Filter Profanity, Toxic Language, and Unwanted Images with our API
The power of Two Hat's Community Sift is just a simple API call away
Two Hat’s Community Sift is a context-based profanity filter and moderation tool designed for online communities of all demographics. Whether you’ve written your app or platform in Java, Python, Ruby, PHP or any other language, you can easily connect to Community Sift’s API to dynamically detect and filter abuse, harassment, profanity, and toxic content in real time. Protect your brand and your community with automated content moderation for chat, usernames, private and public messages, forums, comments, images, and more.
HOW IT WORKS
STEP 1: CALL OUR API
Call our secure RESTful API with a simple JSON request. This sends your user-generated content to Community Sift.
STEP 2: COMMUNITY SIFT PROCESSES CONTENT
Our industry-leading artificial intelligence model identifies and labels high-risk content for abuse, harassment, profanity, sexting, and more — all in real time.
STEP 3: COMMUNITY SIFT RETURNS RESULTS
The content is returned to your platform. Depending on your custom settings, the content is flagged for review by your team, automatically removed from your community, or published.
Getting started today is easy. Simply fill our the form on this page and we’ll be in touch about scheduling a demo.