Building Windows apps that leverage on-device AI models can seem like a daunting task – there’s a lot of work that goes into defining your use case, choosing and tuning the right models, and refining the logic surrounding the models.
While there’s no quick and easy path to learning the ins and outs of AI on Windows, we are going to breakdown an application sample that was showcased at Build to help you see how on-device models can be leveraged to power up your applications.
The sample we will be looking at is an AI-empowered Audio Editor, built with WinUI3 and WinAppSDK. The application functionality itself is minimal, but provides a good framework to showcase the AI portion of the app.
Audio Smart Trimming
The Audio Editor app uses several models to enable “smart trimming” of audio, which has a flow like this:
- User uploads an audio file that includes recognizable speech
- They provide a theme keyword or phrase and a trim duration
- The Audio Editor generates a trimmed…
Remember to like our facebook and our twitter @WindowsMode for a chance to win a free Surface Pro every month.
