Perspective API
Analyzes text for toxicity and harmful content using Google's Perspective API. Helps moderate comments, messages, and user-generated content across multiple languages.
305 viewsLocal (stdio)
What it does
- Analyze text toxicity scores
- Detect harmful or abusive language
- Moderate user-generated content
- Score text across multiple languages
- Generate content safety reports
Best for
Social media platforms needing comment moderationChat applications filtering toxic messagesContent management systems with user submissionsCommunity forums maintaining safety standards
Multi-language toxicity detectionGoogle's production-grade AI model
