README.md

metadata

title: URL to Podcast Generator
emoji: 🎙️
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 3.50.2
app_file: app.py
pinned: false

Gradio Podcast Generator

This project is a Gradio application that generates a podcast episode based on content scraped from a provided URL. It utilizes various components to scrape the content, generate a podcast script, and convert the script into audio format.

Project Structure

gradio-podcast-generator
├── src
│   ├── app.py               # Entry point of the Gradio application
│   ├── scraper.py           # Contains the scraping logic
│   ├── podcast_generator.py  # Generates the podcast episode
│   └── tts.py               # Converts text to speech
├── requirements.txt         # Lists project dependencies
└── README.md                # Project documentation

Setup Instructions

1. Clone the repository:

   git clone https://github.com/yourusername/gradio-podcast-generator.git
   cd gradio-podcast-generator
   

2. Install the required dependencies:

   pip install -r requirements.txt
   

Flask Configuration

The application uses Flask with Gradio integration. Here's how to set it up and run it:

1. Install the requirements:

pip install flask gradio

2. Configure the environment:

export FLASK_APP=app.py
export FLASK_ENV=development  # For development mode

3. Run the application:

python app.py

The server will start on http://0.0.0.0:7860 with the following configuration:

• Host: 0.0.0.0 (accessible from any IP)
• Port: 7860
• Debug mode: Enabled
• Gradio interface: Mounted at root path '/'

Usage

To run the Gradio application, execute the following command in your terminal:

python src/app.py

Once the application is running, you can input a URL into the Gradio interface. The application will scrape the content from the URL, generate a podcast episode, and provide an audio output.

Functionality

• Scraping: The application uses the scraper.py module to extract relevant text from the provided URL.
• Podcast Generation: The podcast_generator.py module utilizes the eva-unit-01/eva-llama-3.33-70b model to create a podcast script that is no longer than 3 minutes.
• Text-to-Speech: The tts.py module converts the generated podcast script into audio using the ElevenLabs TTS API.

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.