ProgrammableWeb's Most Clicked, Shared and Talked About APIs of 2019: Cognitive Computing

Cognitive Computing is next up in our series about the Most Interesting APIs added to ProgrammableWeb in 2019. Cognitive Computing APIs encompass Artificial Intelligence (AI), Machine Learning (ML), Recognition, Speech, Voice, Natural Language Processing, Predictions, Algorithms, Sentiment and other disciplines that attempt to simulate human thought process.

AI is not without its problems, but that hasn't stopped it from being one of the largest trends in technology at the moment. Just about every sector has seen AI adoption by multiple companies, including Security, the Auto industry, Business, Transportation, Education, and even Agriculture. And many of the movers and shakers in the industry have released tools this past year to ease the process for developers adding machine learning and AI functions to applications.

The following APIs made our list because our readers, followers, and editors singled them out as Interesting APIs in Artificial Intelligence, Machine Learning, and other Cognitive Computing categories.

Rosto provides facial detection services using machine learning. The Rosto APITrack this API provides face detection, age detection, gender detection, emotion detection, multi-face detection, landmark detection, glasses detection, smile detection, hair segmentation (still in beta), head-pose calculation, and ethnicity detection.

Microsoft Azure Personalizer APITrack this API allows developers to choose the best experience for their users, by learning from their real-time behavior. It is an AI service that delivers a personalized User Experience to prioritize relevant content and user experiences, improve application satisfaction, usability, and more.

Aito is a predictive database for developers. The APITrack this API enables developers to manage uploads and operations in the database. It provides JSON formats and developers can authenticate with an API Key. Aito aims to replace the current machine learning tools that have a steep learning curve and generate single-purpose models.


Screenshot: provides speech recognition, human transcription, and speech-to-text transcription services. The APITrack this API provides speech-to-text recognition services that can make audio and video content searchable and accessible. automatically adds punctuation and capitalization to transcripts to make them easy to read. It can recognize multiple speakers and attribute text to each. Timestamps are given for each word.

Google Firebase provides tools to develop applications. The Firebase ML Kit APITrack this API offers indirect access to ML Kit iOS and Android SDKs. The SDKs allow users to apply machine learning technologies in mobile applications incorporating the Google Cloud Vision APITrack this API, TensorFlow Lite, and the Android Neural Networks APITrack this API. This technology arms mobile apps with text recognition, face detection, barcode scanning, image labeling and more.

IBM Watson Assistant APITrack this API allows developers to interact with IBM Watson's service for integrating a branded assistant into a device, application, or channel. The assistant connects to existing customer engagement resources to include them in interactions with customers. This service is available in many languages including English, Chinese, Arabic, Japanese, Spanish, Italian, and more.

Intenseye provides computer vision services for video and image processing and image recognition. The Intenseye APITrack this API offers video analytics data in JSON format. With the API, developers can track objects and extract information from videos and cameras. API methods are available to manage camera functions, video task functions, image detection functions and more.

Plate Recognizer provides an API for fast Automatic License Plate Recognition (ALPR). The Plate Recognizer APITrack this API helps applications to read license plates from images, aiming to help parking enforcement, neighborhood safety, and parking management.

CarNET APITrack this API can identify vehicle make, model and generation by photo recognition. The service recognizes 300 car brands and 2500 models and is customizable.

Speechace provides speech recognition services to aid in learning languages. The Speechace APITrack this API uses speech recognition to score pronunciation and fluency. For longer speech, the API returns a speaking fluency score and estimated International English Language Testing System (IELTS) and Pearson Test of English (PTE) Speaking scores.

Video: Speechace/Vimeo

Neuromation provides customized AI and machine learning solutions designed for enterprise. Neuromation supports AI-powered cameras, object detection and classification, medical imaging, industrial robots, and computer vision systems. The Neuro Platform is a machine learning development tool enabling rapid model iteration. This indirect API is accessible through SDKs.

