Attachments: Up to 2 attachments (including images) can be used with a maximum of 512.0 KiB each and 1.0 MiB total.
I think you could try the following approaches:
1 Person is following this question.
Echo-dot was not able to switch into voice/sound recording mode
HELP! How do I make the Alexa Skill speak ALL SSML
Going back and forth between languages in Alexa skill
How can you find out what is providing an Alexa response?
why there is a delay after a response or repromt?