Docs / Moderation / OCR & QR Moderation / Text Moderation in Images and Videos

Text Moderation in Images and Videos

text-content-2.0

Detect profanity, personally identifiable information (PII) such as email addresses and phone numbers, links and URLs, and other unwanted text content in images and videos.

Replaces legacy model text-content

Overview

The Visual Text Moderation API detects unwanted, hateful, sexual, and toxic content within images and videos across 23+ moderation categories in 16+ languages. It uses advanced rules and pattern-matching techniques to identify problematic text, even when users attempt to obfuscate it. The moderation results include the detected language, triggered moderation categories, and detailed information about flagged words or expressions.

1. Detection

Detects text regions within the image or video frame.

2. Recognition

Converts the visually detected text into readable text strings.

3. Analysis

Evaluates the text strings using our rule-based moderation engine.

Customization

This API is highly customizable. You can tailor it to your needs by:

Listing Moderation Categories

Select exactly which categories you want to be evaluated in the API request.

Choosing Languages

Target a specific list of languages applicable to your users or community.

Filtering by Severity

Filter your moderation results based on the detected severity level.

Providing Custom Lists

Apply your own custom disallow and allow lists of words and expressions.

Use the OCR API to retrieve the raw text extracted from your image or video.

Moderation categories

The categories to be evaluated must be specified in the text_categories parameter of your API request, as a comma-separated list. The response will only contain results for the selected categories.

Sexual & Suggestive

sexual

Terms or expressions referring to sexual acts, sexual organs, body parts or bodily fluids typically associated with sexual acts.
Each match is assigned a severity level ranging from low to high.

Insults & Personal Attacks

insult

Words or phrases that insult, undermine or attack the dignity or honor of an individual.
Signs of disrespect that are generally used to refer to someone.
Each match is assigned a severity level ranging from low to high.

Discriminatory & Hate

discriminatory

Discriminatory, hateful, or derogatory content targeting individuals or groups based on protected characteristics (e.g. religion, ethnicity, nationality, sexual orientation, gender identity).
Each match is assigned a severity level ranging from low to high.

Inappropriate Language & Swear Words

inappropriate

Swear words, slang, vulgar language or socially inappropriate expressions used to describe something or to address someone.
Each match is assigned a severity level ranging from low to high.

Grawlix

grawlix

Sequences of typographical symbols (e.g. @#$%!) that are typically used to represent obscenity or profanity.

Email Addresses

Email addresses
Includes obfuscated email addresses such as john.doe [at] gmail [dot] com, john.doe@gmail, 𝒿𝑜𝒽𝓃.𝒹𝑜𝑒@𝑔𝓂𝒶𝒾𝓁.𝒸𝑜𝓂 or Jօнn.ĐØe@g𝐌aìL.cØʍ.

Phone Numbers

phone_number

Phone numbers that are valid numbers in the countries specified through the opt_countries parameter.
Includes obfuscated numbers such as 【2one2】5-fifty-five【twElve,3 four】, ②①②⑤⑤⑤①②③④ or 𝟚1𝟚|⑤𝟝𝟝-𝟙𝟚③𝟜.
You can select the countries to be covered through the opt_countries parameter. Provide a comma-separated list of the ISO 3166 2-letter country codes. For instance us for the United States, fr for France. See the full list of supported countries.
If you do not specify any country, the API will default to the following list of countries: United States us, France fr, United Kingdom gb.

Usernames

username

Usernames, social media handles (e.g. @john_doe, snapUser23, tiktok_user123).

Social Security Numbers

ssn

US social security numbers.

IP Addresses

IP addresses, both IPv4 and IPv6.

Link & URLs

link

URLs to external websites and pages.
Additional information allows you to determine whether link is unsafe, deceptive or known to contain otherwise unwanted content (e.g. adult content, gambling, or drugs). More details are available on the URL and link moderation page.

Extremism

extremism

Words, expressions or slogans related to extremist ideologies, people or events.

Weapons & Firearms

weapon

Names or terms related to guns, rifles, firearms and other weapons (e.g. ak47, kalashnikov, mk-14).

Medical Drugs

medical

Names of prescription or over-the-counter pharmaceutical drugs (e.g. xanax, viagra, flurazepam).

Recreational Drugs

drug

Names related to recreational drugs (e.g. cannabis, weed, xtc, cocaine).

