Courseiva

AI-900 Practice Question: Describe features of computer vision workloads on Azure

What is the purpose of Azure AI Video Indexer's transcript feature?

⚠ Common exam trap

Candidates often confuse the transcript feature (speech-to-text) with the OCR feature (on-screen text extraction) or with translation, because all three involve 'text' but serve fundamentally different purposes in Video Indexer's pipeline.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

To automatically convert speech in videos to searchable text with timestamps

Azure AI Video Indexer's transcript feature uses automatic speech recognition (ASR) to convert spoken audio in videos into a text transcript, which is then indexed with precise timestamps for each word or phrase. This enables users to search, navigate, and analyze video content by keyword or phrase, making the video's audio content fully searchable and accessible.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • To translate video subtitles into multiple languages

    Why it's wrong here

    Translating subtitles into multiple languages requires machine translation applied to an existing subtitle or transcript, which is a separate capability in Video Indexer (e.g., translating the transcript). The transcript feature itself operates only in the original language of the video's speech, generating a verbatim text representation without any language conversion. Thus, it does not handle translation.

  • To automatically convert speech in videos to searchable text with timestamps

    Why this is correct

    The transcript feature in Azure Video Indexer uses automatic speech recognition (ASR) to convert spoken words in the video's audio track into text, with each segment assigned a precise timestamp. This text is stored as a searchable index, enabling users to locate specific moments by keyword or phrase. This is the core purpose of the transcript capability.

  • To generate written scripts for producing new videos

    Why it's wrong here

    Generating written scripts for new videos is a content-production workflow where you draft dialogue or narration before filming. Video Indexer is an analysis service for existing media, and its transcript feature transcribes the speech already present in the uploaded video. It cannot invent or write scripts for content that has not been created yet.

  • To extract text visible in video frames (on-screen text)

    Why it's wrong here

    On-screen text extraction relies on optical character recognition (OCR) applied to individual video frames, which detects visible subtitles, signs, or graphics. The transcript feature, by contrast, performs speech-to-text on the audio track and does not analyze pixels. Therefore, while Video Indexer may offer OCR as a separate insight, it is not what the transcript capability does.

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 →

How Courseiva writes practice questions · Editorial policy

JA

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.