Create longer flow after stream block

I have a host of audio files, many longer than 240 seconds, so I have been using stream blocks.

However, I want to insert a speak block in between them to announce the date of the recording, but the session ends after the first stream block ends. If I use the audio block, the session doesn’t end after the first one, but this means I can’t play a majority of my files.

Is there a recommended workaround for this? Is there a way we can create a rich media response as Google Action’s console allows?

Although I just tried but I think currently no, unfortunately. Voiceflow’s supports for google are still in the middle of progressing.