Foley and effects and music will obviously be extremely important, since this would be an audio production. I also think that some narration is necessary. Descriptions of new settings will be important, as well as some narration that helps transition from scene to scene. That, and some actions are better portrayed with narration than with foley, as foley and FX can only do so much specifically.
I think this is also a good thing to do with Tolkien's writings, as his descriptions of some places are things that should not be left out. There's not a huge amount of it in the Silmarillion, but we can lift some stuff from the BOLT the Lays and other pre-canon works, repurpose them a bit, and I think they would make great narration that would not detract from the story.