Watermark Remover for AI Content
Future Claude models will mark their output with SynthID-Text. Nothing is added. Light edits usually keep the pattern. A rewrite does not.
Paste the text, or drop an image or document. Continuing needs an account and a plan. See how it works.
or type below, or drop a file
Inspected in your browser. A plan is required to finish.
01
Paste
Drop text or a file. Nothing is uploaded until you continue.
02
Inspect here
Your browser reports invisible characters and a style heuristic. Claude’s mark will not appear — it lives in word choice.
03
Rewrite on our machines
A plan spends a credit to rewrite the prose, or to strip metadata from a file.
01
What a rewrite can change
SynthID-Text derives each random number from a secret key and the words so far. Choosing different words breaks that trail. We cannot see Anthropic’s key, so we cannot certify their detector.
- Light edits usually keep the signal. Replacing the wording does not — though the prose will change.
- Short text, code, and tightly factual passages have fewer forks, so the mark is weaker there to begin with.
- A hit only means Claude was likely involved. It does not prove human authorship, and it says nothing about another model.
- Images and documents are a different mark: Claude attaches a C2PA credential in metadata. Drop the file in the tool above to see what is riding along, then continue to strip it.
Anthropic published the method on 14 August 2026. Other major providers who signed the same Code of Practice will ship their own versions. Read Anthropic’s explanation.
A plan covers the rewrite
Disturbing a statistical watermark means calling a model. One credit is one rewrite candidate, or one file cleaned of C2PA and other metadata.
02
What this cannot promise
A watermark check is evidence that Claude was likely involved. Rewriting changes the words. Presenting either as proof of human authorship would be dishonest.
- Rewriting the prose does not mean the content was never AI-assisted.
- No tool can certify that rewritten text will fail Anthropic’s detector. SynthID-Text uses a private key; we cannot see it, and anyone claiming otherwise is guessing.
- C2PA soft binding survives a metadata strip — it can re-link to a remote manifest.
- Pixel-embedded image watermarks are out of scope. Audio and video are not supported at all.
Use it on content you own or are authorised to process, and keep any disclosure the law or a platform requires. Terms.