From the course: AI-Powered Software Development: Coding, Testing, and System Design
Unlock this course with a free trial
Join today to access over 24,900 courses taught by industry experts.
Audio and speech applications
From the course: AI-Powered Software Development: Coding, Testing, and System Design
Audio and speech applications
- [Shaun] All right, so let's move on now to how to use these generative AI APIs in order to work with audio. So there's really two primary things you're gonna wanna do here. One is voice transcription. So if you have recorded meetings and you want to translate those into an actual transcript that you can read, that's something you can do. And the other thing is actually generating audio from text, basically generating a real voice that's saying what the text says. So here's what we're gonna do. We're going to start off by doing the first one, and I actually have a recording here that I'll play for you. It's just a simple voice recording that I did in order to demonstrate this. So here's what it sounds like. Hi, Sean here, and we're gonna test out how good the OpenAI API is at telling what I'm seeing. All right, that was an actual voice recording of me, not me right now. So here's what we're gonna do, we're going to…
Contents
-
-
-
-
-
The basics of generative AI API integration5m 37s
-
(Locked)
Text completion applications6m 5s
-
(Locked)
Image generation and vision applications4m 45s
-
(Locked)
Audio and speech applications4m 43s
-
(Locked)
Challenge: Creating an AI-powered application1m 35s
-
(Locked)
Solution: Creating an AI-powered application5m 14s
-
-
-