TheySay provides sentiment analysis services and products. The TheySay PreCeive APITrack this API enables developers to integrate text analytics into their applications without having to figure out natural language processing for themselves. The API can be used to mix-and-match TheySay's text analysis processors—including sentiment analysis, speculation detection, part-of-speech tagging, dependency parsing, and more—for use in third-party applications.

OpenAI is a non-profit AI research company that provides solutions for safe artificial intelligence. The OpenAI Gym APITrack this API is a local REST API to the gym open-source Library, which provides an environment for developing reinforcement learning algorithms.

Chooch is an artificial intelligence (AI) training platform for visual recognition. The Chooch REST APITrack this API recognizes objects and concepts in videos and images from pre-trained models. This API is compatible with livestreams and live tagging for accurate facial recognition and image recognition.

Chooch API provides custom image, object, and facial recognition for applications

Chooch API provides custom image, object, and facial recognition for applications. Screenshot: Chooch Intelligence Technologies

Vemity is a provider of artificial intelligence and deep learning that offers AI tools for classification, regression analysis, and forecasting. The Vemity APITrack this API is used to incorporate artificial intelligence in any project by creating, training, and connecting models.

deepgreen AI provides computer vision for agriculture. The deepgreen Plant Diagnosis APITrack this API is used to detect pests, diseases, and nutrient deficiencies in crops. This API can be utilized by a variety of mobile applications and equipment, such as LED lighting, irrigation systems, tractors, and drones.

Visionati supports recognition services for developers to programmatically analyze images and videos from Web, Social, YouTube, Vimeo and more. The Visionati APITrack this API enables developers to get data from images and videos including tags, faces, brands, colors, and text. Visionati automatically detects nudity, violence and other sensitive content from video or images.

Visionati uses one API call to return data about images or video frames
Visionati uses one API call to return data about images or video frames. Screenshot: Visionati


Amazon Alexa Music Skill APITrack this API has been generally available in the Alexa Skills Kit since November 2018. The API enables music service providers such as Spotify or Pandora to add music services to Alexa-powered devices. The Alexa Music Skill API also enables devices to understand a user's voice commands to play music. For example, a user could say, "Alexa, play 'I Can See For Miles' by The Who" to hear that particular song.

Intento ( provides a single interface to several cognitive AI models and vendors. The Intento APITrack this API provides JSON responses translating text, tagging images, sentiment analysis, Optical Character Recognition (OCR), and speech transcription. It works with AI APIs from many service providers including Baidu Classify, Alibaba Cloud, Microsoft Computer Vision, Algorithmia Sentiment Analysis, Ayien Text Analysis, AWS Rekognition, Twinword Sentiment Analysis, Salesforce Einstein, Google Cloud Vision, IBM Watson Cloud Visual Recognition and others.

Bespoken provides tools and testing for voice software like Amazon's Alexa. The Bespoken APITrack this API enables users to interact with end-to-end testing services for voice apps. With the API, developers can implement voice ID, async mode, location, conversation ID, and screen mode.

Rasa is a service for creating artificial intelligence assistants for text and voice platforms. The Rasa APITrack this API is REST-based and supports methods for events that modify the internal state of dialogs. JSON is the preferred response format.

Lyrebird provides a service to create realistic, custom artificial voices. The Lyrebird Vocal Avatar APITrack this API provides a way to integrate artificial voices in products and services. The API enables developers to integrate the digital voice of users, return basic user information, generate an audio file and more.

Lyrebird API

Screenshot: Lyrebird

Datafinder is a predictive marketing tool that helps users build predictive models, score leads, generate prospect lists, analyze marketing data and append consumer and business data. The Datafinder Data APITrack this API enables registered developers to access consumer data, contact details, demographic information, purchase interests, education level, family status, financial details, and social insights.

Veritone is an "operating system for artificial intelligence" designed to improve media, legal, and government experiences. The Veritone GraphQL APITrack this API offers mutable query support associated with aiWARE for artificial intelligence. The API can be used to update subscriptions, manage engines, update assets, and more.

Be sure to read the next Artificial Intelligence article: January's DC-Area API Meetup to Feature Talk on the Role of APIs in AI Success