TikTok Video Generator

Automated video generation pipeline that creates TikTok-style videos from topics using AI.

Features

• Content Generation: GPT-4 creates slide content and captions
• Image Generation: DALL-E 3 generates vertical TikTok images
• Narration: ElevenLabs text-to-speech for voiceovers
• Video Assembly: MoviePy combines images, text, and audio
• Data Sources: CSV files or Airtable integration
• Automation: Webhooks and scheduling for batch processing

Setup

1. Install dependencies:

pip install -r requirements.txt

2. Configure environment variables:

cp .env.example .env
# Edit .env with your API keys

3. Create output directories:

mkdir -p output/{images,audio,videos}

Usage

Single Video Generation

python main.py --topic "5 Amazing Space Facts"

Batch Processing from CSV

python main.py --batch --source csv --csv-path topics.csv --limit 3

Batch Processing from Airtable

python main.py --batch --source airtable --limit 5

Custom Voice

python main.py --topic "Your Topic" --voice-id "your_elevenlabs_voice_id"

Automation

Make.com Webhook

cd automation
python make_webhook.py

Webhook endpoint: http://localhost:5000/generate-video

Scheduled Generation

python automation/scheduler.py

Configuration

Edit config.py to customize:

• Video settings (duration, FPS, dimensions)
• Output directories
• Default voice settings

API Keys Required

• OpenAI API key (GPT-4 + DALL-E 3)
• ElevenLabs API key (text-to-speech)
• Airtable API key (optional, for Airtable integration)

Output Structure

output/
├── images/
│   └── {video_id}/
│       ├── slide_1.png
│       └── slide_2.png
├── audio/
│   └── {video_id}_narration.mp3
├── videos/
│   └── {video_id}.mp4
└── {video_id}_manifest.json