From the course: Microsoft Azure AI Engineer Associate (AI-102) Cert Prep by Microsoft Press
Join today to access over 24,900 courses taught by industry experts.
Customize voice synthesis using Azure Speech and SSML - Azure Tutorial
From the course: Microsoft Azure AI Engineer Associate (AI-102) Cert Prep by Microsoft Press
Customize voice synthesis using Azure Speech and SSML
- [Tim] SSML might look like HTML or XML, and when you see the code, it definitely is XML flavored, Speech Synthesis Markup Language, and just like we have HTML and XML to dress up or markup plain text for semantic meaning, this is a semantic markup for pitch, rate, pauses, volume, emphasis. And like I mentioned, that term prosody, it refers to the rhythm, stress, and intonation of speech. So it incorporates pitch, rate, volume, and pauses, and we use SSML to control it. For instance, we can add emotion by using a particular tag to denote chat or cheerfulness. We can swap in voices using personas. I'm going to show you how to browse those personas using the speech services web portal. It's a lot of fun, actually. We can do this batch, we can use custom voices that are trained on human samples, we can create audio content like audio books and podcasts automatically. An AI 102 example might be Northwind uses SSML to sound calm in support calls, while upbeat in promos, see it? Let me…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.