Detect profanities
Detect
The detectProfanities service provides automated identification and flagging of profane or offensive language within a given text string. Operating as a standalone service, it allows for content moderation independently of the translation workflow.
The service analyzes the submitted text to detect sensitive content and returns a structured response including the detected language and content type. This endpoint is designed to help developers maintain platform safety by programmatically identifying potentially inappropriate strings before they are processed or displayed.
Request
res = lara.detectProfanities("Don't be such a tool!",
language='en-US',
content_type='text/plain'
)
print(res)const res = await lara.detectProfanities("Don't be such a tool!", 'en-US', 'text/plain');
console.log(res);
DetectResult res = lara.detectProfanities("Don't be such a tool!", 'en-US', 'text/plain');$res = $lara->detectProfanities("Don't be such a tool!", 'en-US', 'text/plain');res, _ := lara.detectProfanities("Don't be such a tool!", 'en-US', 'text/plain')
fmt.Println(*res.String)val res: DetectProfanitiesResult = lara.detectProfanities("Don't be such a tool!", 'en-US', 'text/plain')var res = await lara.detectProfanities("Don't be such a tool!", 'en-US', 'text/plain');let res = try await lara.detectProfanities(text: "Don't be such a tool!", language: "en", content_type: "text/plain")Here follows the basic fields for the detect method:
Field | Type | Required | Default | Description |
|---|---|---|---|---|
text | String | Yes | The text to be detected. This can be a single string. | |
language | String | No | The source language code (e.g., "en-US" for English). | |
content_type | String | No | The content type. |
The result of the detect method is an object containing:
| Field | Type | Description |
|---|---|---|
| maskedText | String | The masked text |
| profanities | String[] | The detected profanities object |
Response
Result: {
"maskedText": "Don't be s**h a tool!",
"profanities": [
{
"text": "such",
"startCharIndex": 9,
"endCharIndex": 16,
"score": 0.8136
}
]
}Billing
More details are available in the pricing page
Updated about 2 hours ago
