In this session, we will examine 5 different ML API’s offered by AWS to do things like synthesize speech to text, translate English to French, or even analyze text for sentiment analysis and more. To take advantage of these API’s all you need is basic knowledge of how to use API’s and a UI to call them from which we build live for you in React, and talk about how to manage handling credentials when performing client side API requests.

Within our React boilerplate, users will be able to leave the talk with functional code snippets and an understanding of how to use them for:

  • Text to speech: pass in text and receive an audio file as an output with variable voices/languages
  • Sentiment analysis: pass in text and receive sentiment, key phrases, and language
  • Transcription: pass in audio (over mic or static file) and receive a text transcription as an output
  • Translate: pass text of one language and have it translated to another
  • Object recognition: send in a photo and receive the objects found in the photo