Guide

How to remove a SynthID watermark

SynthID-Text is Google DeepMind’s watermark for AI-generated text, applied to text from the Gemini app and web. The idea went mainstream in 2026, when Anthropic and OpenAI shipped their own statistical watermarks for Claude and ChatGPT. Here’s how the SynthID watermark works, why it’s hard to remove by editing, and how to strip it properly. You can do it free with the Unmark homepage scanner.

Updated .

How it works

When a language model writes, it repeatedly samples the next word from a probability distribution. SynthID nudges that sampling with a secret pseudo-random key so the chosen words follow a subtle statistical pattern across the whole passage. Nothing is visibly different — the text reads normally — but a detector holding the key can measure the pattern and estimate whether the text was machine-generated. Because the mark lives in the sequence of word choices, it doesn’t rely on hidden characters or metadata.

Google’s own documentation notes that detector confidence can drop sharply when text is thoroughly rewritten or translated, and that the watermark is weaker on factual answers, where the model has less freedom to vary its wording. Google’s SynthID Detector checks images, video and audio — not text.

Why editing a few words doesn’t remove it

The watermark is distributed, not localized. Swapping a word here and there, fixing punctuation, or trimming a sentence leaves most of the pattern intact — often enough for a detector to still flag it. The only reliable way to remove a statistical watermark is to change enough of the token sequence that the pattern no longer holds, i.e. a genuine rewrite.

We measured it. In our test of 120 passages watermarked with the open-source SynthID-Text, swapping 10% of the words for synonyms left 92% still detectable; after Unmark’s default rewrite, 3% were.

How to remove it

  1. Paste the text into the Unmark homepage scanner.
  2. Choose a rewrite strength and remove the watermark. Unmark rewrites the wording to disrupt the statistical pattern while preserving your meaning, and strips any invisible characters in the same pass.
  3. Copy the clean text and re-read it to confirm the meaning is intact.

A realistic expectation

Rewriting substantially degrades SynthID and other detector signals, and heavier rewrites degrade them more — but no tool can guarantee text is permanently undetectable against every detector. Treat watermark removal as best-effort, and always review the result.

Remove a SynthID watermark now

60 free rewrites an hour, no sign-up.

Open the homepage scanner

FAQ

What is a SynthID text watermark?+
SynthID-Text is a watermark from Google DeepMind that changes how a model samples its words, so the output follows a statistical pattern a detector can measure — without any visible change to the text.
How does the SynthID watermark work?+
When Gemini writes, SynthID nudges each next-word choice with a secret key. The pattern is spread across the whole passage. Nothing looks different on screen; a detector that holds the key can still measure it. There are no hidden characters to strip.
Can you remove SynthID by paraphrasing a little?+
Small edits usually aren't enough — the pattern is spread across the whole passage. In our test, 92% of watermarked passages were still detected after 10% of their words were swapped for synonyms. A thorough rewrite that changes the token sequence is what removes it.
Does Claude or ChatGPT use SynthID?+
No — each has its own watermark built on the same idea. Anthropic watermarks text from Claude models launched since August 2, 2026, and OpenAI's textGrain is rolling out to ChatGPT text in the EU. Both live in word choice like SynthID, so the removal approach is the same: rewrite the text.
Can I check whether text has a SynthID watermark?+
Not with a public tool. Google's SynthID Detector checks images, video and audio; text detection needs the watermarking key, which Google keeps private.
Does Unmark guarantee SynthID is gone?+
No. Rewriting substantially degrades SynthID and other detector signals, and heavier rewrites degrade them more — but no tool can promise text is permanently undetectable. Treat Unmark as best-effort and always re-read the result.
Is removing a SynthID watermark free?+
Yes — Unmark gives you 60 free rewrites an hour with no sign-up. Paste text into the homepage scanner to rewrite and strip any invisible characters in the same pass.