I am very excited to see the 'Speak the Words' task is now available and working with Chrome! Amazing.
Now, if there were just an option to 'add image' as stimulus, and 'add audio' a wealth of content can be created for ESL and other subjects.
I would love to able to ask "What is this a picture of?" "What is happening in the picture?" "Say a noun/verb/adjective in the picture"