A call center manager wants to search past customer service calls for specific phrases mentioned during conversations, but currently only audio recordings exist. Which Azure AI capability should be used first to make the calls searchable by text?
Select an answer to reveal the explanation.
Short Explanation
Think about the raw material here: audio files. If you want to eventually search those calls by keyword, the first move is turning speech into words on a page — that's speech-to-text, doing the heavy lifting of transcription. Going in the opposite direction, turning scripted text into spoken audio for a phone prompt, doesn't help because you already have audio and need text. Adding a translation step assumes the calls are in a different language than what you want to search in, which was never mentioned here — that's solving a problem the manager doesn't have. And figuring out which person is talking tells you who said something, not what they said, so it won't make the content itself searchable. The manager's actual goal — searchable text from existing audio — only lines up with the transcription capability.
Full Explanation
The correct answer is A. The manager already has audio recordings and wants to search their contents by phrase, which requires converting spoken audio into written text — exactly what a speech-to-text (transcription) service does, producing a text version of each call that can then be indexed and searched. Option B is incorrect because text-to-speech runs in the opposite direction, turning written scripts into spoken audio for things like IVR prompts, and does nothing to make existing audio searchable. Option C is incorrect because speech translation converts spoken content from one language into another; the scenario never mentions a language barrier, so translation solves a different problem than the one described. Option D is incorrect because speaker recognition identifies or verifies who is talking based on voice characteristics, which helps attribute a call to a person but does not produce any searchable text of what was said. Only transcription turns the audio archive into the kind of text-based, searchable resource the manager needs.