Guides

RVC training guides

The complete path, in order: prepare the audio, choose how long to train, understand the files you get back, and put them to use. Each guide stands alone, so start wherever you are stuck.

Before you train

Start hereHow to train an RVC model online

What happens between upload and a ready-to-use model package.

DatasetHow much audio do you need?

Duration targets, what to cut, and why preparation beats length.

Source audioAudio requirements for RVC training

Formats, duration, isolation, and the problems that weaken a model.

Training strengthHow many epochs should you use?

Use audio duration and urgency to choose a starting point.

After you train

Model filesRVC .pth vs .index explained

What each output contains and why the package includes both.

Loading itHow to use your RVC model

Where each file belongs, and how to run your first conversion.

CoversMake an AI cover with your model

Separate, convert, set the pitch, and mix it back.

Model formatsPTH to ONNX explained

When conversion helps, what it drops, and when to skip it.

Coming from another service

What happenedWeights.gg shut down

Whether your old models are recoverable, and how to rebuild one.

Focused alternativeReplacing Weights.gg training

What this utility replaces—and what it deliberately does not.

No local GPUAn Applio alternative

The same RVC v2 output without an NVIDIA card or a Python setup.

Own the fileA Kits.ai alternative

When you need a portable model rather than a hosted voice library.

Custom voiceA Jammable alternative

Train your own voice instead of picking one from a catalogue.

Ready to train?

Upload permitted audio and download a portable .pth, .index, and complete ZIP.

Start Training