AI Services

2. API Capabilities

Cloud Speech API 

  • Enables developers to convert audio to text.
  • Recognizes over 80 languages and variants.
  • Can be used to transcribe the text of users, dictating in applications microphone, enable command and control through voice or transcribe audio files.

Cloud Natural Language API 

  • Offers a variety of natural language understanding technologies to developers.
  • Can do syntax analysis, breaking down sentences supplied by users into tokens, identify the nouns, verbs, adjectives, and other parts of speech and figure out the relationships among the words.
  • Can understand the overall sentiment expressed in a block of text.

Cloud Translation API

  • Provides a simple, programmatic interface for translating an arbitrary string into a supported language.
  • Automatically detects the source language.

Cloud Natural Language API

  • Parses text and flag mentions of people, organizations, locations, events, products, and media.
  • Can do entity recognition.
  • Supports multiple languages, including English, Spanish, and Japanese.

Cloud Vision API

  • Classifies images into thousands of categories, detects individual objects within images and finds and reads printed words contained within images.
  • Enables developers to understand the content of an image.
  • Can be used to build metadata on image catalog, moderate offensive content or even do image sentiment analysis.

Cloud Video Intelligence API

  • Enables users to identify nouns within videos and when they occur.
  • Annotates videos in a variety of formats.
  • Can be used to make video content searchable and discoverable.