Free Claude text cleaner
Claude Watermark Remover
Clean the formatting Claude leaves in copied text, and get a straight answer about what Anthropic's new watermark is and what removes it.
- Nothing uploaded
- Cleans as you type
- Free, no sign-up
Watermark check
- Hidden-character marks
- Paste text to check
- AI citation and link tags
- —
- Formatting fingerprints
- —
- Statistical watermark
- Claude (models since August 2026), ChatGPT in the EU (from October 2026) and Gemini mark text through word choice. It cannot be seen, and cleaning characters does not change it. Rewriting the wording does.
Cleaning options
Invisible characters
- Hidden characters
Zero-width spaces and joiners, byte order marks, soft hyphens, direction marks, tag characters.
- Special spaces
No-break, narrow no-break and other odd spaces become normal spaces.
AI leftovers
- AI citations and link tags
ChatGPT citation leftovers and utm_source=chatgpt.com on links.
- Numbered citations
Markers like [1] or [2, 3]. Off by default, since essays use them too.
Formatting fingerprints
- Markdown
Asterisks, # headings, tables, code fences and LaTeX math.
- Em and en dashes
Replaced with a hyphen or a comma.
- Curly quotes
“ ” ‘ ’ become straight quotes.
- Ellipsis character
The single … character becomes three dots.
- Spacing
Double spaces, trailing spaces and extra blank lines.
Advanced
- Fancy letters
Fullwidth, ligature and bold-math letters become plain letters.
- Lookalike letters
Cyrillic and Greek letters hiding inside English words.
- Emoji
Removes emoji such as 🚀 and ✅.
Claude's watermark, explained
Anthropic announced on August 11, 2026 that every Claude model released on or after August 2, 2026 marks the text it writes. The mark applies in every Claude product, including the API and Claude Code, in every country, and there is no setting to turn it off. Anthropic says it will extend the mark to older models too. Images Claude creates carry signed C2PA content credentials instead.
The text mark is statistical. When several words would fit equally well, a secret key steers which one the model picks. You cannot see it, and because it is the words themselves, it travels through copy and paste. Anthropic says it may survive some editing, and it has not released a public detector yet.
What this tool removes from Claude text
Claude rarely leaves hidden characters of its own. It does leave formatting that gives copied text away:
- Markdown. ## headings, **bold** labels and bullet lists that arrive in Google Docs as raw symbols.
- Em dashes. Claude reaches for them often, and readers have noticed.
- Curly quotes and apostrophes. Typographic quotes that differ from what a keyboard types.
- Stray invisible characters. Text that passed through a web page, a PDF or another app can pick up zero-width or no-break spaces on the way. The cleaner removes those too.
Can you remove Claude's watermark?
Not with a remover. There is no character to delete, so a cleaner, including this one, leaves the watermark in place. The only thing that changes it is changing the words, through real editing, translation or a rewrite. We built the Humanizer for rewriting, but we will not promise it beats a watermark that nobody outside Anthropic can test.
How to clean Claude text
Paste your text.
Copy from ChatGPT, Claude, Gemini, a PDF or a web page and paste it into the box. It is cleaned as you type.
Check what changed.
Open What changed to see every hidden character tagged where it was, plus the dashes, quotes and markdown that were fixed.
Pick your options.
Keep em dashes or turn them into commas, keep link URLs, or remove only the invisible characters.
Copy it out.
Copy plain text, or use Copy for Google Docs to paste headings, bold and lists as real formatting instead of symbols.
Writing in Google Docs?
Write It types, humanizes and checks your writing inside Google Docs, Slides and Word. Install the extension to try it free.