Neill-Erasmus/pdf-to-audiobook

A python script that generates a short story and saves it in PDF format, before rendering an audio version and saving it as an MP3 file.

PDF to Audiobook

Table of Contents

• Introduction
• Prerequisites
• Setup
• Usage
• Output
• Notes
• Contributing
• License

Introduction

This Python script empowers you to transform short stories into engaging audiobooks effortlessly. Leveraging the capabilities of OpenAI's GPT-3 and TTS-1 models, the converter not only generates captivating short stories but also converts them into beautifully formatted PDFs and narrates them in audio format.

Prerequisites

• OpenAI API Key
• Python 3 installed on your system

Setup

Follow these simple steps to set up and run the PDF to Audiobook Convertor:

1. Clone the Repository

   git clone https://github.com/your-username/pdf-to-audiobook.git
   

2. Navigate to the Project Directory:

   cd pdf-to-audiobook
   

3. Install Required Packages:

   pip install -r requirements.txt
   

4. Set OpenAI API Key:

   export OPENAI_API_KEY="your-api-key"
   

Usage

Running the script is straighforward. Follow these steps:

1. Execute the main script:

   python main.py
   

2. Respond to the prompt:
   • To generate a new story, PDF, and audiobook, type "Y".
   • To convert an existing PDF to an audiobook, type "N" and provide the PDF filename.

Output

• PDF: The generated PDF is saved in the output/ directory.
• Audiobook (MP3): The audio rendition is saved in the output/ directory.

Notes

• The generated story is limited to 4000 characters.
• Ensure the input PDF is in the root directory and spelled correctly.

Contributing

Currently, contributions are not accepted for this project.

License

This project is licensed under the MIT License - see the LICENSE file for details.