🔴RVC v2

Read this before: RVC V2

Configuring VB-Cable (For Virtual Sound):

VB-Cable is necessary to send sound to the virtual microphone for use with Discord or other software.

1. Go to the official VB-Audio page for VB-Cable and click "Download."

2. This will download a .zip archive that you'll need to extract into a new empty folder.

3. Run setup_x64.exe (for 64-bit Windows) or setup.exe (for 32-bit Windows).

4. After installation, restart your PC so Windows can detect the VB-Cable audio device.

Install Voice Changer:

Next, open up go-realtime-gui.bat in your RVC folder

Once that is launched, you should see a CMD prompt that launches, wait a second and the GUI should open up.

Your GUI may look like this, you can use harvest, or Crepe :

Extra Inference time needs to be above 0.99 for best results!

You need to download a RVC model next, this needs an .index file to run properly. Download the

model from the Voice Models in https://discord.gg/aihub

Click the download link of the model and download it

It should be a .zip in your downloads now, take the .pth file from the .zip you just downloaded, and put it in your weights folder and take the .index file from the .zip and put it in the logs folder, both can be found in the RVC Folder.

Now you can go into your GUI, click where it says “Select the.pth file” and go to your weights folder the the RVC folder, and select the .pth you just put in there.

Now go to “Select the .index file” and choose the index file you just put in the logs folder.

You do not need to select a .npy file. It doesn’t help or hurt anything, so it’s pointless to have.

Audio Settings Configuration:

To achieve the best audio quality, follow these steps to configure the audio settings:

1. Choose your audio devices:

Select your primary microphone for input.

Choose the VB-Cable audio device: "[MME] CABLE Input (VB-Audio Virtual Cable)" for output.

Make sure your headphones are correctly configured as the default output device in the system settings.

If you're using other software like Discord, configure them as follows:

For input, select « CABLE Output ».

For output, choose your headset.

These configurations will ensure that the voice changer works properly with your other applications.

Make sure the “Pitch settings” is set to 12 if you have a low voice trying to use a high pitch voice model (usually male to female voice conversions)

And -12 if you have a high pitched voice trying to use a low pitch voice model (usually female to male)

More information about pitch :

Now press Start Audio Conversion, it will say blocked for a second, give it a second, but if you did everything right, it should work in about 10-20 seconds.

There is also a slight delay on speaking since this is real-time conversion

(Mangio may have added “hear yourself” in the GUI, but as of writing this, not yet)

If you want to hear yourself you can right click on this

Scroll down to the bottom where it says More sound settings, Recording, find CABLE Output, right click it, properties, and then listen. Now tick “listen to this device” and press apply, now you can hear yourself!

Hope this helped, I hate you all.