Self-Harm & Suicide

self_harm

Terms related to suicide.
Mentions of self-inflicted injuries.
Each match is assigned a severity level ranging from low to high.

Violence & Threats

violence

Expressions of violence such as kicking, punching or harming someone, or threatening to do so.
Each match is assigned a severity level ranging from low to high.

Platform Evasion & Circumvention Attempts

platform_evasion

Attempts to send or lure a user to another platform.
These attempts are either for a social media platform (what's your ig?, add me on snapchat, give me ur wasap) or a device-related feature (drop ya phone number, wanna facetime?).

Off-Platform Mentions

off_platform_mention

Names of social media platforms.
The most common social networks are supported by default (facebook, whatsapp, snapchat, instagram, etc.), as well as their variations (ig, insta, snap, snp, etc.).

Content Trade & Solicitation

content_trade

Requests or messages encouraging users to send, exchange or sell photos (send a pic of u, can i see a face pic?) or videos of themselves (do you sell videos?, can you send a recent tape?).

Money Requests & Transactions

money_transaction

Requests or messages encouraging users to send money (give me 8 dollars, send ur credit card, e-transfer money).

Grooming

grooming

Minor-identifying questions.
Sexualized statements about minors.
Each match is assigned a severity level ranging from low to high.

Minor Presence

minor

Self-declared underage status.
Contextual clues indicating the presence of a minor in a conversation (e.g. grade level mention).

If a disallow list is specified through the opt_textlist parameter, the API will also return matches for the terms and expressions included in the list, under the blacklist category.

Disallow list (custom)

blacklist

Custom list of terms and expressions. Read more.

Language support

English is the default language used for text moderation. If no language is specified, the API assumes the text is in English and processes it accordingly

If you are confident about the language used in the message, for example, if your users primarily communicate in a specific language, you can set it using the opt_lang parameter. To do so, use the ISO 639-1 language codes:

Language	Code
English (default)	en
Chinese	zh
Danish	da
Dutch	nl
Finnish	fi
French	fr
German	de
Italian	it
Korean	ko
Norwegian	no
Polish	pl
Portuguese	pt
Russian	ru
Spanish	es
Swedish	sv
Tagalog / Filipino	tl
Turkish	tr

If you are unsure about the language used by a user, you can specify multiple languages as a comma-separated list. For example, en,fr,es for users who may write in English, French, or Spanish. The API will then automatically detect the language and apply the appropriate moderation rules. We recommend specifying the shortest possible list, as this improves both processing speed and detection accuracy.

Other languages are available upon request. Please get in touch regarding your language needs.

Detection strength

The Text Moderation API is significantly more robust than simple word-based filters. It uses advanced linguistic analysis to detect objectionable content, even when users deliberately attempt to bypass filters.

For example, for each word, the API evaluates millions of potential variations that may be used to evade detection, while smartly ignoring situations that could generate false positives. Here is a partial list of scenarios that are covered:

biiiiitttch

Repetitions

Characters being repeated to avoid basic word filtering.

$#it

Replacements

Replacement of characters with typographical symbols.

B__* O _ O -- B__s

Insertions

Adding spaces, punctuation and more within words.

ℙ🅤ᵴṨɏ

Obfuscation and Special characters

Unusual non-ASCII characters used to evade basic word filters.

phok yu

Spelling mistakes & Phonetic Variations

Changing word spellings while retaining their original meaning or pronunciation.

|3as¯|¯AR|)

Leet speak

Replacing some alphabetical characters with a combination of punctuation, digits and letters.

123FuckBlablah

Smart embeddings

Catching profanity based embeddings, while smartly ignoring potential false positives such as bassguitar or amass.

Severity levels

Severity is an optional indicator used to rank harmful content from mild to extreme. It may be available at both the match level and the category level.

Severity	Description
high	The highest severity level. Content that is harmful or dangerous in most contexts and typically requires direct action.
medium	Content that may be acceptable in limited contexts (e.g., adult-only environments) but generally requires monitoring.
low	Mild language that may be acceptable in many contexts.

When multiple matches are detected within the same category, their severity scores are aggregated to determine the overall category severity.

Custom disallow and allow lists

You can use custom disallow lists (also known as blacklists or ban lists) and allow lists in combination with Text-in-Image and Text-in-Video moderation.

