AI Content Moderator API

AI Content Moderator API

The AI Content Moderator API is a powerful tool for machine-assisted moderation of multilingual text. Utilizing Microsoft Azure Cognitive Services, this API detects potentially offensive or unwanted content, including profanity, in over 100 languages. It has a maximum text length limit of 1024 characters, and any content exceeding this limit will result in an error code being returned.

API description

About the API: 

The AI Content Moderator API is a powerful solution for moderating multilingual text with machine assistance. Powered by Microsoft Azure Cognitive Services, this API is designed to detect potentially offensive or unwanted content within text data. It offers a comprehensive suite of moderation tools to ensure that user-generated content aligns with community guidelines, content policies, and legal requirements.

One of the key features of the Content Moderator API is its ability to detect profanity in over 100 languages. By leveraging advanced language processing techniques and a vast profanity database, the API can accurately identify and flag inappropriate language, helping maintain a safe and respectful environment for users.

When utilizing the API, it's important to note that the maximum length of text that can be processed is 1024 characters. This limit ensures efficient and reliable moderation while keeping within the operational constraints. If the content passed to the API exceeds this size limit, the API will return an error code, indicating that the content should be shortened or split into smaller segments for processing.

The Content Moderator API can be seamlessly integrated into various platforms and applications to automate content moderation workflows. It enables developers to proactively moderate user-generated content in real-time, preventing the display or dissemination of offensive, abusive, or inappropriate content.

This API is particularly useful for social media platforms, online communities, chat applications, forums, and any other platforms that rely on user-generated content. By incorporating the Content Moderator API, these platforms can ensure compliance with their content policies and community guidelines, maintaining a positive user experience and safeguarding their brand reputation.

Furthermore, the AI Content Moderator API is equipped with additional capabilities beyond profanity detection. It offers features such as text classification, which enables categorization of content into predefined categories, and text moderation, which helps identify and filter out content that contains potentially sensitive topics or discussions.

The API also supports customized moderation rules, allowing developers to define specific criteria for flagging or filtering content based on their unique requirements. This flexibility ensures that the moderation process aligns with the specific context and guidelines of each platform.

In conclusion, the AI Content Moderator API powered by Microsoft Azure Cognitive Services provides an efficient and reliable solution for machine-assisted moderation of multilingual text. With its ability to detect profanity in over 100 languages, integration of this API can help platforms maintain a safe and respectful environment for users, adhere to content policies, and meet legal requirements.

 

What this API receives and what your API provides (input/output)?

Pass the text that you want to moderate, and receive its analysis.  

 

What are the most common uses cases of this API?

  1. Social Media Moderation: The AI Content Moderator API can be integrated into social media platforms to automatically detect and filter out offensive or inappropriate user-generated content. It helps maintain a safe and respectful online environment by identifying and removing content that violates community guidelines or contains profanity.

  2. Online Community Forums: Community forums often rely on user-generated content for discussions. By implementing the Content Moderator API, forum administrators can ensure that conversations remain civil and respectful. The API can detect and flag potentially offensive language, allowing moderators to review and take appropriate actions.

  3. Chat Applications: Chat applications, especially those open to public conversations, can benefit from the Content Moderator API to prevent the spread of offensive or abusive messages. The API's profanity detection capability can automatically filter out inappropriate language in real-time, creating a more positive and inclusive chat experience.

  4. User Review Platforms: Platforms that feature user reviews, such as product review websites or app stores, can use the Content Moderator API to filter out reviews containing profanity or inappropriate content. This ensures that the displayed reviews maintain a high standard of professionalism and usefulness for other users.

  5. Content Filtering in Online Marketplaces: Online marketplaces that allow user-generated content, such as product descriptions or comments, can leverage the Content Moderator API to filter out inappropriate or offensive content. By implementing the API, marketplace operators can maintain a positive and trustworthy environment for buyers and sellers, reducing the risk of encountering inappropriate or misleading content.

  6. E-Learning Platforms: E-learning platforms often include user-generated content in the form of discussions or comments. By utilizing the Content Moderator API, these platforms can automatically identify and remove offensive or inappropriate language, creating a safe and respectful learning environment for students and educators.

 

Are there any limitations to your plans?

Besides the number of API calls, there is no other limitation

API Documentation

Endpoints


When using the API, text can be at most 1024 characters long. If the content passed to the text API exceeds the size limits, the API will return an error code that informs about the issue.



                                                                            
POST https://zylalabs.com/api/2175/ai+content+moderator+api/1981/moderation
                                                                            
                                                                        

Moderation - Endpoint Features
Object Description
text [Required] Text to moderate
Test Endpoint

API EXAMPLE RESPONSE

       
                                                                                                        
