Azure AI for Developers: Azure AI Speech

Using pre-built or customizable speech models, Azure AI Speech allows developers to build multimodal, multilingual, voice-enabled AI apps. In this course, instructor Marco Casalaina begins by outlining the basic features and capabilities of Azure Speech and identifies the most common use cases. Then, through hands-on instruction, he covers speech to text models and transcriptions, text to speech tools and voices, and avatar creation. The course wraps up with coverage of advanced Azure Speech capabilities.

Learning objectives
Identify common use cases for Azure AI Speech.
Customize speech to text models to fit specific needs.
Build and test text to speech audio content.
Build custom avatars and integrate gestures for enhanced communication.