Upload your audio, choose the epochs, name your model, and press Start Training. NiceVois handles the complete RVC workflow and returns a portable .pth, matching .index, and ZIP.
Already have a .pth? This page is about making one. To convert a vocal with a model you already own, use the RVC voice converter.
How it works
Turn a recording into an RVC voice model.
A real example, start to finish.
01
Upload your voice
A clean recording of only your voice: no music, no backing vocals.
Training recording
02
Train your RVC model
Your model trains in the cloud, and the .pth and .index files are yours to download and keep.
Create a free account and your first voice training is free. It also comes with three free voice conversions, each up to 5 minutes long. The vocal separator, lead and back separator, noise remover, reverb remover and Vocal Enhancer each include one free use, up to five minutes. No account needed.
Checking eligibility...Taster pack
$5 training balance
$4.99$4.99non-expiring
One-time, not a subscription. At current quotes, $5 covers up to 11 one-minute tests at 100 epochs, 4 five-minute runs at 180 epochs, or 2 ten-minute runs at 180 epochs. The exact cost and balance left are shown before training.
Starter pack
$10 training balance
$8.99$8.99non-expiring
Pay different amounts for short tests and longer, stronger training.
Best value
$27.50 training balance
$24.99$24.99includes $2.51 extra
Best for creators training several voices or comparing epoch settings.
Monthly conversion plans
More voice conversions
Use the included free minutes first. Subscribe only when you need more voice conversions; monthly plans also include renewable training credit.
Every tool, unlimited, with separate-file batch processing. Train multiple voices at once.
One-time training
Pay once. No subscription.
Train one voice
$5.00once
1 training run Any length of training audio, up to 500 epochs per voice. Includes 3 voice conversions.
Train three voices
$10.00once
3 training runs Any length of training audio, up to 500 epochs per voice. Includes 9 voice conversions.
Your voice. Your files. Download your models and use them anywhere RVC runs.
.pth.indexZIP
Starter
For occasional projects
$8.99$8.99per month
Then $8.99 per month.
$5 monthly training credit and 30 voice-conversion download minutes.
Creator
For regular cover makers
$14.99$14.99per month
Then $14.99 per month.
$10 monthly training credit and 90 voice-conversion download minutes.
Pro
For high-volume work
$24.99$24.99per month
Then $24.99 per month.
$20 monthly training credit and 240 voice-conversion download minutes.
Secure checkout by Lemon SqueezyCancel any time from your accountYour model files are yours to keep
A few things to know
Can I hear it before I pay?
Yes. Your first training is free, and every model comes with a listening proof first.
How do the Lite allowances work?
Lite includes two trainings per paid billing month and 10 conversions per 24-hour window. A new window starts with your first conversion; all 10 renew together 24 hours later. Your converter shows the reset in your local time. A conversion counts once when it starts and comes back if it fails; listening and downloads are free. Unused allowances do not carry over. Both subscriptions include unlimited vocal separation, lead/back separation, noise removal, reverb removal and Vocal Enhancer.
What does unlimited actually mean?
No minutes to count on any tool, every output included, up to 500 epochs per training run. Fair use applies. Unlimited also unlocks batch processing: drop multiple files, start once and get a separate result for each. Free and Lite process audio files one at a time. Multi-file training datasets and manual mixes are unchanged.
Do I keep my voices if I leave?
Yes. Every model is a .pth, .index and ZIP you download, and they work anywhere RVC runs.
How do I cancel?
One click from your account, no email needed. You keep everything until the end of the period you paid for, a month or a year.
What if a training fails?
You are not charged for it. A failed or cancelled run releases what it reserved, and an upload that never arrives does not spend your free run.
Do I need an account to pay?
No. Pay with any email. Sign in with that same email on any device and everything you paid for is there.
What happens to my audio?
It is processed for your job and never shared. New trainings keep your original recordings as a private dataset ZIP, plus an MP3 listening preview. Your dataset follows your voice's retention: paid runs stay until you delete them; free runs are kept for 7 days. Older voices may only have the MP3 listening copy. Temporary training files are removed after validation.
Who sees my card?
Lemon Squeezy, the merchant of record. NiceVois never sees card details, and tax is handled at checkout.
Wrong charge or an unused month? Email info@nicevois.com with the checkout email and date; it is reviewed with Lemon Squeezy and returned to the original payment method. Refund policy · Privacy
Secure checkout is being prepared.
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 model files and private MP3 listening preview remain available after closing the browser. New trainings also keep the original recordings in a downloadable dataset ZIP. Paid voices and their saved datasets stay until you delete them. Free voices and their saved datasets are kept for 7 days; download them before then. Older voices may only have the MP3 listening copy. Temporary training files are removed after validation.
— used
⌁Loading your models
Checking private cloud storage…
NiceVois is a converter-style utility for people who want the finished RVC files without installing a local training stack or maintaining a notebook.
What you can upload
The current public workspace accepts WAV, MP3, FLAC, M4A, and OGG. Use one speaker, minimal room echo, little or no music, and no clipping. A clean recording matters more than the filename extension.
Training from a song rather than a dry recording? Take the music off first, and take the harmonies off with it — a model trained on stacked background vocals learns the stack, not the singer. The free lead and backing vocal splitter returns the lead on its own.
What happens after upload
The server receives the source audio and creates a private job for your browser.
The RVC pipeline slices and prepares the dataset, extracts pitch and voice features, and waits for cloud GPU capacity.
Training reports real completed epochs, then the service exports and validates the model.
The matching retrieval index is built and both artifacts are packaged into a ZIP.
After the server accepts the job, training continues even if you close the tab or shut down your computer.
Which download should you keep?
File
Purpose
Best use
.pth
Trained RVC model weights
Load the voice model into a compatible RVC interface.
.index
Retrieval index made from the training features
Use with the matching model when your interface supports feature retrieval.
Complete ZIP
The matching .pth and .index together
Archive or transfer the complete model safely.
Current public-beta limits
Your first training is free. Every job shows a fixed quote from audio length and epochs before cloud work begins, and may select up to 500 epochs. Purchased balance does not expire, finished downloads remain available for seven days, and new jobs may pause when cloud GPU capacity is full.
Turn your audio into a trained RVC model
Upload a supported voice recording, name the output, and follow the real training stages.
Upload a voice recording (WAV, MP3, FLAC, M4A, or OGG), name the model, choose the epochs, and press Start Training. NiceVois runs the complete RVC v2 training in the cloud and returns a downloadable .pth, its matching .index, and a ZIP with both. No GPU, Colab notebook, or installation is involved.
Is converting audio to PTH free?
Your first run is free with a free account. It covers up to 100 epochs and under 3 minutes of audio, and you download the finished model before paying anything. Longer audio and stronger training up to 500 epochs are included in the monthly subscription, with a fixed quote shown before the job starts.
How much audio does a good RVC model need?
Two to ten minutes of clean, single-speaker audio is the practical range. Recordings under one minute may not produce a reliable model, and background music or overlapping voices hurt quality more than shortness does.
How long does audio to PTH training take?
Most jobs finish in 10 to 40 minutes depending on audio length and epochs. A live estimate is shown while the job runs, and you can opt into an email when the model is ready.