AI Moderation Models
Explore our comprehensive catalog of 37+ AI-powered moderation models for images, videos, audio, and text content.
AI-Generated Image Detection
Detect if an image was AI-generated or AI-edited
Image Deepfake Detection
Detect deepfakes and face manipulations using BYNN SOTA model
Face Occlusion Detection
Detect if a person's face is occluded in images using AI vision analysis
Minor Detection
Age group and minor detection
Age Detection
Age detection of person or group
People Counting
Count distinct people in images with segmentation masks
Wanted Persons Detection
Face recognition in images against Interpol, Europol, FBI and 52 country law enforcement databases
Nudity & Adult Content Detector
Detect nudity and sexual content using AI vision analysis
Violence Detection
Detect violence levels in images using AI vision analysis
Weapons Detector
Detect weapons, firearms, threatening knives
Recreational & Medical Drugs Detector
Detect pills, cannabis, joints, syringes, heroin...
Alcoholic Beverages Detector
Detect wine, beer, cocktails, spirits
Smoking & Tobacco Products Detector
Detect smoking and tobacco products
Gambling Detector
Detect gambling, casinos, slot machines...
Money & Banknotes Detector
Detect displays of money and banknotes
Destruction & Fire Detector
Detect scenes of destruction, damages to buildings and vehicles, fires
Military Scenes Detector
Detect scenes with military personnel or equipment
Graphic Language Detection
Detect graphic, offensive, or abusive language in images
Document Classifier
Classify KYC/KYB documents into 76+ types including passports, ID cards, invoices, bank statements, and more
Content Rating
Rate image content as General Audience, Teen (13+), Teen (16+), or Adult (18+) based on nudity, violence, and language
Vehicle Detection
Detect and segment vehicles including cars, trucks, buses, motorcycles, and bicycles
Document Tampering Detection
Detect manipulation and forgery in document images
Document Liveness Detector
Detect if a document or portrait image was captured live or photographed from a screen
Video Deepfake Detection
Detect deepfakes and face manipulations using BYNN SOTA model
Face Liveness Detection
Anti-spoofing detection for biometric authentication (iBeta Level 2)
Wanted Persons Detection
Real-time face recognition in videos against Interpol, Europol, FBI and 52 country law enforcement databases
Violence Detection
Detect violence levels in videos using AI vision analysis
Content Rating
Rate video content as General Audience, Teen (13+), Teen (16+), or Adult (18+) based on nudity, violence, and language
AI-Generated Music Detection
Detect if music is AI-generated
Voice Deepfake Detection
Detect AI-generated or cloned voices
Voice Safety Detection
Detect unsafe audio content including harassment, profanity, discrimination, and illegal content
Mental Health Detection
Detect mental health indicators including anxiety, depression, and crisis signals
Fake News Detection
Detect misinformation and fake news in text content
PII Solicitation Detection
Detect when users ask for or share personal information
Fraud Text Detection
Detect fraudulent messages, phishing attempts, and scam content
AI-Generated Text Detection
Detect if text was generated by AI models (GPT, Claude, etc.)
Advanced Sentiment Analysis
Analyze text sentiment with high accuracy (positive, negative, neutral)