# AICoverMaker

Last update: July 18, 2025


image
#

# Introduction ‎

  • AICoverMaker (or known as RVC-AI-Cover-Maker-WebUI) is an Applio RVC Fork developed by the Eddy, as a better and updated version of the old AICoverGen.

  • It's liked for its great UI & Automated AI Cover Process, making it the easiest way to make ai cover, as it automatically separates instrumentals and mixes them back with the converted vocals.


# Are RVC Models Safe?

RVC Models are PyTorch Models, a Python library used for AI. PyTorch uses serialization via Pythons' Pickle Module, converting the model to a file. Since pickle can execute arbitrary code when loading a model, it could be theoretically used for malware, but this fork has a built-in feature to prevent code execution along the model. Also, HuggingFace has a Security Scanner which scans for any unsafe pickle exploits and uses also ClamAV for scanning dangerous files.


# Pros & Cons

✔️ PROS
CONS
  • Automatically separates instrumentals and mixes them with converted ones
  • Currently stable
  • Faster interface
  • Automatic model upload
  • Has Mangio-Crepe
  • User-friendly UI
  • Can't Train models
  • No Precompiled versions for Non-Windows Users
  • Doesn't support Mac nor any NON-Nvidia GPUs

# System & Hardware Requirements

SPEC MINIMUM REQUIREMENT
OS Windows 10 or later / Any Modern Linux Distro
RAM 6GB
Storage 6 GB
SPEC SUGGESTED REQUIREMENT
OS Windows 10 or later / Any Modern Linux Distro
GPU NVIDIA RTX 20 Series or later
RAM 6GB+
Storage 6GB+

In case you don't meet the requirements to run it locally, it also has a 2 Cloud Versions: Kaggle & Colab

#

# Download

#

# Precompiled (Windows)

  1. The easiest way to download RVC-AI-Cover-Maker-WebUI is by going to Eddy's Latest GitHub Release, and clicking the Precompiled version.

    image

  1. Unzip the folder. It may take a few minutes.

  1. Open the AICoverMaker folder & execute run.bat.

    image

  • A console tab will appear, and after a moment your default browser will open with the WebUI ready to use.

# Source / Manual (mainly for Linux)

image

  1. Download the source code, either .zip (which is the most suggested usually) or .tar.gz, from the latest release link.

    image

  2. Extract the folder. It may take a few minutes.

  3. Open the AICoverMaker folder & execute the script run.sh for Linux, or run.bat for Windows.

    image

  • A console tab will appear, and after a moment your default browser will open with the WebUI ready to use.


#

# Downloading Music & Models

#

# Music Download

1. When in the UI look at the top left and look for the tab named Download Music and click it.

image

2. Then put the song you want to download in the text box and click download.

image

# Model Download

1. In the UI look at the top left and look for the tab named Download Model and click it.

image

2. Then put the model you want to download in the text box and click download.

image

3. You can also drag and drop your model in the Drop files box to upload them directly.


# Inference

Please use our Inference Settings guide to find out the inference settings do what.

TTA - results in longer separation time, it gives a little better SDR score but hard to tell if it's really audible in most cases". it “means "test time augmentation", it will do 3 passes on the audio file instead of 1. 1 pass with be with original audio. 1 will be with inverted stereo (L becomes R, R become L). 1 will be with phase inverted and then results are averaged for final output.


# Update

If you don't want to download the latest precompiled the next time a new version comes out, open AICoverMaker's folder & execute the script update.sh for Linux, or update.bat for Windows

image

#

# You have reached the end.

Report Issues