Match each Azure AI service to its associated API or SDK.
Drag a concept onto its matching description — or click a concept then click the description.
Analyze images and extract information
Understand and analyze text
Convert speech to text and vice versa
Translate text between languages
Access GPT-4, DALL-E, and other models
Answer choices
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
Azure Computer Vision: Computer Vision API
The correct matches are: Azure Computer Vision with Computer Vision API, Azure Face Service with Face API, Azure Speech Service with Speech-to-Text API, and Azure Translator Text with Translator Text API. Common confusions include mixing up services with similar capabilities, such as attributing the Face API to Computer Vision or the Speech-to-Text API to Translator Text.
Answer analysis
For each option: why learners choose it and why it is or isn't the right answer here.
Azure Computer Vision: Computer Vision API
Why this is correct
Azure Computer Vision is correctly accessed through the Computer Vision API, which exposes image analysis, OCR, object detection, and tagging operations such as Analyze Image and Read. This dedicated REST endpoint and its client SDKs are the official interface for the Computer Vision service, making the pairing a direct service-to-API match.
Azure Face Service: Face API
Why this is correct
The Azure Face service is specifically built for facial functionality and is invoked through the Face API, which supports detection, verification, identification, and face attribute extraction like age, emotion, and landmarks. It runs on its own endpoint and, in many regions, requires limited-access approval, distinguishing it from Computer Vision. This is the correct association because the Face API is the Face service's primary client surface.
Azure Speech Service: Speech-to-Text API
Why this is correct
The Speech-to-Text API is a core component of Azure Speech, accepting audio streams or files and returning transcribed text through either the Speech SDK or REST. It handles both real-time and batch transcription using acoustic and language models, and it does not perform translation or sentiment analysis. Matching Azure Speech to this API is accurate because the service is the host of Speech-to-Text.
Azure Translator Text: Translator Text API
Why this is correct
The Translator Text API is the REST endpoint for the Azure Translator Text service, performing real-time text translation, transliteration, and dictionary lookup across dozens of languages. It takes text as input and returns translated text, with no audio processing or speech synthesis capabilities. This pairing is correct because the API and the service are effectively the same named product.
Azure Computer Vision: Face API
Why it's wrong here
This match is incorrect because the Face API belongs to the Azure Face service, not Computer Vision. Computer Vision does include basic face detection within its broader image-analysis operations, but the specific Face API endpoint is the dedicated facial recognition service, requiring its own key and resource. Mixing the two ignores the separate resource boundaries and feature sets in Azure AI services.
Azure Translator Text: Speech-to-Text API
Why it's wrong here
This pairing is wrong because the Speech-to-Text API resides in Azure Speech and is designed to convert audio into text, while Translator Text is a text-only translation service that cannot ingest audio. Speech-to-Text does not translate; it only provides the transcription step, and Translator Text does not have a speech-processing pipeline. Therefore, assigning Speech-to-Text to Translator Text conflates two distinct modalities and service owners.
Go deeper
Learn chapter
Azure Machine Learning Studio
Key term
Service
A service is a software component or system that performs a specific function and is available to be used by other programs or users over a network.
Key term
Computer vision
Computer vision is a field of artificial intelligence that enables computers to interpret and make decisions based on visual data from the world, such as images and videos.
About these practice questions
One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.