Omnifence API
Content moderation API for text, images, video, and audio
Omnifence is a content moderation platform. You submit text, an image, a video, or an audio clip. The API returns a pass or reject decision for it.
Every modality works the same way. You submit content and receive a job_id immediately. You then poll for the decision, or you receive it by webhook.
Get started#
Submit your first moderation request in under five minutes.
Agent skillLet a coding agent add moderation to your codebase for you.
AuthenticationAuthenticate requests with Bearer tokens.
API referenceExplore all endpoints with request and response examples.
Moderation#
Screen text, images, video, and audio for unsafe content.
Screen text against your prohibited categories and safety compliance standards.
Image moderationRun automated safety and NSFW classification on an image.
Video moderationAnalyze video content to ensure full policy compliance.
Audio moderationAnalyze audio content for speech policy and safety compliance.
CategoriesThe built-in checks, plus your own custom categories.
Decision logicUnderstand how a job reaches a pass or reject decision.
Shared Registry#
Stop users that other platforms banned for fraud or prohibited content from signing up to yours, and report the users you ban. The registry shares a keyed hash of each email, never the email, and never names the platform that made a report.
How the industry banned-user registry works, and who can join.
Registry quickstartCheck your first sign-up and report your first ban.