MLS-C01 Question 301
Single answerA company wants to create an e-learning platform that delivers audio lessons generated from text content. They plan to use Amazon Polly to synthesize speech and aim to provide users with a personalized and engaging listening experience. Which feature of Amazon Polly should the company use to achieve this personalization?
- A
Neural Text-to-Speech (NTTS)
- B
Speech Marks
- C
Custom Lexicons
- D
SSML (Speech Synthesis Markup Language)
Show answer and explanation
Correct answer: D
Explanation
SSML (Speech Synthesis Markup Language) is a powerful feature of Amazon Polly that allows developers to control various aspects of speech generation, such as pitch, tone, volume, and emphasis. These capabilities make it possible to create highly personalized and engaging audio lessons tailored to the preferences and requirements of the target audience.
- A. Incorrect.
Neural Text-to-Speech (NTTS) provides high-quality, natural-sounding speech but does not directly enable personalization for specific listening experiences.
- B. Incorrect.
Speech Marks provide metadata such as word boundaries and sentence timings, which are useful for synchronizing speech with visuals but do not add personalization to the generated audio.
- C. Incorrect.
Custom Lexicons allow you to define how specific words are pronounced but do not provide broader personalization options for user engagement.
- D. Correct.
SSML (Speech Synthesis Markup Language) allows for significant customization, such as adjusting speaking style, tone, emphasis, pauses, and more, making it ideal for creating personalized and engaging audio experiences.