NNiceVois
One-tap RVC training · No local setup

RVC training online: train a voice model in one tap

Start training belowUpload your audio, choose epochs, name the model, and press once. The trainer is on this page.
Summary

Upload your audio, choose the epochs, name your model, and press Start Training. NiceVois handles everything else and returns the validated .pth, matching .index, and complete ZIP.

RVC training online with NiceVois gives you the portable model files without installing software, maintaining a notebook, running commands, or owning a local GPU.

Once the model is trained, you can convert a vocal or a whole song with it here too - see the RVC voice converter, or sing a Suno song in your own voice. Every conversion returns the normal RVC result and a Clean Consonants version.

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…

3-minute product demo

See the full audio-to-model workflow

Watch one permitted audio file move from upload and configuration to cloud training, the finished model, and the downloadable files.

If your only recording of the voice is a finished song, split it first: the free lead and backing vocal splitter hands back the lead vocal with the instrumental and the background vocals taken off, which is what a voice model should be learning from.

What you do in the browser

  1. Choose a WAV, MP3, FLAC, M4A, or OGG recording.
  2. Name the finished model and review the duration-based epoch recommendation.
  3. Confirm that you own the voice or have clear permission to train it.
  4. Press Start Training.

What NiceVois handles for you

NiceVois prepares the audio, trains the RVC model, validates the result, creates the matching index, and packages the downloads. You only configure the model once and follow clear progress until it is ready.

Can you close the page?

Yes, after the upload and start request complete. Reopening the same browser workspace reloads its active and completed jobs. The interface reports the current stage, completed epochs, elapsed time, checkpoints, and final download actions.

Current public workspace

CapabilityCurrent behavior
Audio durationQuoted from verified duration, subject to the live feasibility limit
EpochsUp to 500 with a subscription; up to 150 on a free run
DownloadsIndividual .pth, individual .index, or complete ZIP
RetentionSeven days, with manual deletion available sooner
Local requirementsA modern browser; no local RVC or NVIDIA GPU

Important: RVC is voice conversion, not text-to-speech. The trained model changes the vocal identity of a source performance; it does not independently generate words from text.

Start a cloud RVC training run

Use a voice you own or have permission to model.

Go to the trainer