To create a new text list, go to the dedicated page in your dashboard.

Once your text list has been created, you can start adding entries to it.

View your custom list

Each entry consists of a text item that you want to detect, along with metadata that helps the engine determine how and when this entry should be triggered. The following information is required:

Text: The text item you want to detect.
Language: The language to which the text item applies. If the same text appears in content identified as a different language, it will not be flagged. If you want the text item to be detected regardless of language, select all.
Match type: Defines how the detection engine should match the entry.
Choose exact match to detect the exact string only (case-insensitive, but without other variations).
Choose standard match to detect variations such as phonetic substitutions, repetitions, typos, leetspeak, and other obfuscation attempts. This option typically covers millions of variations and prevents users from bypassing detection by slightly modifying the word.
Category: A custom categorization label for the text item, allowing you to organize and filter entries more easily.

Add a new entry to your custom list

While most users only need a single text list, you can create multiple lists to apply different moderation criteria to different types of content.

To use a custom list, specify the corresponding list ID in the opt_textlist parameter of your API request.

Use the model (images)

If you haven't already, create an account to get your own API keys.

Moderate text in images

Let's say you want to moderate the following image:

You can either share a URL to the image, or upload the image file.

Option 1: Send image URL

Here's how to proceed if you choose to share the image URL:


curl -X GET -G 'https://api.sightengine.com/1.0/check.json' \
    -d 'models=text-content-2.0' \
    -d 'text_categories=sexual,insult,inappropriate,discriminatory,phone_number,email' \
    -d 'opt_lang=en,fr,es,de' \
    -d 'opt_countries=us,gb,fr,de' \
    -d 'api_user={api_user}&api_secret={api_secret}' \
    --data-urlencode 'url=https://sightengine.com/assets/img/examples/example-text-ocr-3.jpg'


# this example uses requests
import requests
import json

params = {
  'url': 'https://sightengine.com/assets/img/examples/example-text-ocr-3.jpg',
  'models': 'text-content-2.0',
  'text_categories': 'sexual,insult,inappropriate,discriminatory,phone_number,email',
  'opt_lang': 'en,fr,es,de',
  'opt_countries': 'us,gb,fr,de',
  'api_user': '{api_user}',
  'api_secret': '{api_secret}'
}
r = requests.get('https://api.sightengine.com/1.0/check.json', params=params)

output = json.loads(r.text)


$params = array(
  'url' =>  'https://sightengine.com/assets/img/examples/example-text-ocr-3.jpg',
  'models' => 'text-content-2.0',
  'text_categories' => 'sexual,insult,inappropriate,discriminatory,phone_number,email',
  'opt_lang' => 'en,fr,es,de',
  'opt_countries' => 'us,gb,fr,de',
  'api_user' => '{api_user}',
  'api_secret' => '{api_secret}',
);

// this example uses cURL
$ch = curl_init('https://api.sightengine.com/1.0/check.json?'.http_build_query($params));
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
$response = curl_exec($ch);
curl_close($ch);

$output = json_decode($response, true);


// this example uses axios
const axios = require('axios');

axios.get('https://api.sightengine.com/1.0/check.json', {
  params: {
    'url': 'https://sightengine.com/assets/img/examples/example-text-ocr-3.jpg',
    'models': 'text-content-2.0',
    'text_categories': 'sexual,insult,inappropriate,discriminatory,phone_number,email',
    'opt_lang': 'en,fr,es,de',
    'opt_countries': 'us,gb,fr,de',
    'api_user': '{api_user}',
    'api_secret': '{api_secret}',
  }
})
.then(function (response) {
  // on success: handle response
  console.log(response.data);
})
.catch(function (error) {
  // handle error
  if (error.response) console.log(error.response.data);
  else console.log(error.message);
});

See request parameter description

Parameter	Type	Description
url	string	URL of the image to analyze
models	string	comma-separated list of models to apply
text_categories	string	comma-separated list of moderation categories
opt_lang	string	comma-separated list of target languages (optional)
opt_countries	string	comma-separated list of target countries for phone number detection (optional)
opt_textlist	string	id of a custom list (disallow or allow list) (optional)
api_user	string	your API user id
api_secret	string	your API secret

