5  Audio & Performance

Audio & Performance is the phase where you hear your episode for the first time. Rendering dialogue audio before generating a single shot is one of the most cost-effective feedback loops in the pipeline — pacing problems, flat performances, and tonal mismatches are far cheaper to fix in the script than after video generation.

• Voice Selection: Choosing a TTS voice or custom recording for each character.

• Music and Sound Effects: Selecting music that matches the episode's tone and planning sound design.

Listen to the rendered dialogue all the way through before moving to shot planning. Ask: does the timing feel right? Does each character sound like themselves? Is the emotional delivery matching the scene's intent? If not, revise the screenplay now.