A help-desk app receives messages in several languages and sends each one to a language-specific classifier. Before routing, the app needs the language code for each message. Which Google Cloud capability returns that?
Show answer and explanation
Answer: D
Cloud Translation provides a language detection capability that returns the detected language code for input text. Calling it before routing lets the application send each message to the right classifier with little latency. Vision and Speech services work on images and audio, so they do not identify the language of typed messages.
Why the other options are wrong
- A. Vision text detection extracts text from images, not from typed messages. Using it for language identification would require the messages to be screenshots, which is not what the app receives.
- B. Speech-to-Text works on audio input. The app receives typed text, so this service has no role in identifying the language of those messages.
- C. An image classifier handles visual inputs. Language samples are text rather than pictures, so this model type is the wrong tool for the job.