This project allows you to transform documents into listenable audio tracks. The project is designed to integrate various approaches for document analysis and audio conversion.
Clone the repository
git clone https://github.com/bonfry/erasmos.gitInstall the Python project
cd erasmos
pip install .[cli] # only cli dependencies
pip install .[api] # only api dependencies
pip install .[all] # all dependenciesYou can get a preview of the parsed document
erasmos preview <FILENAME>Or convert it to an mp3 file in the same path as the input file
erasmos convert <FILENAME>You can start the FastAPI server
erasmos-serverThe web APIs expose the following endpoints:
/document/preview: to preview the document/document/convert: to convert the document to audio
The project is currently in a simplified preliminary version. It will be considered an incremental process where features will be added or improved with each version:
- Initial project structure
- Simplified parsing of Markdown documents
- TTS implementation with Google TTS API
- Multilingual support
- Better Markdown nodes parsing