Polly

Question 1

Which AWS service uses deep learning technologies to synthesize natural-sounding human speech and convert text or articles into lifelike audio?

Answer 1

Amazon Polly

Question 2

Does Amazon Polly support language translation?

Answer 2

No

Question 3

In which two modes does Amazon Polly operate?

Answer 3

• Standard Text-to-Speech (TTS): converts text using phonemes
• Neural Text-to-Speech (TTS): converts phonemes into spectrograms and uses a vocoder to produce more natural-sounding audio

Question 4

What output formats does Amazon Polly provide?

Answer 4

MP3, Ogg Vorbis, and PCM

Question 5

Which Amazon Polly feature provides fine-grained control over how speech is generated?

Answer 5

Speech Synthesis Markup Language (SSML)

Question 6

What aspects of speech generation can be improved using Amazon Polly SSML?

Answer 6

• Emphasizing specific parts of a sentence
• Adjusting pronunciation
• Whispering selected portions of text
• Applying the newscaster speaking style