Now that we have our Image Analyzer properly working on the beta UI, we can now turn the text to audio output. To do so, we must use the Speech SDK from Azure's Speech service. Similar to the development of our Image Analyzer, we will test it on the UI.
ETA:
How long do you think it will take to complete this?
1 hour
Objective:
Checklist of everything you need to do to complete this issue
[x] Use HTML elements to test overall functionality
[x] Create a function that returns the audio output through the click of a button (part of testing)
[x] Store the textual description by accessing its "textContent"
[x] Utilize the Speech SDK package to emit audio output (from the output text)
Description
ETA:
Objective: