---
title: Text Moderation API
emoji: 🛡️
colorFrom: red
colorTo: blue
sdk: docker
pinned: false
license: mit
---

# Text Moderation API

A robust text moderation API that analyzes user-generated content and returns moderation actions (allow/flag/delete).

## Features

- **Pattern matching** for common harmful content
- **ML-based detection** using BERT models for toxicity and hate speech
- **Leet speak normalization** to catch obfuscated harmful content
- **Fast response times** with efficient processing

## API Usage

### Endpoint: `/moderate`

**Method:** POST

**Request Body:**
```json
{
  "user_id": "user123",
  "text": "Text to moderate"
}