Option 2: Send image file

Here's how to proceed if you choose to upload the image file:


curl -X POST 'https://api.sightengine.com/1.0/check.json' \
    -F 'media=@/path/to/image.jpg' \
    -F 'models=text-content-2.0' \
    -F 'text_categories=sexual,insult,inappropriate,discriminatory,phone_number,email' \
    -F 'opt_lang=en,fr,es,de' \
    -F 'opt_countries=us,gb,fr,de' \
    -F 'api_user={api_user}' \
    -F 'api_secret={api_secret}'


# this example uses requests
import requests
import json

params = {
  'models': 'text-content-2.0',
  'text_categories': 'sexual,insult,inappropriate,discriminatory,phone_number,email',
  'opt_lang': 'en,fr,es,de',
  'opt_countries': 'us,gb,fr,de',
  'api_user': '{api_user}',
  'api_secret': '{api_secret}'
}
files = {'media': open('/path/to/image.jpg', 'rb')}
r = requests.post('https://api.sightengine.com/1.0/check.json', files=files, data=params)

output = json.loads(r.text)


$params = array(
  'media' => new CurlFile('/path/to/image.jpg'),
  'models' => 'text-content-2.0',
  'text_categories' => 'sexual,insult,inappropriate,discriminatory,phone_number,email',
  'opt_lang' => 'en,fr,es,de',
  'opt_countries' => 'us,gb,fr,de',
  'api_user' => '{api_user}',
  'api_secret' => '{api_secret}',
);

// this example uses cURL
$ch = curl_init('https://api.sightengine.com/1.0/check.json');
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, $params);
$response = curl_exec($ch);
curl_close($ch);

$output = json_decode($response, true);


// this example uses axios and form-data
const axios = require('axios');
const FormData = require('form-data');
const fs = require('fs');

data = new FormData();
data.append('media', fs.createReadStream('/path/to/image.jpg'));
data.append('models', 'text-content-2.0');
data.append('text_categories', 'sexual,insult,inappropriate,discriminatory,phone_number,email');
data.append('opt_lang', 'en,fr,es,de');
data.append('opt_countries', 'us,gb,fr,de');
data.append('api_user', '{api_user}');
data.append('api_secret', '{api_secret}');

axios({
  method: 'post',
  url:'https://api.sightengine.com/1.0/check.json',
  data: data,
  headers: data.getHeaders()
})
.then(function (response) {
  // on success: handle response
  console.log(response.data);
})
.catch(function (error) {
  // handle error
  if (error.response) console.log(error.response.data);
  else console.log(error.message);
});

See request parameter description

Parameter	Type	Description
media	file	image to analyze
models	string	comma-separated list of models to apply
text_categories	string	comma-separated list of moderation categories
opt_lang	string	comma-separated list of target languages (optional)
opt_countries	string	comma-separated list of target countries for phone number detection (optional)
opt_textlist	string	id of a custom list (disallow or allow list) (optional)
api_user	string	your API user id
api_secret	string	your API secret

API response

The API will then return a JSON response with the following structure:

                  
                  
{
  "status": "success",
  "request": {
    "id": "req_22Qd0gUNmRH4GCYLvYtN6",
    "timestamp": 1512483673.1405,
    "operations": 1
  },
  "text": {
    "language": "en",
    "detected_categories": [
      "phone_number"
    ],
    "detections": {
      "phone_number": {
        "details": [
          {
            "country": "us",
            "match": "+1 800 222 2408"
          }
        ]
      }
    }
  },
  "media": {
      "id": "med_22Qdfb5s97w8EDuY7Yfjp",
      "uri": "https://sightengine.com/assets/img/examples/example-text-ocr-3.jpg"
  }
}

See response description

Successful Response

Status code: 200, Content-Type: application/json

Field	Type	Description
status	string	status of the request, either "success" or "failure"
request	object	information about the processed request
request.id	string	unique identifier of the request
request.timestamp	float	timestamp of the request in Unix time
request.operations	integer	number of operations consumed by the request
text	object	results for the model
media	object	information about the media analyzed
media.id	string	unique identifier of the media
media.uri	string	URI of the media analyzed: either the URL or the filename

Error

Status codes: 4xx and 5xx. See how error responses are structured.

