AWS Certified Solutions Architect – Associate (SAA-C02) — Question 584

A company wants to create an audio version of its product manual. The product manual contains custom product names and abbreviations. The product manual is divided into sections.
Which solution will meet these requirements with the LEAST operational overhead?

Answer options

• A. Use Amazon Polly. Build custom lexicons for the product names and abbreviations. Use the StartSpeechSynthesisTask API operation for each section of the product manual.
• B. Use Amazon Polly. Build custom Speech Synthesis Markup Language (SSML) for the product names and abbreviations. Use the StartDocumentTextDetection API operation for each section of the product manual.
• C. Use Amazon Textract. Build custom Speech Synthesis Markup Language (SSML) for the product names and abbreviations. Use the StartDocumentTextDetection API operation for each section of the product manual.
• D. Use Amazon Textract. Build custom lexicons for the product names and abbreviations. Use the StartTranscriptionJob API operation for each section of the product manual.

Correct answer: A

Explanation

Amazon Polly is the correct service for converting text to lifelike speech, and its custom lexicons feature allows the customization of pronunciation for specific product names and abbreviations with minimal operational overhead. The StartSpeechSynthesisTask API is the appropriate asynchronous operation to synthesize large text files divided into sections into audio files. Amazon Textract is an OCR service for extracting text from documents, and the other options reference incorrect APIs such as StartDocumentTextDetection and StartTranscriptionJob.