Auto_You (Completely free YouTube Shorts Automation system)

A completely free ($0), cloud-hosted system that generates and uploads YouTube Shorts twice daily using GitHub Actions. Uses YouTube Data API v3 with OAuth refresh tokens (no fragile cookies, lasts[...]

Badges:

How It Works

Step	Component	Service	Cost
Scripts	You provide them	Any AI (ChatGPT/Gemini) in your browser	Free
Voiceover	Microsoft Edge TTS	edge-tts	Free (no API key)
Video clips	Pexels API	requests → Pexels	Free tier
Video composition	MoviePy 1.0.x	ffmpeg + ImageMagick	Free
Upload	YouTube Data API v3	OAuth refresh token (official API)	Free (3,200 of 10,000 daily quota)
Scheduling	GitHub Actions	Cron (2× daily)	Free (2000+ min/month)

Project Structure

.
├── main.py                       # Orchestrator — runs the 5-stage pipeline
├── auth_setup.py                 # One-time local script to get OAuth tokens
├── requirements.txt              # Python dependencies
├── SETUP-GUIDE.txt               # Step-by-step setup instructions
├── README.md                     # This file
├── scripts/
│   └── scripts.json              # Pre-generated scripts (you provide these)
├── src/
│   ├── __init__.py
│   ├── reader.py                 # Reads scripts.json, picks next unused script
│   ├── audio.py                  # edge-tts → MP3 voiceover
│   ├── downloader.py             # Pexels API → video clips
│   ├── editor.py                 # MoviePy → 9:16 video, subtitles, composition
│   └── uploader.py               # YouTube Data API v3 (OAuth) upload
└── .github/workflows/
    └── schedule.yml              # GitHub Actions: cron schedule + env config

Required Secrets

Secret	Description
PEXELS_API_KEY	Pexels API key (free at pexels.com/api)
YT_REFRESH_TOKEN	YouTube OAuth refresh token (get via auth_setup.py)
YT_CLIENT_ID	Google Cloud OAuth client ID
YT_CLIENT_SECRET	Google Cloud OAuth client secret

One-Time Setup

1. Google Cloud Console — create project → enable YouTube Data API v3 → create OAuth 2.0 Desktop credentials
2. Run auth_setup.py locally — paste client ID & secret → sign in to Google → get refresh token
3. Add 4 GitHub Secrets — PEXELS_API_KEY, YT_REFRESH_TOKEN, YT_CLIENT_ID, YT_CLIENT_SECRET
4. Generate scripts — copy the prompt from SETUP-GUIDE.txt → paste to ChatGPT/Gemini → save output as scripts/scripts.json
5. Run workflow — go to Actions → "Run workflow"

Detailed instructions: read SETUP-GUIDE.txt

Script Format (scripts/scripts.json)

[
  {
    "id": 1,
    "title": "Catchy title under 100 chars",
    "description": "Description with hashtags",
    "tags": ["tag1", "tag2"],
    "voiceover_script": "Script under 150 words (~50 seconds)",
    "visual_keywords": ["kw1", "kw2", "kw3", "kw4", "kw5"],
    "used": false
  }
]

Pipeline (5 Stages)

1. read — ScriptReader picks the first unused script, marks it used, pushes back
2. audio — edge-tts converts script to MP3, returns duration
3. download — Pexels searched per keyword; 4-5 portrait clips streamed
4. compose — MoviePy crops to 1080×1920, concatenates, adds subtitles, renders with ultrafast/threads=2
5. upload — Gets fresh access token from refresh token → uploads via YouTube Data API v3

When all scripts are used → prints "All N scripts used. Generate fresh ones." and exits cleanly.

Why OAuth Instead Of Cookies

	Cookies (old)	OAuth Refresh Token (new)
Lifespan	Days to weeks	Years (until revoked)
GitHub setup	Playwright + Chromium (~300MB)	Zero browser deps
Upload method	Browser automation (fragile UI)	Official API (never breaks)
Maintenance	Re-export cookies every few days	Set up once, forget forever
Quota	Unlimited (but unreliable)	10,000 units/day (3,200 used)
Speed	~15 min total	~10 min (no browser launch)

Dependencies

edge-tts>=6.1.0               # Microsoft Edge TTS
moviepy>=1.0.3,<2.0.0         # Video editing
Pillow>=10.0.0                # Image processing
requests>=2.31.0              # HTTP client for Pexels + YouTube API
google-auth>=2.0.0            # OAuth token refresh