GOOGLE CLOUD API EXAM QUESTIONS
AND ANSWERS
The normal edition uses phrase based translation. Phrase based translation translates
based on a phrase or a sentence. The premium edition uses neural machine translation
which reduces translation errors by 55-85 percent. The neural machine translation uses
context around the entire word when translating.
How much does basic usage cost for translate? - ANSWER-Translation API charges on
a per character basis, even if the character is multiple bytes. Basic usage
pricing is $20 per million character.
What is Google Speech API? - ANSWER-Google Cloud Speech API enables
developers to convert audio to text by applying powerful neural network models in an
easy to use API. The API recognizes over 80 languages and variants, to support global
user base.
What codec specifications does Google Speech API recommend? - ANSWER-Use a
lossless codec to record and transmit audio. FLAC or uncompressed is recommended
What is the difference between Google Web Speech API and Google Cloud Speech
API? - ANSWER-Google Web Speech API is now deprecated and Google Cloud
Speech API is the new and improved version
What is Google Vision API? - ANSWER-A powerful image analysis API that enables
developers to understand the content of an image by encapsulating powerful machine
learning models in an easy to use REST API.
What are some features of the Cloud Vision API? - ANSWER-Label Detection
Optical Character Recognition
Face Detection
Image Attributes
Logo Detection
Explicit Content Detection
Landmark Detection
Does the Cloud Vision API have a facial recognition feature? - ANSWER-Facial
recognition is not supported. The API can tell you where faces are in an image but it
cannot tell you who they are. However, the API can detect associated key facial
attributes like emotional state or wearing headwear.
What is the format of responses and requests in the Cloud Vision API? - ANSWER-
Requests and responses used in the Cloud Vision API are both in JSON format.
AND ANSWERS
The normal edition uses phrase based translation. Phrase based translation translates
based on a phrase or a sentence. The premium edition uses neural machine translation
which reduces translation errors by 55-85 percent. The neural machine translation uses
context around the entire word when translating.
How much does basic usage cost for translate? - ANSWER-Translation API charges on
a per character basis, even if the character is multiple bytes. Basic usage
pricing is $20 per million character.
What is Google Speech API? - ANSWER-Google Cloud Speech API enables
developers to convert audio to text by applying powerful neural network models in an
easy to use API. The API recognizes over 80 languages and variants, to support global
user base.
What codec specifications does Google Speech API recommend? - ANSWER-Use a
lossless codec to record and transmit audio. FLAC or uncompressed is recommended
What is the difference between Google Web Speech API and Google Cloud Speech
API? - ANSWER-Google Web Speech API is now deprecated and Google Cloud
Speech API is the new and improved version
What is Google Vision API? - ANSWER-A powerful image analysis API that enables
developers to understand the content of an image by encapsulating powerful machine
learning models in an easy to use REST API.
What are some features of the Cloud Vision API? - ANSWER-Label Detection
Optical Character Recognition
Face Detection
Image Attributes
Logo Detection
Explicit Content Detection
Landmark Detection
Does the Cloud Vision API have a facial recognition feature? - ANSWER-Facial
recognition is not supported. The API can tell you where faces are in an image but it
cannot tell you who they are. However, the API can detect associated key facial
attributes like emotional state or wearing headwear.
What is the format of responses and requests in the Cloud Vision API? - ANSWER-
Requests and responses used in the Cloud Vision API are both in JSON format.
