From the course: Azure AI for Developers: OpenAI Services and Generative AI Models
Join today to access over 24,900 courses taught by industry experts.
What are audio models? - Azure OpenAI Service Tutorial
From the course: Azure AI for Developers: OpenAI Services and Generative AI Models
What are audio models?
- [Narrator] Audio models are AI models that work with sound, especially speech. In simple terms, an audio model can listen to audio or speak out audio. For example, one kind of audio model takes spoken words and turns them into written text. Another kind takes written text and turns it into spoken voice. These technologies let us communicate with computers using our natural voice. Think of voice assistants like Siri and Alexa. They use audio models to understand what you say and to talk back. Common use cases include transcribing meetings or phone calls into text. Enabling hands-free control through voice commands, providing spoken feedback in apps and making content accessible, like reading out text for visual impaired users. Audio models are also used for language translation, hearing speech in one language and outputting text in another. And for interactive chat bots that you can talk to. Azure provides services that make it easy to use audio AI. In Azure OpenAI service, there's a…
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.