🎬 Automatic Story Video Generator

An advanced Python application that automatically creates a complete video story from a single topic. It supports multiple content sources, AI-generated text and images, natural-sounding voiceovers, subtitles, and background music — all combined into a polished final video.

---

✨ Features

• Multiple Content Sources Create videos from:

  • Wikipedia pages
  • Custom topics written by Gemini
  • Your own text

• Flexible Video Formats

  • YouTube Shorts (9:16 vertical)
  • Long Videos (16:9 horizontal)

• AI-Powered Production

  • Text & Summarization (Gemini): Transforms content into a fluent voiceover script.
  • Image Generation (Gemini): Creates custom, context-aware images for each scene.
  • Natural Voiceover (OpenAI TTS): High-quality, human-like narration.
  • Multi-Language Support: Auto-generates multiple language versions with synchronized .srt subtitles.

• Intelligent Music Selection Detects story atmosphere and picks the most fitting track from your music folder.

• Post-Production Tools

  • Automatic Turkish Dubbing for existing videos.
  • Centralized configuration with config.json.

---

📂 Project Structure

Automatic-Story-Video-Generator/
│
├── main.py                # Entry point, orchestrates the workflow
├── config_handler.py      # Handles config.json creation & updates
├── ui_handler.py          # User interface interactions (menus, inputs)
├── content_handler.py     # Fetches text (Wikipedia, Gemini, custom)
├── get_wikipedia.py       # Wikipedia content fetcher with fallback
├── summarize_gemini.py    # Summarization, translation, and script writing
├── image_handler.py       # Image prompt generation & creation
├── text_to_speech_openai.py  # Voiceover generation (OpenAI TTS)
├── video_creator.py       # Combines audio, visuals & subtitles
├── dubber.py              # Turkish dubbing for existing videos
├── music_adder.py         # Intelligent background music adder
├── music/                 # Folder containing .mp3/.wav background tracks
├── requirements.txt       # Project dependencies
└── README.md              # Documentation

---

🚀 Setup and Usage

1. Installation

Create Virtual Environment (recommended):

python -m venv venv
source venv/bin/activate   # macOS/Linux
.\venv\Scripts\activate    # Windows

Install Dependencies:

pip install -r requirements.txt

---

2. Configuration

• .env File Create a .env file in the project root with your API keys:

  GEMINI_API_KEY="AIzaSy..."
  OPENAI_API_KEY="sk-..."

• Music Folder Add .mp3 or .wav files into a music/ folder.

• Config File On the first run, a config.json will be generated automatically. Edit it to adjust settings (output folders, model names, voices, etc.).

---

3. Running the Application

Run the program with:

python main.py

Follow the on-screen menus to create your story video.

---

📌 Notes

• Works with multiple languages.
• Supports both short-form and long-form video creation.
• Easily extensible for new AI models and video formats.

---

📜 License

This project is for educational and personal use. Please check licenses of APIs, images, and music before distributing generated content.