Podcast TTS Generator

Overview

The Podcast TTS Generator is a Python application that automates the process of generating text-to-speech output for podcasts. It takes prompts from text files, generates detailed outlines using the ChatGPT API, creates scripts from those outlines, and finally synthesizes speech to produce audio files.

Project Structure

podcast-tts-generator
├── src
│   ├── main.py               # Entry point of the application
│   ├── chatgpt_api.py        # Functions to interact with the ChatGPT API
│   ├── outline_generator.py    # Class to create outlines from prompts
│   ├── script_creator.py      # Class to generate scripts from outlines
│   ├── tts_engine.py          # Class to synthesize speech from scripts
│   └── utils.py               # Utility functions for file handling
├── prompts
│   └── sample_prompt.txt      # Sample text prompt for testing
├── outputs
│   ├── outlines               # Directory for generated outlines
│   ├── scripts                # Directory for generated scripts
│   └── audio                  # Directory for generated audio files
├── requirements.txt           # Project dependencies
└── README.md                  # Project documentation

Installation

Clone the repository:

git clone <repository-url>
cd podcast-tts-generator

Install the required dependencies:
```
pip install -r requirements.txt
```

Usage

Place your text prompts in the prompts directory. You can use the provided sample_prompt.txt as a template.
Run the application:
```
python src/main.py
```
The generated outlines, scripts, and audio files will be saved in the respective directories under outputs.

Contributing

Contributions are welcome! Please feel free to submit a pull request or open an issue for any enhancements or bug fixes.

License

This project is licensed under the MIT License. See the LICENSE file for more details.

2.0 KiB Raw Permalink Blame History