AWS Certified AI PractitionerAWS Services for AI/ML and Generative AIHard

A media company provides live sports commentary in multiple languages. They want to automatically translate the live audio commentary into text in several target languages with minimal delay, ensuring that global viewers can follow the game in their preferred language. Which AWS service should they use to achieve this real-time, multi-language translation of spoken content?

  1. AAmazon Translate
  2. BAmazon Transcribe
  3. CAmazon Polly
  4. DA combination of Amazon Transcribe and Amazon Translate.
Show answer & explanation

Correct answer: D. A combination of Amazon Transcribe and Amazon Translate.

To translate live *spoken* commentary, first the audio needs to be converted to text, which is done by Amazon Transcribe. Then, this transcribed text can be translated into multiple target languages in real-time using Amazon Translate. This combination provides the full end-to-end solution for real-time spoken language translation.

Why the other options are wrong

  • A. Amazon Translate translates text from one language to another, but cannot process audio directly.
  • B. Amazon Transcribe converts speech to text, but does not perform translation itself.
  • C. Amazon Polly converts text to lifelike speech, which is the opposite of what is needed here (speech to text then translate).

AWS Real-Time Spoken Language Translation

Achieving real-time translation of spoken audio into text in multiple target languages by combining Amazon Transcribe and Amazon Translate.

  • Amazon Transcribe converts live audio to text.
  • Amazon Translate translates the text into desired languages.
  • Enables global audiences to consume spoken content in their native language.

Memory trick: Transcribe the speech, then Translate the text for global reach.

More AWS Services for AI/ML and Generative AI questions