Free · No sign-up

The AI detector that shows its work.

Paste your text and see the exact words, phrases, and patterns that read as AI, each with a human fix. A reproducible score you can trace, not a guessed percentage.

Free Runs in your browser Every flag explained

Your text

Nothing is uploaded
0 words · 0/12000

Instant · no signup · stays in your browser

Three steps

Paste, see the tells, fix them.

1

Paste your text

A draft, a caption, an email. It all runs locally in your browser.

2

See what reads as AI

The exact words and patterns are highlighted, grouped, and counted, with a reproducible score.

3

Apply the fixes

Every flag comes with a specific human fix, so you rewrite toward your voice, not away from a number.

Why most AI detectors are guessing

The popular detectors hand you “87% AI” and no way to check it. Those scores come from models that are wrong often enough to get real students and writers falsely accused. Proving a human wrote something is, in the general case, impossible. So we do not pretend to. Instead of a verdict, this tool gives you a transparent, reproducible read of the patterns that make writing feel machine-made: filler openers, corporate buzzwords, stock cadences, and over-long, listy rhythm. For the full breakdown, read the words AI overuses and why AI tweets all sound the same.

How to actually sound human

The fixes are always in the same direction: be specific, be direct, and let your own rhythm show. Cut the filler opener, name things in plain words, and vary your sentence length the way you naturally would. If you draft in ChatGPT, see how to make ChatGPT write in your voice. And if you want writing that starts in your voice instead of being scrubbed of AI after the fact, the free Humanize AI Text tool rewrites a passage toward a human voice, while the free brand voice analyzer shows you the signals that make your writing yours.

Now that you see the tells

Write like a person from the start.

Humanize a passage

The free Humanize AI Text tool rewrites AI-sounding text toward a natural voice, with a count of tells removed.

Try Humanize

Analyze your voice

The brand voice analyzer reads how you actually write and scores any draft against your own sample, so drafts start human.

Analyze my voice

Draft with a voice score

In Studio, every draft gets a live voice-match score, so it sounds like you before you post.

See Create

FAQ

Good to know

What is this AI detector?
A free AI detector that scans your text for the exact words, phrases, and sentence patterns that make writing read as AI-generated (leverage, delve, robust, 'for good reason', over-long lists), highlights each one, and suggests a human fix. It runs entirely in your browser and nothing is uploaded.
How is this different from other AI detectors?
Other detectors hand you a probability ('73% AI') that is frequently wrong and impossible to act on. This one is deterministic: it flags exact words, phrases, and patterns from a known list and shows you the evidence, so you can see and fix what reads as AI. We ran one of our own articles through five detectors and got 94%, 100%, 69%, and two 'human' verdicts on the same text. This tool never guesses.
Are AI detectors accurate?
Probability detectors often are not. We ran a single article through five and got 94%, 100%, and 69% AI from three while two said 'human', on the exact same text. A number that five tools cannot agree on is not safe to act on, and false accusations are a real risk. That is why this tool shows exact, deterministic flags instead of a guess.
What words does AI overuse?
Common tells include leverage, delve, robust, seamless, unlock, navigate, elevate, and foster, plus phrases like 'it's worth noting' and 'a testament to', and em-dashes. One on its own is fine; a cluster of them is what reads as machine-written.
Does this detect ChatGPT or GPT-4 text?
It detects the patterns those models fall into, not a specific model. Because it flags the actual tells in the words on the page, it works regardless of which model wrote the text, or whether a person did.
What does it flag?
Three layers, all deterministic. First, VoiceMoat's actual refused-word cluster (the words our writing AI is told never to use). Second, a wider set of common AI tells: overused words (genuinely, navigate, unlock), stock phrases (for good reason, a testament to), and em-dashes. Third, AI sentence patterns like over-long lists and 'not just X, but Y'. Every flag carries a human fix or a rephrase note.
How is the AI-slop score calculated?
It is transparent: density (flagged words as a share of total words) plus how many different types of tell appear, clamped to a 0-100 range. Zero tells is always a clean 0. We show the full breakdown so it is never a black box.
Does using these words mean my writing is bad?
Not always. Some words are fine in context, and the common-tell layer (like 'navigate') has honest uses. The problem is that a pile of them together makes writing sound generic. Cut the ones that are not yours.
How do I make my writing actually sound like me?
Removing AI words is step one. VoiceMoat trains on your full profile and scores every draft against your real writing voice, so you keep your style even at volume. You can start free.

Post in your voice. Every day.

De-slopping after the fact is a chore. VoiceMoat helps audenAI write in your voice from the first draft, across Twitter and LinkedIn.

Start your trial See all free tools