                                                                                                                                                                                                                            {"CmTextResult":{"indetified_language":"eng","original_text":"Is this a garbage or crap email [email protected], phone: 6657789887, IP: 255.255.255.255, 1 Microsoft Way, Redmond, WA 98052. These are all UK phone numbers, the last two being Microsoft UK support numbers: +44 870 608 4000 or 0344 800 2400 or 0800 820 3300. Also, 999-99-9999 looks like a social security number (SSN).","auto_corrected_text":"Is this a garbage or crap email [email protected], phone: 6657789887, IP: 255.255.255.255, 1 Microsoft Way, Redmond, WA 98052. These are all UK phone numbers, the last two being Microsoft UK support numbers: +44 870 608 4000 or 0344 800 2400 or 0800 820 3300. Also, 999-99-9999 looks like a social security number (SSN).","classification":{"category1":{"score":9.763961088538053e-07},"category2":{"score":0.12747249007225037},"category3":{"score":0.9879999756813049},"review_recommended":true},"personal_information":{"email":[{"detected":"[email protected]","sub_type":"Regular","text":"[email protected]","index":32}],"ssn":[],"ipa":[{"sub_type":"IPV4","text":"255.255.255.255","index":72}],"phone":[{"country_code":"US","text":"6657789887","index":56},{"country_code":"US","text":"870 608 4000","index":210},{"country_code":"UK","text":"+44 870 608 4000","index":206},{"country_code":"UK","text":"0344 800 2400","index":226},{"country_code":"UK","text":"0800 820 3300","index":243}],"address":[{"text":"1 Microsoft Way, Redmond, WA 98052","index":89}]},"profanity":[{"original_index":21,"term":"crap"}]}}
                                                                                                                                                                                                                    
                                                                                                    

Moderation - CODE SNIPPETS


curl --location --request POST 'https://zylalabs.com/api/2175/ai+content+moderator+api/1981/moderation?text=Is this a garbage or crap email [email protected], phone: 6657789887, IP: 255.255.255.255, 1 Microsoft Way, Redmond, WA 98052. These are all UK phone numbers, the last two being Microsoft UK support numbers: +44 870 608 4000 or 0344 800 2400 or 0800 820 3300. Also, 999-99-9999 looks like a social security number (SSN).' --header 'Authorization: Bearer YOUR_API_KEY' 

    

API Access Key & Authentication

After signing up, every developer is assigned a personal API access key, a unique combination of letters and digits provided to access to our API endpoint. To authenticate with the AI Content Moderator API REST API, simply include your bearer token in the Authorization header.

Headers

Header Description
Authorization [Required] Should be Bearer access_key. See "Your API Access Key" above when you are subscribed.


Simple Transparent Pricing

No long term commitments. One click upgrade/downgrade or cancellation. No questions asked.

๐Ÿš€ Enterprise
Starts at $10,000/Year

  • Custom Volume
  • Dedicated account manager
  • Service-level agreement (SLA)

Customer favorite features

  • โœ”๏ธŽ Only Pay for Successful Requests
  • โœ”๏ธŽ Free 7-Day Trial
  • โœ”๏ธŽ Multi-Language Support
  • โœ”๏ธŽ One API Key, All APIs.
  • โœ”๏ธŽ Intuitive Dashboard
  • โœ”๏ธŽ Comprehensive Error Handling
  • โœ”๏ธŽ Developer-Friendly Docs
  • โœ”๏ธŽ Postman Integration
  • โœ”๏ธŽ Secure HTTPS Connections
  • โœ”๏ธŽ Reliable Uptime

The API utilizes advanced language processing techniques and a comprehensive profanity database to identify and flag offensive or inappropriate language in text data.

Yes, the Content Moderator API is capable of detecting profanity in over 100 languages, ensuring comprehensive coverage for multilingual content moderation.

The API can moderate various forms of user-generated text content, such as comments, reviews, messages, forum posts, and more.

Yes, the AI Content Moderator API is designed to be easily integrated into various platforms and applications, including social media platforms, chat applications, online communities, and more.

Yes, the maximum length of text that can be processed by the API is 1024 characters. Any content exceeding this limit will result in an error code being returned.

Zyla API Hub is, in other words, an API MarketPlace. An all-in-one solution for your developing needs. You will be accessing our extended list of APIs with only your user. Also, you won't need to worry about storing API keys, only one API key for all our products is needed.

Prices are listed in USD. We accept all major debit and credit cards. Our payment system uses the latest security technology and is powered by Stripe, one of the worldโ€™s most reliable payment companies. If you have any trouble with paying by card, just contact us at [email protected]

Sometimes depending on the bank's fraud protection settings, a bank will decline the validation charge we make when we attempt to be sure a card is valid. We recommend first contacting your bank to see if they are blocking our charges. If more help is needed, please contact [email protected] and our team will investigate further

Prices are based on a recurring monthly subscription depending on the plan selected โ€” plus overage fees applied when a developer exceeds a planโ€™s quota limits. In this example, you'll see the base plan amount as well as a quota limit of API requests. Be sure to notice the overage fee because you will be charged for each additional request.

Zyla API Hub works on a recurring monthly subscription system. Your billing cycle will start the day you purchase one of the paid plans, and it will renew the same day of the next month. So be aware to cancel your subscription beforehand if you want to avoid future charges.

Just go to the pricing page of that API and select the plan that you want to upgrade to. You will only be charged the full amount of that plan, but you will be enjoying the features that the plan offers right away.

Yes, absolutely. If you want to cancel your plan, simply go to your account and cancel on the Billing page. Upgrades, downgrades, and cancellations are immediate.

You can contact us through our chat channel to receive immediate assistance. We are always online from 9 am to 6 pm (GMT+1). If you reach us after that time, we will be in contact when we are back. Also you can contact us via email to [email protected]

 Service Level
100%
 Response Time
1,312ms

Category:

NLP

Tags:


Related APIs