This page cleans up pasted AI output: em dashes and curly quotes become plain ASCII, the ellipsis character becomes three dots, and every invisible character is flagged and removed. The sample below is typical assistant output. Everything runs in your browser — nothing is uploaded.
Large language models are trained on professionally typeset text, so their output uses typographic punctuation: em dashes (U+2014), curly quotes (U+2018/U+2019/U+201C/U+201D) and the single-character ellipsis (U+2026). That's correct typography for prose — and a problem the moment the text goes anywhere that expects plain ASCII: source code, config files, CMS fields, CSV pipelines, email systems with strict encoding, or just your house style.
Beyond the visible punctuation, formatted times sometimes carry a narrow no-break space (U+202F) before AM/PM, and non-breaking spaces (U+00A0) appear in numbers and between words. Text that has travelled through chat UIs, docs or web pages can additionally pick up zero-width spaces along the way — invisible characters that break string matching and compilers.
It converts the punctuation to plain ASCII equivalents, normalizes every exotic space to a regular space, strips invisible characters, and shows you an x-ray of exactly what was found before you copy the cleaned result. To be clear about what it doesn't do: it does not rewrite wording, and it will not make text fool AI-content detectors — those look at word choice and sentence structure, not punctuation. This is a formatting tool, not a disguise. If you want to check text for deliberate hidden watermarks, see invisible watermarks.
Paste the text above. Every changed character is highlighted in the x-ray with its Unicode name, and the cleaned output updates live. Untick any rule you don't want — for example, keep em dashes but still remove invisible characters.
Guides for the common cleanup jobs — what the source puts into your text, exactly what it breaks, and the tool preloaded with a demonstration:
AI-generated text · Text copied from Word / Google Docs · Text copied from a PDF · Pasted code that won’t run · CSV & spreadsheet data · Invisible watermarks · Many files at once (batch)
Dedicated pages for the usual suspects — what each one is, where it sneaks in from, the exact errors it causes, and how to find it in your editor:
Zero-width space (U+200B) · Non-breaking space (U+00A0) · Byte order mark (BOM) (U+FEFF) · Soft hyphen (U+00AD) · Smart quotes · Em dash (U+2014) · Narrow no-break space (U+202F) · Ideographic space (U+3000) · Zero-width joiner (U+200D) · Zero-width non-joiner (U+200C) · Word joiner (U+2060) · Right-to-left override (U+202E) · Left-to-right mark (U+200E) · Line separator (U+2028) · Variation selector-16 (U+FE0F) · Object replacement character (U+FFFC) · Hangul filler (U+3164) · Braille pattern blank (U+2800) · Ligatures · Minus sign (U+2212)
Страницы на русском — те же инструменты с переведёнными правилами и примерами под задачу:
Невидимые символы в тексте · Убрать невидимые символы · Почистить текст нейросети · Неразрывные пробелы в числах · Текст из Word · Код не запускается