Deploy on Google Colab 🚀

Free, convenient, and hassle-free, ideal for users with limited device performance. Highly recommended!

Want to try local deployment? Jump to the "Local Installation" section.

What is Colab?

Google Colab, powered by Colaboratory (shortened as Colab), allows you to write and execute Python code in your browser with:

• No configuration required
• Free GPU usage
• Easy sharing

Whether you're a student, data scientist, or AI researcher, Colab can help you work more efficiently. You can watch Introduction to Colab or Colab Features You May Have Missed to learn more, or start using it below!

Similar platforms include:

Kaggle, an online platform for data science and machine learning, provides a community for data scientists and ML engineers to share code, datasets, and solutions.

Provider	CPU	Memory	GPU	GPU Memory	Usage Limit
Google Colab	Intel Xeon(R) CPU @ 2.20GHz	12G	T4	15G	1-3 hours/day
Kaggle	Intel Xeon(R) CPU @ 2.20GHz	30G	T4*2	15G*2	30 hours/week

Note

Google Colab requires a VPN for access, while Kaggle does not.

Installation Steps

1. Clone and Download

# Default Directory
%cd /content

# Remove Files
%rm -rf /content/CreatorBox/

# Clone Repository
!git clone https://github.com/xiesx123/CreatorBox.git

# Install Dependencies
# Optional
!pip install --use-deprecated=legacy-resolver -r /content/CreatorBox/src/support/third_party/cosyvoice/requirements.txt
# Optional
!pip install --use-deprecated=legacy-resolver -r /content/CreatorBox/src/support/third_party/f5_tts/requirements.txt
# Required*
!pip install --use-deprecated=legacy-resolver -r /content/CreatorBox/requirements.txt

# Install Software
!pip install pyngrok
!curl -sSL https://ngrok-agent.s3.amazonaws.com/ngrok.asc \
  | sudo tee /etc/apt/trusted.gpg.d/ngrok.asc >/dev/null \
  && echo "deb https://ngrok-agent.s3.amazonaws.com buster main" \
  | sudo tee /etc/apt/sources.list.d/ngrok.list \
  && sudo apt update \
  && sudo apt install ngrok \
  && sudo apt install rubberband-cli \
  && sudo apt install jq

2. Environment Variables

Tip

Refer to the "Preparation" section for environment variable configuration.

3. Start and Run

The program runs in the current terminal window and occupies it until the program exits.

# Working directory
%cd /content/CreatorBox

# Start application without tunneling
# !python run.py start -p 80

# Start application with tunneling (`-nh` is your Host address)
!python run.py start -p 80 -nh 'toucan-real-informally.ngrok-free.app' --ngrok

As shown, successful output indicates the application has started successfully.

_____                _            ______
/  __ \              | |           | ___ \
| /  \/_ __ ___  __ _| |_ ___  _ __| |_/ / _____  __
| |   | '__/ _ \/ _` | __/ _ \| '__| ___ \/ _ \ \/ / 
| \__/\ | |  __/ (_| | || (_) | |  | |_/ / (_) >  < 
\____/_|  \___|\__,_|\__\___/|_|  \____/ \___/_/\_\   v1.0.8

2025-04-08 11:34:52.458 | INFO 1496 task.py:18 - Startup Scheduler 2 Job Completed.
2025-04-08 11:34:52.458 | INFO 1496 main.py:84 - Started CreatorBox Run Debug Success (3.16 seconds)
2025-04-08 11:34:52.459 | INFO 1496 main.py:85 - http://172.18.0.1:8000

TIP

• 1、Notebook can only execute one cell at a time.
• 2. Default output directory: Google Colab /content, Kaggle /kaggle/working

Tunneling Issues

PyngrokNgrokError: 
The ngrok process errored on start: authentication failed: 
Your account is limited to 1 simultaneous ngrok agent sessions.
You can run multiple simultaneous tunnels from a single agent session by defining the tunnels in your agent configuration file and starting them with the command `ngrok start --all`.
Read more about the agent configuration file: https://ngrok.com/docs/secure-tunnels/ngrok-agent/reference/config
You can view your current agent sessions in the dashboard:
https://dashboard.ngrok.com/agents ERR_NGROK_108.

Info

If the above error occurs, go to the Ngrok Dashboard at https://dashboard.ngrok.com/agents, terminate the running agent, and retry step 3.