TeleTrans - The Telegram Translator

TeleTrans is a Python-based Telegram bot that translates messages in real-time. It uses the OpenAI API and DeepL/Azure API for translation.

Warning

This project requires the use of Telegram Apps API, which is a high-risk operation that could easily lead to a ban of your account. Please make sure you read and understand the Telegram API Terms of Service before using this project.

Features

Real-time translation of messages.
Supports multiple languages.
Uses OpenAI and DeepLX/Azure for translation.
Configurable source and target languages.
Command mode for enabling/disabling translation and setting languages.

Requirements

Python 3.10+
aiohttp
telethon
requests
emoji
azure-ai-translation-text

Manual Installation

Click for manual install details

Install & Setup & Run

Clone the repository:

git clone https://github.com/ihategfw/teletrans.git

Navigate to the project directory:
```
cd teletrans
```
Install the required Python packages:
```
pip install -r requirements.txt
```

Create a config.json file in the project directory:

{
  "api_id": "your_telegram_api_id",
  "api_hash": "your_telegram_api_hash",
  "translation_service": "deeplx",
  "azure": {
     "key": "your_azure_key",
     "endpoint": "https://api.cognitive.microsofttranslator.com/",
     "region": "global"
  },
  "deeplx": {
     "url": "your_deeplx_url"
  },
  "openai": {
     "enable": true,
     "target_lang": "en",
     "api_key": "your_openai_api_key",
     "url": "https://api.openai.com/v1/chat/completions",
     "model": "gpt-3.5-turbo",
     "prompt": "Translate the following text to English: ",
     "temperature": 0.5
  },
  "target_config": {}
}

api_id and api_hash are required for the Telegram API. You can get them by creating a new application at my.telegram.org.
translation_service can be set to deeplx or azure.
DeepLX: Click here to get your unique API url.
Azure: Click here to create an Azure Translator resource and get your Azure key.
If openai.enable is set to true, the bot will use the OpenAI API to translate, you can configure the target_lang and prompt for OpenAI. Only effective when the target language is same as openai.target_lang.

Run the script with an optional argument to specify the working directory:
```
python teletrans.py </path/to/your/directory>
```
If no directory is specified, the script will run in the current directory.

Running as a Daemon

Create a new service file:

sudo nano /etc/systemd/system/teletrans.service

Add the following content to the file:

[Unit]
Description=TeleTrans
After=network.target

[Service]
Type=simple
WorkingDirectory=/path/to/teletrans
ExecStart=/usr/bin/python3 /path/to/teletrans/teletrans.py /path/to/your/directory
Restart=on-failure

[Install]
WantedBy=multi-user.target

Replace /path/to/teletrans with the path to the project directory. /path/to/your/directory is the directory where the bot will store the configuration and logs.

Start the service and enable it to run on boot:

sudo systemctl start teletrans
sudo systemctl enable teletrans

Check the status of the service:
```
sudo systemctl status teletrans
```
To stop the service, use:
```
sudo systemctl stop teletrans
```

Installation with Docker

Click for Docker install details

Install Docker:

bash <(curl -sSL https://get.docker.com)

Make a directory for the bot:
```
mkdir teletrans
cd teletrans
```

Create a config.json file in the project directory:

{
    "api_id": "your_telegram_api_id",
    "api_hash": "your_telegram_api_hash",
    "target_config": {},
    "openai": {
        "enable": true,
        "api_key": "your_openai_api_key",
        "url": "https://api.openai.com/v1/chat/completions",
        "model": "gpt-3.5-turbo"
    }
}

api_id and api_hash are required for the Telegram API. You can get them by creating a new application at my.telegram.org.
If openai.enable is set to true, the bot will use the OpenAI API to translate, and this is only effective when the target language is English.

Run the bot with Docker:

docker run -itd --name teletrans -v $(pwd):/app/config --restart=unless-stopped ghcr.io/ihategfw/teletrans:latest

For the first time, you need to execute the following command to log in to your Telegram account:
```
docker exec -it teletrans python teletrans.py /app/config
```
Follow the instructions to log in.

After logging in, please stop the container by pressing Ctrl+C and restart it:
```
docker restart teletrans
```

Usage

Click for usage details

To enable translation from Chinese to English and Japanese, and keep the original message, use the following command in the chat:
```
.tt-on,zh,zh|en|ja
```
The code of languages supported by DeepL API can be found here.
To disable translation in the chat, simply use:
```
.tt-off
```
To enable or disable global translation, use the following command:
```
.tt-on-global,zh,zh|en|ja
.tt-off-global
```
- The chat config is prioritized over the global config.
If you want to send a message without translating it, use the .tt-skip command followed by your message:
```
.tt-skip Hello, this message will not be translated.
```
If you want to translate only this message once, use the following command, making sure to separate the command and the text with a space; this command ignores the .tt-on or .tt-on-global parameter:
```
.tt-once,en,en|zh Hello, I am teletrans bot
```
Edited message is not translated by default. If you need to translate it, insert .tt at the beginning of the message.
```
.tt This edited message will be translated.
```
If you want to translate the message you replied to, use the below command:
```
.tt,zh,zh|en|ja
```

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

License

This project is licensed under the MPL-2.0 License - see the LICENSE file for details.

love4taylor/teletrans