# StealthGPT

> Rewrite AI-generated text into natural, human-sounding content with StealthGPT.

App · AI Models · 1 action. Web page: https://docs.lodol.com/docs/integrations/stealthgpt

## Actions

### Humanize content

Rewrite AI-generated text so it reads as natural, human-written content that is less likely to be flagged by AI detectors.

**Inputs**

- Content (`content`, text, required): The text to humanize (up to 3,000 words).
- Reading level (`tone`, text): The reading level of the rewritten text. Defaults to Standard. One of: `Standard`, `HighSchool` (High school), `College`, `PhD`.
- Quality (`quality_mode`, text): Whether to favour higher quality or a faster response. Defaults to higher quality. One of: `quality` (Higher quality), `fast` (Faster).
- Output format (`output_format`, text): The format of the returned text. Defaults to plain text. One of: `text` (Plain text), `markdown`.

**Outputs**

- `ai_detection_score` (number): How likely the rewritten text is to be flagged as AI, from 0 to 100. Lower is more human.
- `humanized_text` (text): The rewritten, human-sounding text.
- `remaining_credits` (number): Words remaining on your account.
- `words_spent` (number): How many words this request used.

**Example output**

```json
{
  "ai_detection_score": 8,
  "humanized_text": "Solar and wind power matter more every year. They cut the carbon we put into the air and keep clean electricity flowing for the people who come after us.",
  "remaining_credits": 984740,
  "words_spent": 260
}
```