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.
Summary

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.

Voice training

Train an RVC voice from an audio file

Add up to 50 WAV, MP3, FLAC, M4A, or OGG files. NiceVois keeps them separate and prepares them together as one private training dataset.

.pth

This name is used for the .pth, .index, and complete ZIP package.

Standard is selected automatically.
200 epochs

Recommended: add your audio and NiceVois will suggest the right number.

Clean audio produces a better model. Use a dry voice recording with minimal music, echo, or background noise. Prepare your audio first if it needs it.

Persistent cloud storage

Your model library

Your voice models are files you own. Download them once and no platform can take them away.

Loading…
Paid model packages stay saved until you delete them.

Your .pth, .index, ZIP, and private listening preview remain available after closing the browser or restarting your computer. A model from the free training run is kept for 7 days and shows its expiry date; download it before then. Full-resolution source audio and temporary training files are removed after validation.

⌁Loading your models

Checking private cloud storage…

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, in WAV, MP3, FLAC, M4A, or OGG. Your first training is free, and every job is quoted before it starts. 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