gemini-youtube-automation
A fully autonomous AI Agent/Python pipeline that utilizes Large Language Models (LLMs) like Gemini to generate content, produce videos, and automatically upload
What is gemini-youtube-automation?
A fully autonomous AI Agent/Python pipeline that utilizes Large Language Models (LLMs) like Gemini to generate content, produce videos, and automatically upload educational videos to YouTube.
Overview of gemini-youtube-automation
What it is
Gemini YouTube Automation is a fully autonomous AI agent and Python pipeline that uses Large Language Models (LLMs) like Gemini to generate content, produce videos, and automatically upload educational videos to YouTube. It runs entirely on GitHub Actions with zero human input required.
Key features
- Zero-touch operation — fully autonomous, runs on a cron schedule
- Dual-format output — long-form lesson video AND a YouTube Short per day
- AI-generated curriculum — Gemini creates and extends the course plan automatically
- Dynamic visuals — Pexels stock imagery matched to each slide topic
- Professional audio — per-slide narration with soft background music
- Custom thumbnails — auto-generated for every video
- Self-updating repo — content plan committed back after each successful run
- GitHub Actions native — no server, no hosting cost, just free CI runners
Use cases
This pipeline is designed for creating and uploading daily educational YouTube videos automatically. It can be used to produce a structured course series (e.g., “AI for Developers”) covering topics like Generative AI, LLMs, Prompt Engineering, RAG, Vector Databases, LangGraph, Fine-tuning, and Computer Vision.
Getting started
bashgit clone https://github.com/ChaitanyaEswarRajeshJakki/gemini-youtube-automation.gitcd gemini-youtube-automationpip install -r requirements.txtConfigure GitHub Secrets: GOOGLE_API_KEY, PEXELS_API_KEY, CLIENT_SECRET_B64, CREDENTIALS_B64. Then run locally with python main.py.
License and pricing
MIT License. See LICENSE for details.
Based on the project's public README and repository metadata.