NNiceVois

Phone and voice-memo audio

M4A to PTH: use a voice memo to train an RVC model

Upload an M4A and start trainingVoice Memos, WhatsApp notes, and AAC exports upload directly.
Summary

Yes. An M4A uploads directly and trains an RVC .pth model - no conversion step on your side. M4A is the format an iPhone Voice Memo, a WhatsApp voice note, and most phone recorders produce, which makes it the most common real starting point for a voice dataset.

M4A is a container holding AAC audio. AAC is lossy, but at the bitrates phones record at it holds voice detail well - usually better than an MP3 of the same size. You do not need to export it to WAV first.

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…
Finished 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. Full-resolution source audio and temporary training files are removed after validation.

Loading your models

Checking private cloud storage…

What phone audio does well, and where it hurts

Phone recordings are convenient and usually close to the mouth, which is exactly what training wants. The risk is everything else the room contributed.

Voice notes from messaging apps

A WhatsApp or iMessage voice note is usable, but it is encoded for small size rather than fidelity. If you have the same words recorded in the Voice Memos app, use that instead. When a voice note is all you have, gather several minutes of it rather than relying on one short clip - length partly compensates for a compressed source.

What the service does with the M4A

The official RVC training workflow reads supported source audio through FFmpeg, decodes it 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. Nothing about the M4A container needs handling on your side.

M4A versus the alternatives

QuestionM4A (AAC)WAV
Can this tool upload it?YesYes
CompressionLossy, but efficient at voice bitratesUncompressed
Typical sourcePhone recorder, voice note, AAC exportDesktop recording, DAW export
File sizeSmallLarge
Best choiceUse when the recording was made on a phonePrefer when you recorded straight to your computer

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.

Have a voice memo?

Upload the M4A directly - the service prepares the training dataset for you.

Train a PTH model from M4A

Technical reference: RVC Project training instructions.