AI text detection
Examines vocabulary repetition, recurring phrases, sentence-length distribution, punctuation frequency, and unusual characters. More complete text usually produces steadier statistical signals.
Open text detectorPrivacy first · Local by default
Free AI content detector Text · Image · Video
No login or sign-up required. Text, video, and the default image screen run locally; optional remote image checks disclose uploads before use.
Content screening and verification
Results separate heuristic screening signals, file facts, and evidence limitations.
Text content
GenDetect checks repetition, sentence length, punctuation, and character structure.
Image content
GenDetect checks sampled color diversity, luminance variance, and adjacent-pixel edge density.
本地启发式不会上传图片。
Video content
GenDetect reads duration, resolution, estimated average bitrate, file extension, and MIME type.
Detection methods
Each content type needs a different analysis. GenDetect separates screening signals, file facts, and limitations.
Examines vocabulary repetition, recurring phrases, sentence-length distribution, punctuation frequency, and unusual characters. More complete text usually produces steadier statistical signals.
Open text detectorExamines color distribution, brightness contrast, and edge gradients. Dimensions and file size are shown separately and never affect the index.
Open image detectorReads duration, resolution, average bitrate estimated from total file size, file extension, and MIME type. It does not inspect frames or audio, so it returns no generation score.
Open video metadata checkHow to read the score
This demo uses local text and image heuristics by default while video shows metadata only. Optional remote image modes return provenance or metadata clues. The index is not trained or probability-calibrated and cannot prove origin.
Understand and verify
Understand the signals and false-positive limits first, then verify the original file, provenance, and editing process. These resources separate methodology, accuracy, and human review.
See how text and image signals form screening indexes, which video file facts are read, and what browser heuristics cannot determine.
Read methodology and limitationsUnderstand false positives, false negatives, thresholds, and sample differences without mistaking an uncalibrated screening score for a probability of origin.
Review accuracy and false positivesCheck original material, content credentials, publishing sources, version history, and contextual facts with separate workflows for text, images, and video.
Read the human verification guideFrequently asked questions
Understanding the limits of detection scores helps reduce false positives for human and edited content.
AI content detection provides supporting clues only. Models, rewriting, compression, and input length can all affect the result, so a score alone cannot establish the source.
Longer text contains more samples of sentence structure, repetition, and punctuation, making statistical signals steadier than they are for short snippets.
The current demo examines image color, brightness, and edges. For video it only displays duration, resolution, estimated bitrate, file extension, and MIME facts and makes no AI-origin judgment.
No. Verify the author, publication date, original file, content credentials, and publishing source before reaching a conclusion.
No login or sign-up is required. Text, video, and the default image screen stay in your browser. Source metadata, SD/Flux, Gemini visual screening, and available external Verify modes upload to the same-origin API. GenDetect deletes completed uploads immediately and retains interrupted jobs for at most one day; Gemini and external Verify also forward the image to the provider named in the interface.