AI/ML Predictions

The Predictions category provides a solution for using AI and ML cloud services to enhance your application. Some supported use cases:

Convert text to speech
Transcribe audio to text
Translate text from one language to another
Identify text from an image
Identify entities from an image
Identify real world objects from an image
Interpret text

Predictions is broadly organized into 3 key use cases - Identify, Convert, and Interpret - which are available in the client API as well as CLI workflows.

Identify will find text (words, tables, pages from a book), entities (faces and/or celebrities) from images. You can also identify real world landmarks or objects such as chairs, desks, etc. which are referred to as “labels” from images.
Convert allows you to translate text from one source language to a target language. You can also generate speech audio from text input. Lastly, you can take an audio input and transcribe it using a websocket stream.
Interpret allows you to analyze text for language, entities (places, people), key phrases, sentiment (positive, neutral, negative), and syntax (pronouns, verbs, adjectives).

Some common use cases are listed below, as well as an advanced workflow which allows you to perform dynamic image indexing from a connected s3 bucket.

Predictions comes with built-in support for Amazon Translate, Amazon Polly, Amazon Transcribe, Amazon Rekognition, Amazon Textract, and Amazon Comprehend.

Note: Predictions also supports generic invocation of SageMaker Inference API from a native (iOS/Android) application.