AI text cleaner API

Strip the em dashes, curly quotes and hidden characters that make text read as AI-generated.

When to call it

A model's output carries fingerprints that no human types: em dashes where a comma belongs, curly quotes, zero-width joiners, non-breaking spaces. Cleaning them by hand works once. In a content pipeline, a CMS import or a publishing step, it has to happen to every document without anyone remembering to do it.

For a one-off, the browser version needs no token and never sends your data anywhere: it runs on your own machine.

Example

curl -X POST https://astraltext.com/api/v1/ai-text-cleaner \
  -H "Authorization: Bearer ast_YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"input": "The result — as we’ll see — is “clean” text​ with no artefacts."}'

{
  "tool": "ai-text-cleaner",
  "result": "The result - as we'll see - is \"clean\" text with no artefacts.",
  "chars": 62,
  "ms": 1
}

In your language

const res = await fetch("https://astraltext.com/api/v1/ai-text-cleaner", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ASTRAL_TOKEN}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({"input": "The result — as we’ll see — is “clean” text​ with no artefacts."}),
});
if (!res.ok) throw new Error((await res.json()).detail);
const { result } = await res.json();

import os, requests

res = requests.post(
    "https://astraltext.com/api/v1/ai-text-cleaner",
    headers={"Authorization": f"Bearer {os.environ['ASTRAL_TOKEN']}"},
    json={"input": "The result — as we’ll see — is “clean” text​ with no artefacts."},
    timeout=30,
)
res.raise_for_status()
result = res.json()["result"]

Parameters

Errors

Errors are RFC 7807 problem documents with a stable type you can branch on.

Questions

What exactly does it remove?

Em and en dashes become hyphens, curly quotes become straight ones, and invisible characters go: zero-width spaces and joiners, the byte-order mark, soft hyphens, bidirectional marks and exotic spaces such as the non-breaking and thin space.

Does it rewrite my sentences?

No. It touches characters, never words. Nothing is rephrased, summarised or reordered, so the meaning and the length of the text are unchanged.

Will this make text pass an AI detector?

It removes formatting artefacts, which is a real signal some tools use, but no detector is defeated by punctuation alone. Treat it as tidying, not as a disguise.

Other endpoints

• Remove em dashes API
• Remove invisible characters API
• Remove emoji API
• Remove line breaks API
• Strip Markdown API
• Remove citations API