Top-level information

text.language	Language used for the moderation rules applied to this media. The language is automatically detected based on the list provided in the opt_lang field.
text.detected_categories	List of triggered moderation categories. Provides a quick overview of all detected unwanted content to allow fast filtering.
text.detections	Detailed detection information per detected category.

Detections

For each detected category, the API returns additional information in the text.detections field, including the specific matches that triggered the category and their associated severity levels (if available).

Objects in text.detections have the following fields:

Category-level severity	Optional aggregated severity for a detected category, computed from individual matches.	severity
Details	List of matches with additional details for each match.	details

For each match, the available details depend on the category. Here are some examples of the information that may be provided for specific categories:

Matched text	The exact text that triggered a category.	match
Match-level severity	Optional severity assigned to a specific detected match.	severity
Phone number country	Country associated with a detected phone number.	country
Link category	Category of a detected link (e.g., unsafe, adult, gambling, etc.).	category

Use the model (videos)

Moderate text in videos

Option 1: Short video

Here's how to proceed to analyze a short video (less than 1 minute):


curl -X POST 'https://api.sightengine.com/1.0/video/check-sync.json' \
  -F 'media=@/path/to/video.mp4' \
  -F 'models=text-content-2.0' \
  -F 'text_categories=sexual,insult,inappropriate,discriminatory,phone_number,email' \
  -F 'opt_lang=en,fr,es,de' \
  -F 'opt_countries=us,gb,fr,de' \
  -F 'api_user={api_user}' \
  -F 'api_secret={api_secret}'


# this example uses requests
import requests
import json

params = {
  # specify the models you want to apply
  'models': 'text-content-2.0',
  'text_categories': 'sexual,insult,inappropriate,discriminatory,phone_number,email',
  'opt_lang': 'en,fr,es,de',
  'opt_countries': 'us,gb,fr,de',
  'api_user': '{api_user}',
  'api_secret': '{api_secret}'
}
files = {'media': open('/path/to/video.mp4', 'rb')}
r = requests.post('https://api.sightengine.com/1.0/video/check-sync.json', files=files, data=params)

output = json.loads(r.text)


$params = array(
  'media' => new CurlFile('/path/to/video.mp4'),
  // specify the models you want to apply
  'models' => 'text-content-2.0',
  'text_categories' => 'sexual,insult,inappropriate,discriminatory,phone_number,email',
  'opt_lang' => 'en,fr,es,de',
  'opt_countries' => 'us,gb,fr,de',
  'api_user' => '{api_user}',
  'api_secret' => '{api_secret}',
);

// this example uses cURL
$ch = curl_init('https://api.sightengine.com/1.0/video/check-sync.json');
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, $params);
$response = curl_exec($ch);
curl_close($ch);

$output = json_decode($response, true);


// this example uses axios and form-data
const axios = require('axios');
const FormData = require('form-data');
const fs = require('fs');

data = new FormData();
data.append('media', fs.createReadStream('/path/to/video.mp4'));
// specify the models you want to apply
data.append('models', 'text-content-2.0');
data.append('text_categories', 'sexual,insult,inappropriate,discriminatory,phone_number,email');
data.append('opt_lang', 'en,fr,es,de');
data.append('opt_countries', 'us,gb,fr,de');
data.append('api_user', '{api_user}');
data.append('api_secret', '{api_secret}');

axios({
  method: 'post',
  url:'https://api.sightengine.com/1.0/video/check-sync.json',
  data: data,
  headers: data.getHeaders()
})
.then(function (response) {
  // on success: handle response
  console.log(response.data);
})
.catch(function (error) {
  // handle error
  if (error.response) console.log(error.response.data);
  else console.log(error.message);
});

See request parameter description

Parameter	Type	Description
media	file	image to analyze
models	string	comma-separated list of models to apply
interval	float	frame interval in seconds, out of 0.5, 1, 2, 3, 4, 5 (optional)
api_user	string	your API user id
api_secret	string	your API secret

Option 2: Long video

Here's how to proceed to analyze a long video. Note that if the video file is very large, you might first need to upload it through the Upload API.


curl -X POST 'https://api.sightengine.com/1.0/video/check.json' \
  -F 'media=@/path/to/video.mp4' \
  -F 'models=text-content-2.0' \
  -F 'callback_url=https://yourcallback/path' \
  -F 'text_categories=sexual,insult,inappropriate,discriminatory,phone_number,email' \
  -F 'opt_lang=en,fr,es,de' \
  -F 'opt_countries=us,gb,fr,de' \
  -F 'api_user={api_user}' \
  -F 'api_secret={api_secret}'


