Audio synthesis with screenshot image

Audition doesn't do video at all. This isn't a machine read either - that's a real voice. What you would need to create something like that is Premiere. That does video, and captions, and you can record audio into it. Audition can do text to voice but the voices it uses are copyright, and can only be used for private purposes unless you negotiate with the owners of them (Generally Microsoft, but not exclusively). Also, I don't think that a virtual voice would be particularly good for a long read. And you'd still need Premiere for the captions and video.