Allow adding pauses to beginning, middle, end of dialogue

For now, use:

https://elevenlabs.io/docs/best-practices/prompting/controls

Rather than playing the video and having them speak out of the blue, it would be better to play the video and show the original still image for the first 2 to 3 seconds before they start speaking. At the very least, having a specification that allows users to decide the number of seconds before they start speaking would be a benefit to almost all users.