Google has watermarked Gemini's text with SynthID since 2024, on by default in the Gemini app and on the web, with no setting to turn it off. Google's own "ask Gemini" check covers images, video, and audio, but not pasted text. The Gemini SynthID Detector fills that gap: it checks a piece of text for the signal and gives a clear answer, removing any guesswork before you publish it or trust it.
Words limit: 0 / 500
Everything you need to check, verify, and monitor Gemini's SynthID watermark, whether it's a single page or your entire publishing workflow.
One document at a time. Paste in any piece of text, Gemini's or otherwise, and get a transparent read on where it stands. No account setup needed to try it, and no limit on how many times you check the copy before you're confident in the result.
No unclear "it might be AI" language. Every check comes back with a detection score attached, so you're confident instead of eyeballing it and hoping.
Route content through the Watermark Detector API before it hits your CMS, your inbox, or your archive. Built for teams drafting in Gemini who need to check at scale, whether that's verifying your own rewritten content stays clean or screening incoming text at volume, with fast turnaround inside a real production pipeline.
What is Google Gemini SynthID, and can you detect it?
SynthID is not a logo or mark at the corner of an image. As Gemini writes, it scores every possible next word, and SynthID uses a secret key to tilt those scores in a consistent pattern. Nothing is added to the page, no hidden characters and no metadata, so it's invisible and travels with the text through copy and paste. Google designed it to hold up through cropping, a few changed words, and mild paraphrasing, and it marks Gemini app and web output by default.
Google has also published where the signal breaks: detector confidence drops sharply when text is thoroughly rewritten or translated, and the mark is weaker on short, factual answers where Gemini has fewer word choices to play with. Even Google's own detector returns three states, watermarked, not watermarked, or uncertain, rather than a simple yes or no. The Watermark Detector is built around that word-choice signal, not the surface-level style guesses older AI detectors rely on. It reports a clean result: no SynthID found, not proof a human wrote it.
Signal checked
Hidden characters
Result format
Volume
Update cadence
Still have more questions?
Learn more in our support page.
Paste the text into the Gemini SynthID Detector. It checks for SynthID's word-choice signal and returns a detection score, so you know whether the mark is present before you publish the piece or trust it.
Yes. Google has watermarked Gemini's text with SynthID since 2024. It's on by default in the Gemini app and on the web, and there's no setting to turn it off. The mark is a pattern in word choice, not a visible logo, hidden characters, or metadata.
Yes. This tool is built around SynthID's marking method. A clean result means SynthID wasn't found, not that no other model was involved.
No. A missing mark doesn't automatically mean a piece is human-written. Thorough rewriting, translation, and short factual answers can all weaken or break the signal. Google's own detector returns watermarked, not watermarked, or uncertain. This tool reports a clean result as no SynthID found, not as proof of human authorship.
Yes. That's one of the main uses. Run a draft through the detector before it hits your CMS or publish button so you know whether SynthID is still in the text.
A general AI detector guesses from style and phrasing. The Watermark Detector checks for SynthID's actual word-choice pattern and returns a score, rather than a vague "might be AI" label.
Yes. The Gemini SynthID Detector checks text for Google's invisible SynthID mark and returns a detection score on every check.
You can't turn SynthID off in Gemini. The watermark is embedded as the text is generated. Google says detector confidence drops sharply when text is thoroughly rewritten or translated. To strip it, you need a structural rewrite. StealthGPT's Gemini SynthID Remover is built for that.
One person checking one document, a team verifying content before it goes out, or screening submissions at scale, the check works the same way. Enterprise options are available for teams that need it running quietly in the background.
