AI Automated Audio Book Generator
This AI automated audio book generator is a solution based on large models (Gemini, CosyVoice2-0.5B) aimed at automatically converting text novels into audiobooks. It is written in Python and requires certain environment configurations (Python 3.10+, API Key, ffmpeg, optional mongodb).
Core Features Include:
- Novel Crawling: Crawl novel content from novel websites.
- Chapter Processing: Obtain chapter lists and content of each chapter, and save them.
- AI Dialogue Information Processing: Use AI to identify dialogues in chapters, distinguish characters, and prepare for audio allocation.
- Character Voice Configuration: Create a character model selection table, specify main character and narrator voices, and randomly assign or use narrator voices for other characters.
- Audio Generation: Generate audio files using multithreading technology.
- Assistance Tools: Provide API Key batch testing, audio file sorting, Ximalaya work batch deletion management, and novel crawling management tools.
Use Cases:
- Personal Audiobook Production: Convert favorite novels into audiobooks for listening anytime and anywhere.
- Batch Audiobook Production: Used for commercial purposes, such as quickly generating audiobooks and uploading them to platforms like Ximalaya.
- Labor Liberation: Reduce the cost of audiobook production, eliminating the need for human voiceovers, requiring only minimal human intervention.
- Content Creation and Experimentation: Used for research and experimentation in AI voice synthesis and content creation.
In summary, this tool aims to simplify the audiobook production process, reduce costs, and improve efficiency through automated workflows and AI technology.