Place pauses where the listener needs them
A comma in the text can affect how a voice reads a sentence, but it is a poor way to control the gap between two exported clips. In TTS Lines, the pause after a line is a separate setting.
Read two neighboring lines aloud. A topic shift or speaker handoff may need more room than two connected steps in a tutorial. Change one gap at a time and listen to the joined playback.
Understand the exports
The chosen gap appears in full playback and the joined MP3 or WAV. The SRT positions the next cue after that gap. Individual MP3 clips stay focused on their spoken lines so you can place them independently on a timeline.
If you later move a clip in a video editor, the exported SRT no longer follows it. Move the caption cue there as well.
Check speaker changes
A two-person exchange can feel hurried with no space or sluggish with too much. Generate both replies, listen at the handoff, and choose the pause that fits the script. Avoid setting every gap to the same value only for consistency.