One free training per signed-in account. Up to 5 minutes of audio and 150 epochs.
A few minutes of clean, varied singing can be enough for a good, usable voice model. Start with your own voice or a voice you have permission to use.
Hear it work
0:00 / 0:10
Voice-to-voice conversion
Convert a vocal or full song with your voice
Loading allowance...
Five free conversion download minutes. Listening is free, only downloading uses minutes.
Convert a vocal or a full song with a saved NiceVois voice or your own RVC model. Every conversion includes the normal RVC output and a NiceVois Clean Consonants version for more natural sibilance and breaths. Hear an original and converted voice.
Your free conversion time is usedA monthly plan adds more voice-conversion download minutes, or pay for one download from your training balance.Convert as much as you like - unlimited voice conversion, stem separation, noise removal and reverb removal, on one plan.
Voice modelChoose a saved voice or bring your own
.pth or model .zip
Your NiceVois voices
Voice model original audioOr drop your RVC model here
Your uploaded models
Trained voices live in your library further down and are counted separately, so removing one there does not free a slot here.
Only upload a model you own or have permission to use. By uploading, you agree to the Acceptable Use Policy.
Once you've selected a voice, Auto-convert will start the conversion right away, no need to press Convert.
Selected audio
Check this for a full song, or for a vocal with harmonies layered over it. We split the lead out, convert only the lead, and mix it back with the untouched music and harmonies. Leave it unchecked if your file is already a clean solo vocal.
Pitch shift
Converts ten seconds of your file at every pitch from −12 to +12, so you can hear which one suits this voice.
OutputConversion results
♫Your converted audio will appear here
Choose a voice and audio on the left, then press Convert.
Every pitch
Credit this voice when you publish:
NiceVois Clean Consonants Conversion
Voice models buzz on the sounds that carry no pitch: the s, f, sh, ch and t sounds, plus the breaths between lines. We put the original vocals back in those spots, so the singing changes voice and the consonants stay human.
Trained on your phone? Send the files somewhere you can use them.
Training stopped at this stage
The provider returned an error. Your other saved models were not affected.
Hear it first
An original vocal. A different voice.
The same words, melody and timing, converted with a licensed female library voice and NiceVois Clean Consonants.
Original
The recorded vocal
Converted
AI Minagi
Voice credit: AIみな〜ぎ（CV 花夜みなぎ）. Loudness-matched excerpts from an authorized source recording. This is a library-voice listening example, not a guaranteed result or a claim that this model used the free training limits.
From recordings to songs
Quick voice cloning, without the setup
You provide the voice and the performance. NiceVois handles the training and conversion.
01
Record your voice
Use clean solo recordings of your own voice or a voice you have permission to train. Sing a range of notes and sounds without background music.
02
Train your voice
Create a free account, add your recordings to the trainer, name your model and press Start Training. Your first training is free for up to 5 minutes of audio and 150 epochs.
03
Convert a vocal or song
Press Convert with this voice in your model library, add the vocal or song and press Convert. For a full song, select Separate the stems first. Listen to the result and download the version you prefer.
Download your .pth, .index or ZIP to keep locally. Free-trained models are stored here for 7 days; paid-trained models stay until you delete them.
In the same workspace
Prepare and clean your audio
Optional tools when you need them. Use Send to on a finished file to carry it into another tool without downloading it first.
10 shared free minutes every 24 hours. No account needed. One allowance covers separation and noise or reverb removal. A split counts the song's length at its first stem download; cleanup counts when processing finishes. Other stems and repeat downloads use no extra minutes. Subscribers have unlimited use. Trimming is free with no daily allowance.
Vocal and instrumental separatorSeparate a song into two tracks
Vocal and Instrumental Separator
Split a song into vocals and instrumental
Drop in a song and get the vocals and the instrumental as separate files.
Your first training is free with a signed-in NiceVois account: one free training per account, up to 5 minutes of audio and 150 epochs. You also get five free voice-conversion download minutes. Listening is free. Later training and additional conversion downloads have paid options.
Are five minutes and 150 epochs enough for a good voice?
They can be enough for a good, usable voice model when the recording is clean, solo and varied. Include the notes, vowels and consonants you want to use. More epochs cannot fix background music or poor recordings, and results vary with the source and voice. What to record.
Can I clone my voice in five to ten minutes?
Short recordings can train in minutes, but five to ten minutes is not a guaranteed completion time. Upload speed, audio length, epochs and GPU availability affect the wait. NiceVois shows a training estimate before you start and live progress afterward. See our measured training benchmark.
Is this text-to-speech or voice-to-voice conversion?
NiceVois uses RVC voice-to-voice conversion. You supply recorded singing or speech and a trained voice model. It changes the voice while following the performance's words, melody and timing; it does not sing typed lyrics or generate a song from text.
Can I put my cloned voice on a full song?
Yes. Choose your trained voice in the converter, upload the song and select Separate the stems first. NiceVois separates the instrumental, lead and backing vocals, converts the lead, and returns the cover and its parts. Use audio you have the right to process.
Can I download and keep my voice model?
Yes. Download the .pth, matching .index or complete ZIP and keep the files locally for compatible RVC software. A free-trained model is stored on NiceVois for 7 days; paid-trained models stay until you delete them. Download your free model before it expires.
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.
— used
⌁Loading your models
Checking private cloud storage…
Pricing
Training balance and conversion plans.
Train free, pay once, or subscribe.
Your first training is free - then pay only for the cloud training you use. Every account also includes five voice-conversion download minutes.
Your first training is free. After that, choose a single training, a three-training pack, or Unlimited for regular use. Every model you train is yours to download and keep.
Up to 500 epochs for every balance-funded training.
An exact quote first based on your audio and selected epochs.
Training balance
Pay only when you train
One balance for every NiceVois training. Your balance never expires. For more voice-conversion downloads, choose a monthly plan below.
20% off your first balance purchase. Applied automatically at checkout.
Free to start
Your first training
$0with a free account
Create a free account and your first voice training is free. It also comes with five voice-conversion download minutes. A shared 10-minute free allowance per rolling 24 hours covers both separators, noise removal and reverb removal, with 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-conversion download minutes
Use the included free minutes first. Subscribe only when you need more conversion downloads; monthly plans also include renewable training credit.
Pricing
Subscribe, or pay once
Use every tool with Unlimited, or buy one or three voice trainings without a subscription.
25% off your first month. Regular monthly price after that.
Unlimited everything
Every tool, one price
$20.00$20.00per month
Then $20.00 per month.
Every tool, unlimited: voice training, voice conversion, stem separation and cleanup. Train multiple voices at once.
Train one voice
$5.00once
One training run, any length, up to the full epoch range. Five minutes of conversion downloads included. No subscription, nothing to cancel.
Train three voices
$10.00once
Three training runs, any length, up to the full epoch range. Fifteen minutes of conversion downloads included. No subscription, nothing to cancel.
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
Before you pay
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 does unlimited actually mean?
No minutes to count on any tool, every output included, up to 500 epochs per training run. Fair use applies.
How do I cancel?
One click from your account, no email needed. You keep everything until the end of the month you paid for.
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.
Who sees my card?
Lemon Squeezy, the merchant of record. NiceVois never sees card details, and tax is handled at checkout.
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.
What happens to my audio?
It is processed for your job and never shared. Source audio is removed after validation. Models trained on a paid run stay until you delete them; a model from the free run is kept for 7 days, and its expiry date is shown on the model itself.
Can I hear it before I pay?
Yes. Your first training is free, and every finished model comes with a listening proof before you decide anything.
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