Video Description and Voiceover Generator

This Python script processes a video file, generates a compelling description, creates a voiceover script in the style of David Attenborough, and synthesizes the voiceover using OpenAI's Text-to-Speech API.

Features

• Extracts frames from a video file
• Generates a video description using GPT-4 Vision
• Creates a voiceover script in David Attenborough's style
• Synthesizes the voiceover using OpenAI's Text-to-Speech API

Prerequisites

Before running the script, make sure you have the following installed:

• Python 3.x
• OpenCV (opencv-python)
• OpenAI Python library
• Requests library

Clone the Repo:

git clone https://github.com/RaheesAhmed/video_description_generator.git

Navigate to the Directory:

cd video_description_generator

You can install the required libraries using pip:

pip install opencv-python openai requests

Setup

1. Clone this repository or download the script.
2. Set up your OpenAI API key as an environment variable in .env file :

   OPENAI_API_KEY='your-api-key-here'
   

Usage

1. Place your video file in the data directory and name it bison.mp4, or modify the script to use a different file path.
2. Run the script:

   python main.py
   

The script will:

1. Extract frames from the video
2. Generate a video description
3. Create a voiceover script
4. Synthesize the voiceover audio

Output

The script will print:

• The number of frames extracted from the video
• The generated video description
• The voiceover script

The synthesized audio will be available as a binary object, which can be saved to a file or played using appropriate audio libraries.

Note

This script uses OpenAI's GPT-4 Vision model and Text-to-Speech API, which may incur costs. Make sure you're aware of the pricing and your usage limits.