Real-time Telegram content moderation system powered by Roberta model.
- Deploy on personal machine or docker
- Select settings that match your associations needs
- Press start
Chatique moderates your groupchat in realtime to detect hate speach and profanity using fine-tuned data and Metas Roberta Model
Use Sentence Transformers to capture input and compare to similar words in profanity filter
Realtime NSFW image detection with custom in-house model
Content moderation tools to manage users and set custom warnings such as 18+ emojis, urls, profanity, and hate speech
Create Your Own Rule-Book For Groupchat
Please be aware that the installation requires technical skills and is not for beginners. Consider downloading the prebuilt version.
Chatique will work on a CPU but will run slower I reccomend to run on a machine that has CUDA compatible Nvidia GPU, however bot will still execute.
1. Set up Your Platform
- Python (3.13 recommended)
- pip
- git
- Telegram
- Pyenv (Optional if on Linux Machine)
2. Clone the Repository
git clone https://github.com/Btylrob/Chatique.git
cd Chatique3. Add Your Telegram Bot Token
Create a .env to load your token
4. Install Dependencies
We highly recommend using a venv to avoid issues.
For Windows:
python -m venv venv
venv\Scripts\activate
pip install -r requirements.txtFor macOS:
Apple Silicon (M1/M2/M3) requires specific setup:
# Install Python 3.13 (specific version is important)
brew install python@3.13
# Create and activate virtual environment with Python 3.13
python3.13 -m venv venv
source venv/bin/activate
# Install dependencies
pip install -r requirements.txt** In case something goes wrong and you need to reinstall the virtual environment **
# Deactivate the virtual environment
rm -rf venv
# Reinstall the virtual environment
python -m venv venv
source venv/bin/activate
# install the dependencies again
pip install -r requirements.txtRun: If you don't have a GPU, you can still run Chatique as it will default to your CPU
Check out these helpful guides to get the most out of Deep-Live-Cam:
Visit our [official blog] for more tips and tutorials.
- All the people who starred or contributed to this repo 😍.




