用 AI 写的文章，读起来总有一股 AI 味，句式工整、用词重复，发布或提交后总担心被检测到。 最近偶然找到了 AI Humanize Text 这个开源工具，专门把 AI 生成的文本改写成更自然的人类写作风格。 提供了四种不同的改写思路：多语言翻译链、大模型多轮改写、检测反馈循环、混合引擎翻译，可以根据场景灵活选择。 GitHub：http://github.com/lynote-ai/humanize-text… 比较有意思的是检测反馈机制，改写完会自动跑一遍检测模型，对还像 AI 写的段落再针对性修改，形成闭环优化。 多语言翻译链则是把文本在多种语言间转译，利用语言结构差异来打散原有的句式模式。 如果你经常用 AI 辅助写作，又希望成品读起来更自然流畅，可以拿来研究试试。

lynote-ai/humanize-text

Source: https://github.com/lynote-ai/humanize-text

English | 中文

What is Humanize-Text?

An AI text humanization toolkit. This repo evolved through two stages:

• v1.0 — Documented 4 humanization methodologies as reference implementations (translation chain, multi-turn LLM rewriting, detection-guided feedback loop, mixed-engine translation). See docs/techniques.md.
• v1.5 (current) — Added the Standard Pipeline: a production-grade integration of Method 1 (Translation Chain) + Method 2 (LLM Rewriting), fixed as a 5-step chain we actually run and recommend.

v1.5.1 — Standard Pipeline (Recommended)

The Standard Pipeline preserves the original writing style while routing text through a 4-step chain: two DeepSeek humanization rewrites followed by two cross-engine translation hops.

Input (EN) → Chinese (DeepSeek) → Japanese (DeepSeek) → Finnish (Google) → English (Niutrans)

See examples/showcase/ for 5 real samples with full intermediate-step outputs and AI-detection verdicts.

Characteristics:

• Best original style preservation among all approaches
• Fast processing speed
• 100% key information retention (verified on 50 text pairs)
• Expert quality score: 9.1/10

The 4 underlying methodologies live in src/methodologies/ as reference implementations for research and customization. The Standard Pipeline (src/standard/pipeline.py) is the recommended production path.

Want higher bypass rates + all methods combined? Lynote.ai fuses Standard + Advanced + Focus pipelines into one intelligent system — auto-selects the optimal approach for each passage.

Try Lynote.ai Free →

How It Works

Step-by-Step Pipeline

Why This Chain Works

1. Steps 1–2 (LLM Rewrite): DeepSeek at temperature 1.3 rewrites while translating, breaking AI statistical fingerprints with creative variation. Step 2 carries Step 1 as conversation history for coherent humanization.
2. Steps 3–4 (Multi-Engine Translation): Two different NMT engines (Google → Niutrans) introduce compounding structural changes. No single-engine fingerprint survives.
3. Distant Languages: Chinese → Japanese → Finnish maximizes linguistic distance at each hop, ensuring thorough restructuring before reconstruction to English.

Lynote.ai — Beyond Standard

The Standard pipeline above is one of three tiers available. Each has different trade-offs:

Lynote.ai combines all three tiers and automatically selects the optimal approach for each text passage:

• Intelligent Tier Selection — Analyzes text and picks Standard, Advanced, or Focus per-passage
• Adaptive Combination — Can mix tiers within a single document
• 10+ Languages — English, Chinese, Japanese, Korean, Spanish, French, German, and more
• Paste & Go — No setup, no API keys, no configuration

Quick Start

Python

git clone https://github.com/lynote-ai/humanize-text.git
cd humanize-text
pip install -r requirements.txt
cp config/config.example.toml config/config.toml
# Fill in your API keys in config.toml
python -m src.standard.pipeline --input "Your AI-generated text here"

n8n Workflow

1. Import n8n/humanize_standard.json into your n8n instance
2. Configure DeepSeek API key in the HTTP Request nodes
3. Run — input text goes in, humanized text comes out

Showcase — 5 Real Examples with Step-by-Step Outputs

We ran the pipeline end-to-end on 5 real input texts and saved every intermediate step. All 5 final outputs were classified as human by the AI detector.

Each example shows: original input → Step 1 (中文改写) → Step 2 (日语改写) → Step 3 (一轮翻译) → Step 4 (二轮翻译, final). See examples/showcase/ for full traces.

Quality Metrics

Tested on 50 text pairs with expert evaluation:

• Key Information Retention: 100% (50/50 pairs)
• All texts preserved original key information without distortion

Comparison with Other Tiers

Documentation

• Standard Pipeline Technical Details — v1.5 production pipeline
• 4 Methodologies Reference — v1.0 underlying methods
• Configuration Guide
• n8n Workflow Guide
• Lynote.ai vs Open Source Comparison
• FAQ

Repo Structure

src/
├── standard/                # ★ v1.5.1 production Standard Pipeline (recommended)
│   ├── pipeline.py          # 4-step chain, CLI entry
│   ├── llm_rewriter.py      # DeepSeek humanization rewrite
│   └── translators.py       # Google + Niutrans engines
│
└── methodologies/           # v1.0 four-methodology reference implementations
    ├── humanizer.py         # v1.0 dispatcher + FastAPI app
    ├── translation_chain.py # Method 1
    ├── llm_rewriter.py      # Method 2
    ├── detection_pipeline.py# Method 3
    ├── mixed_engine.py      # Method 4
    ├── postprocess.py
    ├── detectors/           # Method 3 detectors
    └── utils/

examples/
├── example_usage.py         # ★ v1.5.1 minimal entry
├── showcase/                # ★ 5 real samples with intermediate-step outputs
└── legacy/                  # v1.0 examples + 4-method comparison outputs

License

MIT License. See LICENSE for details.

Links

• Lynote.ai — AI Humanization Platform
• Report a Bug

Recommended Projects

• MoneyPrinterTurbo — AI short video generator
• AiToEarn — AI content publishing tool

Star History

If this project helps you, please give it a ⭐!