# this example uses requests
import requests
import json

params = {
  # specify the models you want to apply
  'models': 'text-content-2.0',
  # specify where you want to receive result callbacks
  'callback_url': 'https://yourcallback/path',
  'text_categories': 'sexual,insult,inappropriate,discriminatory,phone_number,email',
  'opt_lang': 'en,fr,es,de',
  'opt_countries': 'us,gb,fr,de',
  'api_user': '{api_user}',
  'api_secret': '{api_secret}'
}
files = {'media': open('/path/to/video.mp4', 'rb')}
r = requests.post('https://api.sightengine.com/1.0/video/check.json', files=files, data=params)

output = json.loads(r.text)


$params = array(
  'media' => new CurlFile('/path/to/video.mp4'),
  // specify the models you want to apply
  'models' => 'text-content-2.0',
  // specify where you want to receive result callbacks
  'callback_url' => 'https://yourcallback/path',
  'text_categories' => 'sexual,insult,inappropriate,discriminatory,phone_number,email',
  'opt_lang' => 'en,fr,es,de',
  'opt_countries' => 'us,gb,fr,de',
  'api_user' => '{api_user}',
  'api_secret' => '{api_secret}',
);

// this example uses cURL
$ch = curl_init('https://api.sightengine.com/1.0/video/check.json');
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, $params);
$response = curl_exec($ch);
curl_close($ch);

$output = json_decode($response, true);


// this example uses axios and form-data
const axios = require('axios');
const FormData = require('form-data');
const fs = require('fs');

data = new FormData();
data.append('media', fs.createReadStream('/path/to/video.mp4'));
// specify the models you want to apply
data.append('models', 'text-content-2.0');
// specify where you want to receive result callbacks
data.append('callback_url', 'https://yourcallback/path');
data.append('text_categories', 'sexual,insult,inappropriate,discriminatory,phone_number,email');
data.append('opt_lang', 'en,fr,es,de');
data.append('opt_countries', 'us,gb,fr,de');
data.append('api_user', '{api_user}');
data.append('api_secret', '{api_secret}');

axios({
  method: 'post',
  url:'https://api.sightengine.com/1.0/video/check.json',
  data: data,
  headers: data.getHeaders()
})
.then(function (response) {
  // on success: handle response
  console.log(response.data);
})
.catch(function (error) {
  // handle error
  if (error.response) console.log(error.response.data);
  else console.log(error.message);
});

See request parameter description

Parameter	Type	Description
media	file	image to analyze
callback_url	string	callback URL to receive moderation updates (optional)
models	string	comma-separated list of models to apply
interval	float	frame interval in seconds, out of 0.5, 1, 2, 3, 4, 5 (optional)
api_user	string	your API user id
api_secret	string	your API secret

Option 3: Live-stream

Here's how to proceed to analyze a live-stream:


curl -X GET -G 'https://api.sightengine.com/1.0/video/check.json' \
    --data-urlencode 'stream_url=https://domain.tld/path/video.m3u8' \
    -d 'models=text-content-2.0' \
    -d 'callback_url=https://your.callback.url/path' \
    -d 'api_user={api_user}' \
    -d 'api_secret={api_secret}'


# this example uses requests
import requests
import json

params = {
  'stream_url': 'https://domain.tld/path/video.m3u8',
  # specify the models you want to apply
  'models': 'text-content-2.0',
  # specify where you want to receive result callbacks
  'callback_url': 'https://your.callback.url/path',
  'api_user': '{api_user}',
  'api_secret': '{api_secret}'
}
r = requests.post('https://api.sightengine.com/1.0/video/check.json', data=params)

output = json.loads(r.text)


$params = array(
  'stream_url' => 'https://domain.tld/path/video.m3u8',
  // specify the models you want to apply
  'models' => 'text-content-2.0',
  // specify where you want to receive result callbacks
  'callback_url' => 'https://your.callback.url/path',
  'api_user' => '{api_user}',
  'api_secret' => '{api_secret}',
);

