Moderate user-generated images efficiently and in real-time with our API.

#### Detect any type of unwanted content in Images
- Easily choose what models you want to apply. 
- Create your own Moderation rules. 
- Change them at any time.
#### Detect 8 levels of nudity and suggestiveness
Nudity is not a binary concept. Your audience and your brand need a custom and fine-grained way to filter what's acceptable to you and what's not. With our pre-trained priorietary Nudity Models, easily decide exactly what you accept and what you reject.
#### Detect 20+ offensive, violent or otherwise inappropriate concepts
Pick and choose from our list of fine-grained models to decide what's appropriate and what's not. You decide what you want to filter.
#### Highly customizable. Define your own thresholds and your own custom rules
Different communities need different moderation rules. Easily set up rules that work best with your community and your brand.
#### High Accuracy, Fine Grained Results
Your customers expect their content to be validated correctly and immediately — not eventually.
We constantly monitor our accuracy and speeds.

Image Moderation API

Classifies images and detects children, teenagers and babies automatically.

#### What does it do?
Minor Detection API will classify pictures and returns True if it is able to detect a child, teenager or a baby. This is useful if you run a business that needs heavy moderation of preventing users from posting pictures of minors.

#### How it works:
If a minor is detected in the image, a confidence score will be calculated for the result and returned. A score of 1 would mean that the content almost certainly contains a minor in it while a score close to 0 would imply that we are not that sure. In most cases, value of 0.5 is safe to go.

#### Where to use it
Minor Detection API is predominantly used by social media and news sites where a massive amount of user generated data needs to be moderated lightning fast. Instead of manually approving all uploaded images or hosting inappropriate images until someone reports, using Minor Detection API helps you prevent any complaints.

#### Key Features
- Fast response time.
- Pre-trained models.
- Auto rotates images.
- Predicts a confidence score.

Minor Detection API

Performs BRISQUE algorithm on the image and predicts an image quality score.

#### What is Image Quality Assessment?
It is easy to take photos, but it is difficult to take good ones. It requires good composition and good lighting. The right lens and top quality hardware can make a big difference. Most importantly, a high quality photo requires good taste and judgment. You need an expert eye. But is there a mathematical measure of quality that constitutes this human judgment?

There is a scientific method called BRISQUE (Blind/Referenceless Image Spatial Quality Evaluator ) which is a no-reference image quality score well-accepted in the market. This API is a scalable and performant implementation of this method.

#### Use cases
- Determining the best image of the product to display on the front page.
- Sort the products/listings based on the image quality score on your e-commerce site.
- Show only the high-quality images for adverts.
- Only permitting high-quality images for your listing/product.

#### Key Features
- Fast and scalable.
- No human touch.
- Privacy Compliant.
- Pre-trained models.

Image Quality Assessment API

#### What does our API do?
Classifier computes a score on a 1 to 5 scale for the content passed to it. A score of 5 would mean that the content is most likely violence while a score close to 1 would imply the content is safe to be published. In most cases, value of 4 is safe to go.

#### Use cases
This API is useful for apps containing direct messaging features, as they often monitor content as it comes in. Rather than reviewing all content manually, Violence Detection API lets you automate the content approval process.

This API also works for cartoon images containining violence.

#### Key Features
- Pre-trained model.
- Ability to work on cartoons and hand drawings.
- Predicts if a gun is in shooting position or not.
- Fast and efficient.

Violence Detection API

Tags and classifies visual content using machine learning at a glance.

#### How does it work?
Image Labeling API makes it easy to extract labels/tags from your images and detect for specific content out-of-the-box. Our pre-trained models enable you to analyze images for objects, colors, food, explicit content and other subjects for insights into your visual content.

We use deep learning algorithms to analyze images for scenes, objects, and other content. The response includes keywords that provide information about the content.

#### What can you do with our API?
Image labeling gives you insight into the content of images. When you use the API, you get a list of the entities that were recognized: people, things, places, activities, and so on. Each label found comes with a score that indicates the confidence the ML model has in its relevance. With this information, you can perform tasks such as automatic metadata generation and content moderation.

#### Key Features
- Full privacy.
- Pre-trained models.
- Accurate extractions.

Image Labeling API

Recognizes and reads the text embedded in images.

#### How does it work?
Image to Text API uses a neural net (LSTM) based OCR engine which is focused on line recognition, but also supports recognizing the character patterns. It supports both handwriting and printed materials.

