AIF-C01 Practice Question 32: Speech to Text Service
AWS Certified AI Practitioner (AIF-C01) · Test 4 · question 2 of 10
A contact center stores thousands of recorded customer calls in Amazon S3. Before analysts can search the calls for mentions of competitors, the audio needs to be converted into text, with each speaker's words kept separate. The company wants a managed AWS AI service rather than training its own model. Which service should it use?
Show answer and explanation
Answer:
Amazon Transcribe is an automatic speech recognition service that uses machine learning models to convert audio to text (option A). It can transcribe media files stored in Amazon S3 (batch) or live audio streams, and it can partition the speech of individual speakers. Once the calls are text, analysts or other services can search and analyze them.
- B is wrong because Amazon Polly does the opposite: it turns *text into lifelike speech*. - C is wrong because Amazon Translate translates *text* from one language to another. It can't process audio recordings. - D is wrong because Amazon Comprehend extracts insights such as entities and sentiment from *text*. It would be a useful next step after transcription, but it can't turn speech into text.
Reference: What is Amazon Transcribe?