Sightengine is an API service for moderating and analyzing user-generated content. Developers send images, videos, audio or text and receive instant results that flag nudity, violence, hate, drugs, weapons, personal information and other unwanted material across more than 120 moderation classes. The same API detects AI-generated images, video, speech and music, identifies deepfakes and face swaps, and finds near-duplicates and spam. A free tier gives 2,000 operations a month, Starter costs $29 a month for 10,000 operations, and Pro costs $99 a month for 40,000, with $0.002 per extra operation.
The service is aimed at engineers and trust and safety teams at social networks, dating apps, marketplaces, forums, gaming communities and any site that accepts uploads. Small projects can prototype on the free tier, growing apps use Starter for visual and text moderation, and larger platforms choose Pro for live-stream moderation, audio moderation, custom image and video search, liveness checks and age estimation. Enterprise customers get custom models and classes, geo-fencing, service level agreements and a dedicated support engineer. Fast responses and scaling into tens of millions of images per month suit high-traffic products.
Typical use cases include screening profile photos for a clear, real face, blocking explicit images before they reach a feed, and catching phone numbers, links or external usernames that try to move buyers off a marketplace. Platforms flag AI-generated listings and deepfakes, run face liveness checks during onboarding or account recovery, and detect recaptured photos of screens or printouts. Teams also build disallow lists to block repeated abuse, score images for quality, and extract text with OCR to moderate memes and screenshots.
