Yes. An OGG uploads directly and trains an RVC .pth model. OGG usually holds Vorbis or Opus audio, which is what Discord, Telegram, and many browser recorders produce. It works - but chat codecs are tuned for low bandwidth, so the source deserves a closer listen than a studio file would.
Opus is genuinely good at speech for its size. The catch is that voice-chat applications often encode at very low bitrates, and what a call drops to stay smooth is exactly the high-frequency detail a voice model wants.
Active trainings
Selected job
Training details
Working
Model—
Training strength—
Elapsed time—
Stage 1 of 6Receiving audio
Epoch 0 of 2000%
Epoch progress comes directly from the running RVC trainer.
The audio you sent
PTH
Latest training checkpoint
An inference-ready early model is available while training continues.
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. Each separator, noise remover and reverb remover includes 10 free minutes, one time. No account needed. Vocal Enhancer is part of a subscription.
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.
Subscriptions
Cancel any time
For everyday projects
NiceVois Lite
Unlimited audio tools, with a smaller training and conversion allowance.
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 finished model comes with a listening proof before you decide anything.
How do the Lite allowances work?
Lite includes two training runs per paid billing month and 5 voice conversions every 24 hours, measured from when each one starts, not midnight. 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…
Listen for what chat compression removes
Before training on chat audio, play it back on headphones and listen for these:
Sibilants (“s”, “sh”) that sound watery, smeared, or swishy.
Breaths that vanish entirely between words - a sign of aggressive voice activity detection.
Momentary dropouts or robotic patches where the connection struggled.
Background suppression that pumps, opening and closing around speech.
Those artefacts are part of the training signal. The model can and will reproduce them.
Getting a usable model from chat audio anyway
If a Discord recording is what you have, it can still work. Favour longer stretches of continuous speech over many short clips, cut sections where other people talk, and avoid material recorded while the connection was poor. If the same speaker has any non-chat recording at all - a voice memo, a video soundtrack - prefer it, and consider combining sources.
What the service does with the OGG
The official RVC training workflow reads supported source audio through FFmpeg, decodes Vorbis or Opus into the representation preprocessing requires, and extracts the features used for training. NiceVois runs that workflow in a pinned cloud environment and validates the exported model before showing the downloads.
OGG versus the alternatives
Question
OGG (Vorbis / Opus)
M4A or MP3
Can this tool upload it?
Yes
Yes
Compression
Lossy, often at low chat bitrates
Lossy, usually at higher bitrates
Typical source
Discord, Telegram, browser recorder, game audio
Phone recorder, music library
Risk to watch
Voice-chat artefacts and dropouts
Repeated re-encoding
Best choice
Use when chat audio is the only recording of the voice
Prefer when a phone or file recording exists
What you receive
The finished model is available as a named .pth, a matching .index, and a ZIP containing both. The public workspace retains the completed files for the displayed seven-day window, and you can delete an inactive job from your private model library at any time.
Only have a Discord recording?
Upload the OGG directly and let the service prepare the dataset - just listen for chat artefacts first.