Self-hosted team chat web app in Go that connects to OpenAI, Azure, Claude, Gemini and Ollama models, with user management and rate limiting.
yihong0618/tg_bot_collections
A Python Telegram bot that bundles many AI models and media tools (ChatGPT, Claude, Gemini, ChatTTS, image and video generation) into one chat interface.
- Stars
- 592
- Forks
- 114
- Open issues
- 2
- Last commit
- 17 days ago
What is it?
tg_bot_collections is a set of command-driven Telegram bots written in Python, run as a single process by passing a Telegram bot token. Each feature is triggered by a prefix in chat, such as gemini:, claude:, gpt:, or tts:, and the bot forwards the message to the corresponding service.
The bot connects to hosted LLM providers including Google Gemini, Anthropic Claude, OpenAI ChatGPT, MiniMax, Groq-hosted Llama 3, Together-hosted Qwen, Cohere, lingyiwanwu, and Dify chatbots. It also includes local or media features: ChatTTS text-to-speech, Kling image and video generation, a fake-text image generator, a poster generator built on GitHubPoster, and a Telegraph article publisher. Each service requires its own API key set through environment variables.
Setup involves installing requirements with pip or building a Docker image, then supplying the relevant keys. Individual commands can be turned off with the --disable-command option.
Key features
- 01Chat with ChatGPT, Claude, Gemini, MiniMax, Cohere and other LLMs via command prefixes.
- 02Text-to-speech with ChatTTS.
- 03Image and video generation through Kling.
- 04Poster and pretty-map image generation.
- 05Publish content to Telegraph.
- 06Individual commands can be disabled at startup.
Use cases
- Using several LLM providers from a single Telegram chat without switching apps.
- Self-hosting a personal Telegram bot that relays requests to your own API keys.
- Generating voice, images or video from within Telegram conversations.
Quick start
- 1
Install Python dependencies
pip install -r requirements.txt - 2
Get a Telegram bot token from BotFather
- 3
Set your Google Gemini API key
export GOOGLE_GEMINI_KEY=${your_google_gemini_apikey} - 4
Start the bot with your Telegram token
python tg.py ${telegram_bot_token}
Things to know
- Most AI features need a paid or third-party API key from a specific provider.
- Running the bot as a shell process may break your system config, according to the README's own warning.
In collections
Topics
FAQ
- What is tg_bot_collections?
- A Python Telegram bot that bundles many AI models and media tools (ChatGPT, Claude, Gemini, ChatTTS, image and video generation) into one chat interface. tg_bot_collections is a set of command-driven Telegram bots written in Python, run as a single process by passing a Telegram bot token. Each feature is triggered by a prefix in chat, such as gemini:, claude:, gpt:, or tts:, and the bot forwards the message to the corresponding service.
- Is tg_bot_collections free to use? What license does it have?
- tg_bot_collections is open source under the MIT license. Check the license terms before using it in commercial products.
- Is tg_bot_collections still maintained?
- Actively maintained. The last commit to tg_bot_collections was on Oct 21, 2026.
- What can I use tg_bot_collections for?
- Using several LLM providers from a single Telegram chat without switching apps. Self-hosting a personal Telegram bot that relays requests to your own API keys. Generating voice, images or video from within Telegram conversations.
- How do I install tg_bot_collections?
- Install Python dependencies: pip install -r requirements.txt Get a Telegram bot token from BotFather Set your Google Gemini API key: export GOOGLE_GEMINI_KEY=${your_google_gemini_apikey} Start the bot with your Telegram token: python tg.py ${telegram_bot_token}
- Where can I get tg_bot_collections?
- The source code and installation instructions are on GitHub: https://github.com/yihong0618/tg_bot_collections
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Windows desktop app that sends one prompt to ChatGPT, Gemini, Claude, Grok, DeepSeek and Copilot at the same time.
Self-hosted admin system for integrating many LLM providers (OpenAI, Claude, Gemini, DeepSeek, Qwen and others) behind one unified API.
A Thunderbird add-on that brings ChatGPT, Gemini, Claude or Ollama into your mailbox to reply, proofread, translate, summarize and tag emails.
An Obsidian plugin that finds semantically related notes and excerpts as you write, using a built-in local embedding model.
Open-source Python package that turns websites, PDFs, images, YouTube videos or topics into multilingual audio podcast conversations using GenAI.