#### OCR
There are two annotation features that support optical character recognition (OCR):

- **TEXT_DETECTION** detects and extracts text from any image. For example, a photograph might contain a street sign or traffic sign. The JSON includes the entire extracted string, as well as individual words, and their bounding boxes.
- **DOCUMENT_TEXT_DETECTION** also extracts text from an image, but the response is optimized for dense text and documents. The JSON includes page, block, paragraph, word, and break information.

#### Key Features
- Works with handwriting.
- Multi-lingual.
- Lightning speed.
- Pre-trained models.

Image to Text API

Enterprise grade "natural language processing" (NLP) tools with a simple, yet powerful API.

### Main Functionalities
- **Tokenizer:** Segmenting text into words, punctuations marks etc. This is done by applying rules specific to each language. Each Doc consists of individual tokens, and we can iterate over them.
- **Visualizer:** Visualizing a dependency parse or named entities in a text is not only a fun NLP demo – it can also be incredibly helpful in speeding up development and debugging your code and training process.
- **Lemmatization:** Assigning the base forms of words. 
- **Similarity:** This API is used to compare two texts, and make a prediction of how similar they are. Predicting similarity is useful for building recommendation systems or flagging duplicates.
- **Named Entity Extraction:** A named entity is a “real-world object” that’s assigned a name – for example, a person, a country, a product or a book title. spaCy can recognize various types of named entities in a document, by asking the model for a prediction.
- **Language Detection:** Detects the human language of any given text

#### Key Features:
- Perform NLP tasks without complex formulas.
- Pre-trained statistical models.
- Ability perform NLP operations in 6 languages.
- Visualization capabilities.
- No background NLP know-how needed.
- Predictive modeling.

NLP API

Given a text, it can be automatically classified in categories.

In Natural Language Processing there is a concept known as Sentiment Analysis. Given a movie review or a tweet, it can be automatically classified in categories. These categories can be user defined (positive, negative) or whichever classes you want.

In case of sentiment analysis, even humans cannot agree on 100% of the cases due to linguistic ambiguities like sarcasm. However state of the art sentiment analysis algorithms trained by thousands of real life examples perform on par with humans.

#### So what does our API do?
This API comes pre-trained with tens of thousands of APIs, carefully classified as positive or negative. You don't need to deal with training any model. Just call the API and go!

This API will also identify text with HTML code in it. Just send the HTML text without any worries.

#### Use Cases for Sentiment Analysis
Brands are relying heavily on analyzing social media monitoring and Sentiment Analysis API in order to measure return on investment (ROI) of their marketing efforts. You can also apply thematic analysis to determine the features on which the customers are talking about the most.
#### Key Features
- Pre-trained statistical models
- Ease of use

Sentiment Analysis API

Fast machine translation API at reasonable prices.

#### What does it do?
The Lecto Translation API provides the following endpoints. For details, please refer to sub-sections below which give details and request/response examples for each endpoint.
- **Translates text.** Batch translate array of texts into multiple target languages.
- **Translates JSON Payloads.** Translate JSON values from JSON formatted strings into multiple target languages, with protected keys feature available.
- **Detect Language.** Send array of source texts in request body and receive JSON response with the detected language codes.
- **List Languages.** We support more than 90 languages at present as follows. The language codes presented are in ISO-639-1 format unless stated otherwise below.

#### Features
- Fast, high quality Translation API powered by Neural Machine Translation models.
- Free Translation API plan with paid plans as low as $0.3 per million characters.
- Text/HTML/JSON translation
- Multiple source texts and target languages in a single request.
- Protected JSON values: Skip translations as desired with JSON data payload.

Lecto Translation API

Find the perfect domain name for your website with NLP, improved search and automated whois lookups.

### Why Use our API?
One of the very first steps of building a website is to choose a domain name — one that’s memorable, and that tells people who you are. It’s the first part of your site that people will encounter, so make it count!

Searching for a domain name manually can be very exhausting and time-consuming when we consider the number of registered domain names on the Internet (over 360 million). You might even think all good names are already taken.

To make sure you find the right domain that is available, we’ve built Domain Name Discovery API. We've been processing more than half a million whois lookups for years in order to find an undiscovered domain name that might be valuable. This is the API we've put our years of experience on. We hope everyone will benefit from it.

#### How does it work?
Domain Name Discovery API just needs a search term in order to operate. It analyzes the search term and suggests the best domain name candidates by applying many techniques.

#### Key Featues
- Fast and reliable
- NLP based name prediction
- Automated Whois lookups
- Sentiment Analysis



The best machine learning APIs