PDF to Speech Converter

A command-line tool that converts PDF documents to speech (an audio file) using Google Document AI and OpenAI's Text-to-Speech API.

(I use this for my book club)

Features

• Convert PDF files to text using Google Document AI
• Convert text to speech using OpenAI's TTS API
• Support for multiple voice models
• Handles large PDF documents by splitting them into manageable chunks
• Configurable through YAML configuration file

Prerequisites

• Python 3.8 or higher
• Google Cloud account with Document AI API enabled
• OpenAI API key
• Required Python packages (see requirements.txt)

Installation

1. Clone the repository:

git clone https://gitlab.com/anuna/pdf-to-speech
cd pdf-to-speech

2. Install required packages:

pip install -r requirements.txt

3. Set up configuration:
   • Copy config.yaml.example to config.yaml
   • Add your API keys and configuration details

Configuration

You can configure the tool either through environment variables or the config.yaml file:

1. Copy the example configuration file:

   cp config.yaml.example config.yaml
   

2. Edit config.yaml and add your:

   • Google Cloud credentials file path
   • OpenAI API key
   • Any other custom settings

3. Required minimum configuration:

   api:
     google:
       credentials_path: "/path/to/your/credentials.json"
     openai:
       api_key: "your-openai-api-key"
   
   

Environment Variables:

export GOOGLE_APPLICATION_CREDENTIALS="/path/to/credentials.json"
export OPENAI_API_KEY="your-openai-api-key"

Config File:

Update the config.yaml file with your API keys and preferences.

Usage

Basic usage:

python pdf-to-speech.py -i input.pdf -o output.mp3 -v nova

Options:

• -i, --input: Input PDF file path (required)
• -o, --output: Output audio file path (required)
• -v, --voice: Voice model to use (optional, defaults to 'nova')

Available voice models:

• alloy
• echo
• fable
• nova
• onyx
• shimmer

Examples

Convert a PDF using the default voice:

python pdf_to_speech.py -i documents/sample.pdf -o audio/output.mp3

Convert using a specific voice model:

python pdf_to_speech.py -i documents/sample.pdf -o audio/output.mp3 -v shimmer

License

Apache License Version 2.0

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request