Profanity Detector
Detect offensive language in text with word-level position reporting
/v1/text/profanity
How to Use
1. Send a POST request to `/v1/text/profanity` with the `text` field. 2. Check `contains_profanity` (boolean) for a quick pass/fail result. 3. Inspect the `matches` array for the specific words flagged and their positions. 4. Use `count` to decide on escalation thresholds.
About This Tool
The Profanity Detection endpoint scans text for offensive language and returns a boolean flag along with a list of flagged words and their character positions. Useful for content moderation pipelines where user-submitted text needs to be screened before publication.
The word list covers common English profanities. Detection is case-insensitive and handles common letter substitutions.
Use Cases
User-generated content
Screen comments, reviews, and forum posts before publication
Chat applications
Flag or block offensive messages in real-time chat systems
Content moderation queue
Auto-route flagged submissions to a human review queue
Brand safety
Prevent offensive content from appearing alongside paid advertising