Prompt Text Cleaner
Clean AI prompts and ChatGPT output: convert Markdown to plain text, tidy Markdown, strip emoji, normalise whitespace and escape quotes for code.
About this tool
Prompt Text Cleaner
Clean AI prompts and ChatGPT output: convert Markdown to plain text, tidy Markdown, strip emoji, normalise whitespace and escape quotes for code.
Pick a cleaning step, paste your text and copy the cleaned result. This page brings together 5 separate prompt text cleaner pages (Strip emoji, Escape quotes, Markdown cleaner, Markdown to plain, Whitespace) so you can compare them without hunting for the right one.
How to use Prompt Text Cleaner
- 1
Open Prompt Text Cleaner on AltFTool — it loads instantly in your browser.
- 2
Choose your clean at the top: Strip emoji, Escape quotes, Markdown cleaner, Markdown to plain and 1 more. On a phone it is a drop-down list.
- 3
Fill in the prompt text cleaner for that clean; each of the 5 options keeps its own rules, data and defaults.
- 4
Read the result, then switch clean to compare. The page link keeps your clean (?v=emoji-stripper), so you can bookmark or share it.
Why use Prompt Text Cleaner
All 5 in one place
Strip emoji, Escape quotes, Markdown cleaner and the rest sit behind one picker, so switching clean takes a tap instead of a new search.
Built for each option
Every clean keeps its own rules, numbers and defaults rather than one generic template.
Shareable view
The link remembers the clean you picked, so a bookmark or a shared link opens straight on it.
Common use cases
- Clean a system prompt copied out of a Notion or Google Doc that silently carried zero-width characters into your codebase.
- Paste a multi-line system prompt containing quotes and braces into a JavaScript file without hunting down the one unescaped character that breaks the build.
- A writer pasting a Google Docs draft into ChatGPT who wants the curly quotes and bold markers gone so the model does not echo the formatting back
- Flatten a prompt for a form, SMS gateway or voice assistant that displays Markdown characters literally instead of rendering them.
Frequently asked questions
Which clean options does this tool cover?
5: Strip emoji, Escape quotes, Markdown cleaner, Markdown to plain, Whitespace. Pick one at the top of the tool; the page link updates (for example ?v=emoji-stripper) so you can bookmark or share that exact view.
Do emoji use more tokens than regular text?
Yes, substantially more per visible character. Most emoji sit outside the Basic Multilingual Plane and take four UTF-8 bytes each, and in common byte-pair vocabularies a single emoji typically costs between one and four tokens, against roughly four characters per token for plain English.
How do I escape a single quote inside a single-quoted shell string?
You cannot escape it inside the quotes — POSIX single quotes make every character literal, including the backslash. The standard idiom is to close the string, emit an escaped quote and reopen it: '\''. So O'Brien becomes 'O'\''Brien', which the shell concatenates back into one word.
Why do quotes turn curly when I copy text from Word or Google Docs?
Word processors autocorrect straight ASCII quotes to typographic 'smart' quotes (Unicode U+2018/U+2019 and U+201C/U+201D) as you type. When that text is pasted into a prompt, code sample or config file, the curly characters are different code points from ' and ", which can break string matching and code. This tool maps them back to their ASCII equivalents.
How do I remove Markdown formatting from text?
Resolve the constructs in the right order: lift out code fences and code spans first, then handle block markup such as headings, lists, blockquotes and tables, then inline markup such as emphasis and links, and resolve backslash escapes before emphasis rather than after. A single find-and-replace pass over asterisks will corrupt any code sample in the text.
Does extra whitespace actually cost me tokens?
Yes. Most byte-pair tokenizers encode runs of spaces and newlines as their own tokens, so a prompt with stacked blank lines and double spaces costs slightly more than the same prompt cleaned up. As a rough guide, one token is about four characters of English text, so removing 400 stray characters saves roughly 100 tokens per call.