This project transforms any URL into a podcast, specifically targeting the Xiaoyuzhou platform, offering a Chinese alternative to Google's NotebookLM. It's designed for users who want to consume web content in an audio format, making information more accessible and portable.

How It Works

The system comprises several Python scripts: api.py handles web and API services, server.py manages the core text-to-speech (TTS) and podcast generation tasks asynchronously, and server_pro.py adds automatic publishing to Xiaoyuzhou. It utilizes a configuration file (config.py) for LLM and TTS service details, requiring FFmpeg to be installed and added to the system's PATH.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt
• Run API service: python api.py
• Run backend service: python server.py (or server_pro.py for auto-publishing)
• Requires Python 3.11.5 (recommended), FFmpeg installed and in PATH.
• Access the service at http://127.0.0.1:8811/.

Highlighted Details

• Converts web URLs into audio podcasts.
• Supports automatic publishing to the Xiaoyuzhou platform (via server_pro.py).
• Provides UI for homepage, synthesis records, and record deletion.

Maintenance & Community

Contact: ceo@tingwu.co, https://tingwu.co

Licensing & Compatibility

The license is not specified in the README. Compatibility for commercial use or closed-source linking is not detailed.

Limitations & Caveats

The project is described as a "Chinese version" and may have limited support for non-Chinese content or platforms. Specific LLM and TTS model configurations are required via config.py, implying potential complexity in setup depending on the chosen services.