Develop Voice-enabled Apps with Azure AI Speech
Azure AI provides a rich set of speech-related tools and capabilities for developers. This course will teach you how to leverage speech-to-text, text-to-speech, speech translation, and other features in your applications.
What you'll learn
Azure AI Speech provides a powerful set of features for transcribing speech to text, generating neural voices from text, language translation, and keyword detection. In this course, Develop Voice-enabled Apps with Azure AI Speech, you’ll learn to leverage Azure AI speech capabilities in your applications. First, you’ll explore speech to text, including diarization with multiple speakers. Next, you’ll discover text to speech, with fine grained control over the generated audio using speech synthesis markup language. Finally, you’ll learn how to translate speech into multiple languages. When you’re finished with this course, you’ll have the skills and knowledge needed to start building speech capabilities into your applications.
Table of contents
- Understanding Azure AI Speech to Text 2m
- Create a Speech Resource in the Azure Portal 1m
- Speech Studio - Speech to Text 1m
- Speech SDK - Speech to Text 4m
- Understanding Speaker Recognition and Diarization 2m
- Speech Studio - Diarization 1m
- Speech SDK - Diarization 1m
- Understanding Text to Speech 2m
- Speech Studio - Text to Speech 2m
- Speech SDK - Text to Speech 2m
- Understanding Speech Translation 1m
- Speech Studio - Speech Translation 1m
- Speech SDK - Speech Translation 2m
- Understanding Keyword Recognition 1m
- Speech Studio - Keyword Recognition 2m
- Speech SDK - Keyword Recognition 1m