Novel Glossary Extractor
Extract recurring names, titles, places, sects, and techniques from EPUB and TXT files so your translation glossary starts clean.
Drag and drop or click to upload
Supports EPUB and TXT files up to 30MB
Why glossary extraction matters before translation
Long novels break down when names drift. A character appears as one spelling in chapter 6, another in chapter 27, and a third in the final arc. Sect names, move names, and place names drift the same way. A glossary extractor solves that before the translation starts.
Upload an EPUB or TXT file and the tool scans for recurring proper nouns, titles, places, sects, and techniques. Instead of discovering inconsistencies after a full translation run, you begin with a cleaner glossary candidate list that can be reviewed and reused.
Best use cases
This is especially useful for web novels, light novels, wuxia, xianxia, and fan-translated files where recurring terminology matters. It works well with messy source files because the extractor focuses on repeated terms and context, not perfect formatting.
Once the glossary is ready, import it into your translation workflow so the same character, sect, or skill stays stable from the first chapter to the last.