Protect. Moderate. Empower.
Keep your community safe and protect your business from compliance risk using our advanced content moderation AI.
Gaming
Maintain safe communities, enforce in-game rules, and address cheating or toxic behavior
Comments
Prevent spam, toxicity, and offensive language in user comments
User-Generated Content
Identify illegal or abusive content and other terms of service violations before publishing
Beyond Keywords: Multilingual AI with Customizable Tags for Precise Control
Multilingual support
Our model is trained on 50+ languages.
Select from our expert tags
Expert tags are well-tested by our staff and produce the best results.
Define custom tags
Leverage our advanced AI to identify issues specific to your needs.
Zero Model Training
Add your custom content tags and begin seeing results immediately.
How It Works
Testimonials
What our clients say
Product
Start automating content moderation in minutes with our simple REST API.
Base URI
The base URI for the current version of the TrustWin REST API is:
-
https://api.trustwin.io
Authentication
The TrustWin REST API accepts HTTP basic authentication credentials.
Text Moderation
Endpoint
-
/text
Required Inputs
Only content
(string) is a required input.
Example Request
curl -X POST https://api.trustwin.io/text \ -H "Content-Type: application/json" \ -H "Accept: application/json" \ --user "{API_KEY_ID}:{API_KEY_SECRET}" \ --data '{"content": "Sylvanas did nothing wrong!"}'
Example Response
{ "id": 12345, "created_at": "2024-01-22T08:00:00Z", "content": "Sylvanas did nothing wrong!" "moderation_tags": [ "World of Warcraft Reference" ], "policy_decision": "ban_user" }