korcarc/text-humanizer
text-humanizer is an open-source project designed to convert text generated by AI to its "humanized" version. Bypasses the most of AI detectors such as Turnitin or GPTZero
What it solves
It addresses the issue of AI-generated text being easily detectable by AI-detectors and often lacking natural linguistic variety. The project aims to make AI text feel more human-like while preserving the original meaning.
How it works
The system uses a multi-stage rewriting pipeline to introduce structural and linguistic variation:
- LLM Rewrite: Uses DeepSeek to rewrite the text and translate it into Chinese as an intermediate step to break original patterns.
- Google Translation: Translates the text into Turkish to introduce further syntactic distortion.
- DeepL Translation (Optional): Translates the Turkish text into Japanese for additional diversity.
- Final Reconstruction: Uses DeepSeek to translate the text back into the original language, removing translation artifacts and restoring natural flow.
Who it’s for
Users who want to rewrite AI-generated content to bypass AI detectors and improve the naturalness and stylistic diversity of their text across eight different languages.
Highlights
- Supports 8 languages including English, Japanese, Chinese, Korean, German, French, and Spanish.
- Combines multiple translation engines (DeepSeek, Google Translate, and optionally DeepL) to distort and then reconstruct text.
- Fully open-source and free.
- Configurable parameters for temperature and model selection.
Related
- Project
- Project
- Project
- Project