Auto-Audio-Book is a Python 3.10+ open source project created by developer zqq-nuli and hosted on the GitHub platform. The tool through the integration of large model technology (such as Gemini and CosyVoice2-0.5B) , to achieve the complete process from the network to crawl the novel content to generate multi-character audiobook . The project code is completely public, allowing users to download and modify it freely, making it especially suitable for technology enthusiasts and audiobook producers.
The core architecture contains five key technology modules: 1) a web crawler system based on the requests library; 2) a dialog analysis engine using NLP technology; 3) a multi-role speech synthesis interface; 4) an audio processing system based on ffmpeg; and 5) optional MongoDB database support. This modular design makes the project highly scalable and developers can easily replace the components in it.
As of the latest version (0.5B) in March 2025, the project is still in the development phase and the GUI is not yet complete, but it is possible to complete the entire workflow from crawling to generation via the command line. Typical runtime environments require Python 3.10+, ffmpeg audio tools, and the appropriate Big Model API keys, which are specified in the project documentation.
This answer comes from the articleTool to automatically crawl novels and generate multi-character audiobooksThe
