1. A voice assistant needs to convert a user's spoken words into text so it can process the request. Which Azure AI Speech capability is this?
- A. Speech-to-text (speech recognition)✓ Correct
- B. Text-to-speech (speech synthesis)
- C. Sentiment analysis
- D. Optical character recognition
Explanation
Transcribing spoken audio into text is speech-to-text (speech recognition). Text-to-speech (B) is the reverse — generating spoken audio from text. Sentiment analysis (C) works on text emotion, and OCR (D) reads text from images.