A bank wants its call-center software to produce a live written transcript while a customer is still speaking. Which API should the software call?
Show answer and explanation
Answer: C
The Speech-to-Text API recognizes spoken audio and returns text, and it supports streaming recognition so transcripts appear while speech is still happening. Text-to-Speech performs the reverse conversion, Natural Language analyzes text that already exists, and Translation converts text between languages.
Why the other options are wrong
- A. Text-to-Speech converts written text into synthesized spoken audio, which is the opposite direction from what the bank needs. It would not produce a transcript of a caller.
- B. Natural Language API analyzes text for entities, sentiment and syntax, but it requires text as input. It cannot transcribe the audio of a live call on its own.
- D. Translation API converts text from one language to another. It assumes written input already exists and does not turn speech into text.