// this example uses cURL
$ch = curl_init('https://api.sightengine.com/1.0/video/check.json');
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, $params);
$response = curl_exec($ch);
curl_close($ch);

$output = json_decode($response, true);


// this example uses axios and form-data
const axios = require('axios');
const FormData = require('form-data');
const fs = require('fs');

data = new FormData();
data.append('stream_url', 'https://domain.tld/path/video.m3u8');
// specify the models you want to apply
data.append('models', 'text-content-2.0');
// specify where you want to receive result callbacks
data.append('callback_url', 'https://your.callback.url/path');
data.append('api_user', '{api_user}');
data.append('api_secret', '{api_secret}');

axios({
  method: 'post',
  url:'https://api.sightengine.com/1.0/video/check.json',
  data: data,
  headers: data.getHeaders()
})
.then(function (response) {
  // on success: handle response
  console.log(response.data);
})
.catch(function (error) {
  // handle error
  if (error.response) console.log(error.response.data);
  else console.log(error.message);
});

See request parameter description

Parameter	Type	Description
stream_url	string	URL of the video stream
callback_url	string	callback URL to receive moderation updates (optional)
models	string	comma-separated list of models to apply
interval	float	frame interval in seconds, out of 0.5, 1, 2, 3, 4, 5 (optional)
api_user	string	your API user id
api_secret	string	your API secret

Moderation result

The Moderation result will be provided either directly in the request response (for sync calls, see below) or through the callback URL your provided (for async calls).

Here is the structure of the JSON response with moderation results for each analyzed frame under the data.frames array:

            
                  
{
  "status": "success",
  "request": {
    "id": "req_gmgHNy8oP6nvXYaJVLq9n",
    "timestamp": 1717159864.348989,
    "operations": 21
  },
  "data": {
    "frames": [
      {
        "info": {
          "id": "med_gmgHcUOwe41rWmqwPhVNU_1",
          "position": 0
        },
        "text": {
          "language": "en",
          "detected_categories": [
            "phone_number"
          ],
          "detections": {
            "phone_number": {
              "details": [
                {
                  "country": "us",
                  "match": "+1 800 222 2408"
                }
              ]
            }
          }
        },
      },
     ...
    ]
  },
  "media": {
    "id": "med_gmgHcUOwe41rWmqwPhVNU",
    "uri": "yourfile.mp4"
  },
}

You can use the classes under the text object to analyze text content in the video.

Top-level information

text.language	Language used for the moderation rules applied to this media. The language is automatically detected based on the list provided in the opt_lang field.
text.detected_categories	List of triggered moderation categories. Provides a quick overview of all detected unwanted content to allow fast filtering.
text.detections	Detailed detection information per detected category.

Detections

Objects in text.detections have the following fields:

Category-level severity	Optional aggregated severity for a detected category, computed from individual matches.	severity
Details	List of matches with additional details for each match.	details

For each match, the available details depend on the category. Here are some examples of the information that may be provided for specific categories:

Matched text	The exact text that triggered a category.	match
Match-level severity	Optional severity assigned to a specific detected match.	severity
Phone number country	Country associated with a detected phone number.	country
Link category	Category of a detected link (e.g., unsafe, adult, gambling, etc.).	category

On this page

Text Moderation in Images and Videos

Overview

Customization

Listing Moderation Categories

Choosing Languages

Filtering by Severity

Providing Custom Lists

Moderation categories

Sexual & Suggestive

Insults & Personal Attacks

Discriminatory & Hate

Inappropriate Language & Swear Words

Grawlix

Email Addresses

Phone Numbers

Usernames

Social Security Numbers

IP Addresses

Link & URLs

Extremism

Weapons & Firearms

Medical Drugs

Recreational Drugs

Self-Harm & Suicide

Violence & Threats

Platform Evasion & Circumvention Attempts

Off-Platform Mentions

Content Trade & Solicitation

Money Requests & Transactions

Grooming

Minor Presence

Disallow list (custom)

Language support

Detection strength

Severity levels

Custom disallow and allow lists

Use the model (images)

Moderate text in images

Option 1: Send image URL

Option 2: Send image file

API response

Successful Response

Error

Top-level information

Detections

Use the model (videos)

Moderate text in videos

Option 1: Short video

Option 2: Long video

Option 3: Live-stream

Moderation result

Top-level information

Detections