Technology Blogs by Members
Explore a vibrant mix of technical expertise, industry insights, and tech buzz in member blogs covering SAP products, technology, and events. Get in the mix!
cancel
Showing results for 
Search instead for 
Did you mean: 
patrosrinivasa
Participant
1,199

Introduction:

Hello SAP members!!

I am back again with another interesting topic that captures your attention for a moment. Microsoft Azure AI Studio with a powerful Speech AI feature, enabling developers to integrate speech recognition, synthesis, and understanding into their applications seamlessly. With Azure Speech AI, developers can create interactive voice response systems, transcribe audio recordings, and even build sophisticated virtual assistants for Automations.

Leveraging state-of-the-art machine learning algorithms, Azure Speech AI empowers developers to unlock new possibilities in communication and interaction. From enhancing accessibility to revolutionizing customer service, Speech AI in Azure AI Studio opens doors to innovative solutions in the realm of human-computer interaction. Interesting thing is you can select different voice modulations that are pre-build for AI Speech interactions.

I have a small videoclip that walks you through the platform, where you'll experience the AI voice (that I have used- "Ava") utilized for custom app interaction.

Let's start without further delay.

Azure AI Studio:

Azure AI Studio serves as a consolidated web portal that integrates various Azure AI services into a cohesive development environment. It encompasses:

  • The capabilities of Azure Machine Learning service, including the model catalog and prompt flow development.
  • The deployment, testing, and custom data integration features for generative AI models from Azure OpenAI service.
  • Seamless integration with Azure AI Services, covering speech, vision, language, document intelligence, and content safety.

Note: In some cases, Azure AI services are integrated directly into to the Azure AI Studio interface and the underlying Azure AI Service resource. In other cases, a link is provided to external service-specific studios where you can create and use Azure AI services resources. In either case, Azure AI Studio provides a central starting point from which you can find and integrate Azure AI services into your solution.

image1.png

Azure AI Studio Features:

Azure AI Studio enables teams to collaborate efficiently and effectively on AI projects, such as developing custom copilot applications that use large language models (LLMs). Tasks you can accomplish with Azure AI Studio include:

  • Deploying models from the model catalog to real-time inferencing endpoints for client applications to consume.
  • Deploying and testing generative AI models in an Azure OpenAI service.
  • Integrating data from custom data sources to support a retrieval augmented generation (RAG) approach to prompt engineering for generative AI models.
  • Using prompt flow to define workflows that integrate models, prompts, and custom processing.
  • Integrating content safety filters into a generative AI solution to mitigate potential harms.
  • Extending a generative AI solution with multiple AI capabilities using Azure AI services.

Azure AI resource:

An Azure AI resource is the foundation for AI development projects on Azure, and enables you to define shared assets that can be used across multiple projects. You can use AI Studio to perform the following tasks in an Azure AI resource on the Manage page:

  • Create members and assign them to specific roles.
  • Create and manage compute instances on which to run experiments, prompt flows, and custom code.
  • Create and manage connections to resources, such as data stores, GitHub, Azure AI Search indexes, and others.
  • Define policies to manage behavior, such as automatic compute shutdown.

 Azure AI projects:

An Azure AI resource can host one or more projects. Each project encapsulates the tools and assets used to create a specific AI solution. For example, you might create a project to enable data scientists and developers to collaborate on building a custom copilot for a business application or process.

image2.png

Once you created a resource and project you can able to see below interface where you can train,develop and deploy your model.

image3.png

I have enabled speech feature in playground so you can interact with model with voice commands.

 Here is small video of my application,

After deploying the application, we can see Launch Button next to Deploy option. Thus, your deployment will complete and clicking on Launch button will navigate to our application.

image4.png

Application is live and ready to use. Best feature is you can share this app to your fellow team members. Isn't that awesome! 😊

image5.png

Conclusion:

This way we can use Azure AI services to create our own app using custom model. You can also choose existing models based on your requirement and feed data to train your model. I believe speech AI for copilot apps will be more interesting. Thanks for your time to read this blog.

As always Happy Learning...Spread the knowledge...

Reference Links:

https://learn.microsoft.com/en-us/azure/ai-studio/ 

https://learn.microsoft.com/en-us/azure/ai-studio/what-is-ai-studio?tabs=home 

 

 

 

 

 

 

 

 

 

 

1 Comment
Labels in this area