Questions and straight answers
Including the ones where the answer is "you cannot do that, and neither can anybody else".
The basics
- Is checking really free?
- Yes. You see the whole report: every hidden character, what it is called, how many there are, where it sits. Five texts and two images a day, with no account. You only pay if you want the clean copy.
- Why is the removal the paid part?
- Because nobody should have to pay to find out whether they have a problem. If we charged for the check, you would be paying for a number you cannot verify. This way you see the evidence first, and people whose text turns out to be clean pay nothing.
- Does ChatGPT put invisible characters in text?
- OpenAI has never said it does it on purpose. But ChatGPT text very often arrives with invisible characters in it anyway: odd spaces, zero-width characters, narrow no-break spaces picked up while formatting. On purpose or not, they are in your document. They survive copy and paste, and anyone looking will find them. We show you which ones are there instead of guessing why.
- Does Gemini watermark its text?
- Yes, with SynthID, but not with hidden characters. SynthID for text works by nudging which words the model picks, so the watermark is the word order itself. No character-removal tool can find or remove that, including this one. Reading it needs Google's key. Gemini text can carry hidden characters on top of that, and those we do remove. Be very sceptical of anyone selling SynthID removal for text.
- Will this get me past my university's AI detector?
- Probably not, and we would rather say so than sell you a promise. Turnitin and tools like it mostly look at writing style, not hidden characters, so taking the characters out usually will not change their answer. What we do is tell you exactly what is in your file. That is real, checkable information about your own document. It is not a detector bypass, and anything advertised as one is overselling.
- Is it safe to paste my essay here?
- Your text is read in memory and thrown away when we answer. We do not write it to disk, we do not log it, and we do not train anything on it. The only thing we keep is a salted hash used to count your free checks, and it cannot be turned back into an IP address. If you would rather not send it at all, the whole method is written out on the How it works page.
- What is C2PA, and why is it in my image?
- C2PA, also called Content Credentials, is a signed record inside an image file saying what made it. Most big image generators now add one automatically. It survives uploads and downloads, and usually re-saving too. Anyone can read it with a free verifier. We take it out along with EXIF and XMP, without re-encoding your picture, so nothing about the image itself changes.
- Can you remove SynthID from an image?
- No, and nor can anything else that leaves the picture intact. SynthID for images lives in the pixels rather than the metadata, and it survives cropping, resizing, compression, even a screenshot. Removing it would mean regenerating the image, which changes what it looks like. We remove the metadata completely and tell you plainly when a picture looks like it also carries a pixel watermark we cannot touch.
- Do I need an account?
- No, for either tier. Checking needs nothing at all. If you buy a pass, that browser is unlocked the moment you pay. No password, no key to type in. The confirmation page also gives you a link that unlocks your phone or another computer, if you want it there too.
More detail
- What is a zero-width character?
- A character that takes up no space on screen. U+200B, the zero-width space, is the best known one. It looks like nothing, but it is really there in the file: it counts toward the length, it travels with every copy and paste, it shows up instantly in a hex view. A few of them spread through a document make a pattern that says where the text came from.
- What are Unicode tag characters?
- A block of characters from U+E0000 to U+E007F that mirror ordinary ASCII but show absolutely nothing. Because each one maps onto a normal character, a whole readable message can be written in them and hidden inside a normal-looking sentence. They are the usual way hidden text is smuggled, and they are easy to spot once you know to look. We list every one we find.
- Why do you keep some invisible characters instead of deleting them all?
- Because deleting all of them breaks real text. The zero-width non-joiner is part of how Persian and Devanagari are spelled. The zero-width joiner is what holds a family emoji together as one picture. Flag emoji are built out of tag characters, the same block used to hide messages. A tool that strips every invisible character quietly mangles any document containing those, and most tools do. We look at what is around each character and keep the ones doing real work, with an option to strip them anyway.
- Does removing metadata change my image quality?
- No. We read the file structure, drop the metadata blocks, then write the rest back untouched. The compressed picture data is copied byte for byte and never re-encoded, so a JPEG does not lose another generation of quality. We also keep the colour profile and the Adobe colour-transform marker on purpose, because dropping those shifts the colours.
- Which image formats work?
- PNG, JPEG, WebP. Animated PNG and animated WebP work too. GIF is detected but not cleaned yet, so convert it first. PDF and video are not supported yet.
- What is the AI writing score?
- A rough count of the habits unedited assistant text tends to have: em-dashes, stock phrases, sentences that are all the same length, curly quotes, bolded bullet openings. It is a "here is what a human marker would notice" reading. It is not a watermark decoder, and it is not the odds that something was written by AI. Nobody can produce that second number reliably, and tools that claim to are guessing in a confident font.
- Can I use this on work I wrote myself?
- Yes, and people do. Text picks up invisible characters from copying out of PDFs, web pages, Google Docs, email. If an automated checker has ever flagged something you genuinely wrote, running it through here tells you whether stray characters were the reason.
- Is there an API?
- The endpoints this site uses are described on the How it works page and they are stable. A proper documented API with keys is planned. Email us if you need one and it moves up the list.
- What happens when my pass runs out?
- You go back to free checking. Nothing is deleted, because nothing was stored. Buying another pass unlocks you again straight away.
- Do you do refunds?
- Yes. If it did not do what you expected, email us within 14 days and you get your money back. Free checking exists so you can confirm there is something to remove before you pay to remove it.
Something we did not cover?
If it is a technical question, the how it works page goes through the whole thing. Otherwise, email us.
Get in touch