# Tg Develop's W Okada Fork Kaggle

Last update: September 6, 2025

• This is a cloud-based alternative to run Wokada Tg-Develop's Fork, Realtime Voice Changer for calls/games, only for people who don't have a good PC GPU, via the Kaggle Service.

• A VAC (Virtual Audio Cable) makes a fake audio device, used to re-route the audio of different programs.
• In AI Realtime Voice Changing context, it's used to get the output of AI Converted Voice Output as the input in other programs such as Discord.

• Run setup64, not 64a, after extracting the zip to a new folder

• After installing the VAC Lite, it changes your default audio system. Click Yes when it asks you to open the audio device settings (or press WIN+R, type "mmsys.cpl" if you closed it already), and change your Recording and Playback devices back to your usual devices. Same for communications device aswell (right click -> set as default communication device)

sudo apt-get update && sudo apt-get install -y portaudio19-dev

sudo yum install -y portaudio

sudo pacman -Syu portaudio

1. Start by making an account here. ‎

   

‎

2. Verify your acount with a phone number so you can turn on the "internet" option.

1. Start by making an account here. ‎

   

‎

2. Verify your acount with a phone number so you can turn on the "internet" option.

1. Go to Kaggle and click "Create" then "New Notebook" at the top left.

   

‎

2. Under your session's name click "File" then "Import Notebook".

   

‎

3. On the new window that appeared on the right click "Link" then type in the box this link https://github.com/tg-develop/voice-changer/blob/master-custom/Kaggle_RealtimeVoiceChanger.ipynb.

   

Click "Import" on the bottom right once you've done this.

4. When it's done importing it will display this text window.

   

‎

5. Under "Session options" in the sidebar turn on "internet". Make sure persistance is on for both files and varibles.

   

6. Turn on T4 X2 GPUs in accelerator.

   

‎ g: (Optional) Turn on headless mode so you can run so you can run the GPU on all sessions and save your progress. Go to the top right and click "Save version" then open the advanced dropdown.

‎

1. Starting from the top run the first cells, with the first being:

   

a2. When it's done, which may take a couple of minutes, it will output Done! Proceed with the next steps.

2. Run the third cell which is:

   

1. Scroll down to the last cell and you should see a section where you put your ngrok token. If you dont have a ngrok acount sign up here.
   a2. Once you have an acount you can authenticate your ngrok tunnel agent here: https://dashboard.ngrok.com/get-started/your-authtoken
   ‎

2. put the Ngrok token in the last cell like so:

   

3. Once the Ngrok token is there run the cell and let it download what it needs then you can click on the ngork link and start using W-Okada.

4. (Optional) Directly under where you put your ngrok token there is region selection. You can change it to any of these servers to get less latency:

• us -> United States (Ohio)
• ap -> Asia/Pacific (Singapore)
• au -> Australia (Sydney)
• eu -> Europe (Frankfurt)
• in -> India (Mumbai)
• jp -> Japan (Tokyo)
• sa -> South America (Sao Paulo)

3. From here it's pretty much the same as using local W-Okada.

Now that you have the web interface running via Kaggle, the rest of the process is identical to using a local installation.

For mostly all subsequent steps, including audio routing, application settings, and model usage, please continue by following the Local PC guide.

Continue with the Local PC Guide