Powered by

Tg Develop's W Okada Fork Cloud

Last update: April 1, 2026

Introduction

Virtual Audio Cable

A Virtual Audio Cable (VAC) is required to use the realtime voice changer on Discord & Games.

  • A VAC makes a virtual audio device, used to re-route audio between programs.

  • In this context, it allows you to set the AI Converted Voice Output as your input device in programs like Discord.

Choose your Cloud Service

Set up the program using your preferred cloud service guide. Once configured, use the Public Tunnel URL to open the interface and continue with the next steps

Colab

Google Colab Web UI

Decent performance and easiest setup for standard use.

 Kaggle

Kaggle

Generous free GPU quotas. Great alternative if Google Colab is limited.

 Lightning

Lightning.AI

Persistent storage and powerful GPUs.



Google Colab

  • 1. Access: Go to the Tg-Develop Colab.

  • 2. Install: Start from the top and run the first cell. Colab Install

  • 3. Second Cell: When it finishes (it will output Done! Proceed with the next steps), run the second cell. Colab Second Cell

  • 4. Ngrok: Scroll to the last cell, place your Ngrok token in the TOKEN_HERE field. Ngrok Token

  • 5. Launch: Run the cell. (Optional) Under the token field, you can change the region selection for lower latency. Once it finishes downloading, click the generated Ngrok link to start the Web UI.

Kaggle

Account Setup

  • Start by making an account here.
Kaggle Sign In
  • Verify your account with a phone number. This is required to enable the "Internet" option in your notebooks, which is necessary for downloading models and dependencies.
Kaggle Phone Verification

Notebook Creation & Setup

  • Create: Go to Kaggle and click Create then New Notebook at the top left. New Notebook

  • Import: Under your session's name click File then Import Notebook. Import Notebook

  • Link: In the new window, click the Link tab and paste the following URL: https://github.com/tg-develop/voice-changer/blob/master-custom/Kaggle_RealtimeVoiceChanger.ipynb. Click Import. Link Tab

  • Settings: In the sidebar on the right, turn on the Internet switch. Make sure persistence is set to Files and variables.

Internet

  • GPU: Turn on T4 x2 GPUs in the Accelerator settings. GPU

  • Save: (Optional) Turn on "Save version" to save your progress. Persistence

Installation & Tunnels

  • Install: Starting from the top, run the first installation cell. When it outputs Done! Proceed with the next steps, run the third cell. Install 1 Install 2

  • Ngrok: Put your token in the last cell. Token

Lightning.AI

Create an Account

LightningAI Signup
  • Make sure you verify yourself with a phone number. Once you've done that you will get an email that looks like this:
LightningAI Verification
Clone
  • GPU: Switch to a GPU environment (Studio Environment -> Switch To GPU).
GPU Settings

  • Install: Run the first cell to install, run the second cell to configure.

  • Tunnels: In the third cell, choose your tunnel (Port Viewer recommended) and run it. Use the provided file drive to upload models and TensorBoard to monitor training.

  • File Management: Use the Teamspace Drive button on the right sidebar to upload files. LightningAI Teamspace Drive

  • Maintenance: If you need to update the Program or start fresh, you can run the final cell in the notebook, "Delete everything". This will remove all downloaded files and configurations from your persistent storage, allowing for a clean installation by re-following the notebook with perhaps a changed branch variable.

Usage

Now that you have the Web UI running, the rest of the process is identical to using a local installation.

Continue with the Local Guide

Troubleshooting

The web interface (client) is just a control panel; the actual voice conversion and backend processes happen on the server. If the cloud server crashes or fails to launch properly, you can enable Debug Mode to read the exact error logs directly in your notebook's output cell.

To do this, you need to append the --log-level debug argument to the command that launches the server.

  1. Scroll to the bottom of your notebook to find the cell that starts the server.
  2. Look for the execution command: !./ML_Program
  3. Add the debug flag to the end of the command so it looks like this:
!./ML_Program --log-level debug
  1. Run the cell again.
  1. Locate the final cell in your notebook/studio that actually starts the server.
  2. Look for the execution command: !./VoiceChanger
  3. Add the debug flag to the end of the command so it looks like this:
!./VoiceChanger --log-level debug
  1. Run the cell again.

The notebook output cell will now print detailed debug logs. If the server crashes, copy the text output from that cell. Save it to a .txt file, or paste it to a site like Pastebin to share with others when asking for support.
‎

You have reached the end.

Report Issues

© Copyright 2026. All rights reserved.

⚠️
SECURITY ALERT: COMMUNITY SAFETY NOTICE
  1. Discord Vanity Hijack: AI HUB official vanity discord.gg/aihub was hijacked on April 30, 2026. Do not join it, it's a malicious clone server. Please use our official permanent invite: discord.gg/mmRR2TUJF5.
  2. Weights.gg Vanity (At Risk): We are aware of actors targeting AI HUB's Former Partner Weights.gg's vanity discord.gg/weights. To ensure you remain on the legitimate server, please use our permanent invite: discord.gg/CHGgVRCHvm. Be aware that Weights.gg's Discord Server is semi closed since the shutdown on April 1st 2026.
  3. We aren't affiliated with W8ights / INERTIV: We have no affiliation with W8ights, which rebranded to INERTIV for the name being too close to Weights.gg, our former Partner. They currently don't seem adversial or malicious, but please be cautious.
  4. TL;DR: YOU ARE SAFE. This is the original, legitimate AI Hub Docs. We are just informing users about impersonations.