio
To use one model across several different toolsNiceVois
A model that survives the service closingNiceVois

Why portability is the real difference

A hosted voice works inside the platform that hosts it. A downloaded .pth and .index work in any compatible RVC interface, on your own machine, indefinitely. That distinction stopped being theoretical in 2026, when a large hosted model catalogue closed and took its models with it. People who had exported files kept working; people who had not, did not.

What we do not provide: no voice catalogue, no licensed artist voices, no in-browser cover creation, and no rights clearance. If your project needs a commercially cleared voice, a licensing platform is the correct tool and this is not a substitute for it.

What you need to bring

A clean, single-speaker recording of a voice you own or have clear permission to train — up to 15 minutes during the public beta, in WAV, MP3, FLAC, M4A, or OGG. The dataset guide covers what makes a recording usable.

Permission is the boundary

Because we do not supply voices, the rights question sits with you. Train your own voice or one you have explicit permission to use. Our acceptable use policy is specific about this.

Need the model, not the library?

Upload permitted audio and download a portable .pth, .index, and complete ZIP.

Train my RVC model