PRODUCTION SCENARIO
A conference app must turn a presenter's live English audio into Spanish and German captions at the same time, using one real-time call per audio stream.
Which capability meets the requirement?
Answering here is anonymous. Nothing is saved unless you sign in.
Show answer and explanation
Answer: Speech translation to two target languages
Speech translation 'directly offers the ability for you to translate the input language into two target languages ... in a single API call', which is the Spanish and German caption pair. Speech to text plus Translator produces both captions but needs a call per language, which the one-call constraint rules out. Text to speech makes audio from text, not captions from audio. Language identification only names the language being spoken.