AI-901 19/25: Building a Speech App with Azure Speech | Microsoft Azure AI Fundamentals

Building a Speech App with Azure Speech explained for the Microsoft Azure AI Fundamentals exam: the Azure Speech SDK (azure-cognitiveservices-speech) uses a SpeechConfig for credentials, endpoint, language and voice, an AudioConfig for microphone, speaker or file, a SpeechRecognizer whose recognize_once_async returns text for one utterance, and a SpeechSynthesizer whose speak_text_async speaks text with the voice set in speech_synthesis_voice_name, or SSML for finer control. Building a Speech App with Azure Speech is in Domain 2, Implement AI Solutions by Using Microsoft Foundry, which is 55–60% of the AI-901 exam. This exam-focused lesson is for beginners starting a career in AI solution development on Azure preparing for the certification. What you will learn: • The Speech SDK • SpeechConfig and AudioConfig • Recognizing speech • Synthesizing speech • Longer audio and SSML • Exam traps and self-check questions CHAPTERS 00:00 Building a speech app with Azure Speech for the AI-901 exam 00:25 The Speech SDK objects 00:55 Recognizing speech 01:22 Synthesizing speech 01:47 Longer audio and SSML 02:17 A small voice app 02:41 Exam traps for speech apps 03:09 Self-check questions AI-901 full course: video 19 of 25, in blueprint order (Domain 1 to Domain 2). Next: Interpreting Images with Multimodal Models. Facts checked against the official Microsoft AI-901 study guide and Microsoft Learn documentation on 2026-10-21. Skills measured and weights are from the official Microsoft study guide for AI-901 (skills measured as of April 15, 2026; checked October 2026). Unofficial study material, not affiliated with or endorsed by Microsoft. Confirm against the current study guide before you sit the exam. Subscribe to Core Concept Learning for clear, visual explanations of AI and software engineering concepts. #AI901 #AzureAI #SpeechAI