VidSentry
VidSentry is an AI video content moderation platform that detects hate speech, graphic violence, explicit content, weapons, drug use, harmful audio, and on-screen text across 40+ languages — including multilingual code-switching that no other platform handles.
Core capabilities:
- Surgical frame-level redaction of flagged content
- Zero racial bias across all skin tones, verified on every detection
- Cultural guardrails: context-aware decisions, not blunt keyword filters
- OCR: detects harmful text visible within video frames
- Audit-ready compliance reports for NITDA, ICASA, and FPB
- Self-improving: active learning pipeline sharpens accuracy over time
- API-first integration for rapid deployment
Available as pay-as-you-go, volume tiers, or enterprise contracts.
The moderation infrastructure African platforms have been waiting for.
Learn more about VidSentry
WebPurify
World-Class Image Moderation & More. Discover a faster, more efficient way to keep user-generated content clean. Given the complexities associated with nuance and context, our human moderators are trained to flag violations that fall into the gray areas and make final image decisions that align with your brand standards. Our Automated Intelligent Moderation (AIM) API service offers 24/7 protection from the risks associated with having user-generated content on your brand channels—detecting and removing unwanted images in real-time. This one-of-a-kind solution delivers the best of automated and live moderation through a single, easy-to-use API. AI technology detects images with a high probability of containing undesirable content, limiting the volume that requires human review. The remaining images are then queued up for moderation by experts who are trained to flag any additional violations.
Learn more about WebPurify
Tisane
Tisane is NLU API with a focus on abusive content and law enforcement needs. Tisane detects:
* hate speech
* cyberbullying
* criminal activity
* sexual advances
* attempts to establish external contact
and more.
Tisane classifies the actual issue, and pinpoints the offending text fragment; optionally, explanation can be supplied for a sanity check or audit purposes.
Tisane supports 30 languages, even if the text contains slang and obfuscation.
Learn more about Tisane
Community Sift
AI-powered chat filter and content moderation platform for social networks. A powerful, scalable, and automated content moderation platform for social products. Simply connect to our API to moderate text, usernames, images, and videos in real time. Two Hat’s AI-powered content moderation platform classifies, filters, and escalates more than 102 billion human interactions, including messages, usernames, images, and videos a month, all in real-time. With an emphasis on surfacing online harms including cyberbullying, abuse, hate speech, violent threats, and child exploitation, we enable clients across a variety of social networks to foster safe and healthy user experiences. Maintain autonomy over your content moderation practices with the agency to adjust your settings, create flexible workflows, make real-time updates, and have full transparency into our solution. During a real-world crisis on your platform where real lives matter every second counts.
Learn more about Community Sift