The Copyleaks Text Moderation API provides a flexible and powerful solution for identifying and managing a wide range of harmful or risky content. Our API supports a comprehensive set of moderation labels, allowing you to tailor the moderation process to your specific community standards.

Supported Labels

Label ID	Description
toxic-v1	Harmful language that insults, demeans, or degrades in a general way, not necessarily aimed at a specific person. This category is reserved for language intended to cause emotional harm, not for other stuff like illegal or toxic substances.
profanity-v1	Use of strong or offensive swear words.
hate-speech-v1	Language that demonizes or incites harm toward a group or individual based on inherent traits, often calling for violence or systemic discrimination.
harassment-v1	Targeted abuse that insults or degrades a specific person or group, focusing on personal traits or beliefs. This language aimed at a specific person or group that attacks their character or reputation—this can include defamatory or accusatory statements meant to harm someone’s standing.
self-harm-v1	References that encourage or normalize self-injurious behavior.
adult-v1	Explicit descriptions, references, or portrayals of sexual acts or behavior intended to evoke sexual arousal. This excludes non-sexual explicit content.
violent-v1	Language that incites or glorifies physical harm or injury.
drugs-v1	References, descriptions, or endorsements of the use, abuse, or distribution of drugs in a bad way, including illegal substances or the misuse of legal drugs.
firearms-v1	Content discussing the use, possession, or distribution of guns and other weapons, especially when such discussions could promote or cause violence or unsafe practices.
cybersecurity-v1	Content related to computer security, including discussions on hacking, data breaches, and measures to hack digital systems or gain unauthorized access.

Usage

When submitting text for moderation, include the desired labels in your request. You can specify all labels or only the ones relevant to your use case:

Request

POST https://api.copyleaks.com/v1/text-moderation/{scanId}/check

Headers

Content-Type: application/json
Authorization: Bearer YOUR_LOGIN_TOKEN

Body

{
  "text": "Your text content to be moderated goes here.",
  "language": "en",
  "labels": [
    { "id": "toxic-v1" },
    { "id": "profanity-v1" },
    { "id": "hate-speech-v1" },
    { "id": "harassment-v1" },
    { "id": "self-harm-v1" },
    { "id": "adult-v1" },
    { "id": "violent-v1" },
    { "id": "drugs-v1" },
    { "id": "firearms-v1" },
    { "id": "cybersecurity-v1" }
  ]
}

Full details about the request and response structure can be found in the Text Moderation API Reference.

Next Steps

Moderate Text Content Learn how to use the Text Moderation API to scan and moderate text content.

Text Moderation API Reference Explore the complete API reference for text moderation, including request and response details.