Alecto_Perfecto Stokes   •   about 1 year ago

Can you explain more of this multimodal?

Best Use of Azure AI: Entrants must create a multi-modal app that features at least 2 modes from the categories of images, video/motion, voice/audio, or text in addition to language capabilities with Microsoft Azure’s Responsible AI tools.

So I got to use voice/audio with images, or voice/audio with video/motion?

• 2 comments
• 

  Marc Alfaro   •   about 1 year ago

  I also need clarity on this please

• 

  Sara S Manager   •   about 1 year ago

  For this category, you would need to create an app that can leverage 2 or more AI services or use 2 or more services in combination - images, voice, audio, vision, text, search, motion

Comments are closed.