Script Editing

After the script generation step completes, you have a written script ready to review. This step is your chance to check accuracy, adjust tone, and make corrections before any audio synthesis begins. Editing the script costs nothing — voice rendering only happens when you click Render.

What the Script Looks Like

For dialogue formats (Deep Dive and Debate), the script is structured as a conversation between two speakers. Each spoken turn is its own segment — Speaker 1, then Speaker 2, alternating through the piece.

For narration formats (Brief and Critique), the script is a continuous monologue from a single narrator.

You can read through the full script in the editor before committing to a render.

How to Edit

Click into any segment in the script editor and type your changes directly. Common edits include:

• Correcting factual details you’ve spotted.
• Adjusting the tone or phrasing to better match your brand voice.
• Shortening verbose segments to improve audio pacing.
• Adding or removing specific talking points.

What to Check Before Rendering

Do a final pass before clicking Render:

1. Check the Grounding Report — if any statements were flagged as unverifiable, review those sections carefully before including them in the final audio.
2. Review dialogue flow — for dialogue formats, read through the exchange to make sure it flows naturally and doesn’t repeat itself.
3. Check the overall length — read through the script and judge whether it feels appropriately long for your chosen format.
4. Speaker balance — for dialogue formats, make sure both speakers have roughly even contributions.

Tip

For narration scripts, if any passage feels too dense or long, split it into two shorter segments. Shorter segments tend to produce cleaner, more natural-sounding speech.

After Editing

Once you’re happy with the script, head back to Creating Audio and follow Step 3 to choose your voices and render the final file.

Advanced Usage Notes

Use these patterns to get more predictable results:

• Keep inputs specific and scoped to one intent per generation request.
• Save intermediate outputs often, especially before running major edits or regenerations.
• Use review and assignment workflows early to reduce rework late in the lifecycle.

Troubleshooting

If results are not what you expected:

• Verify source quality first (missing context, inconsistent structure, or conflicting inputs reduce output quality).
• Re-check selected options and audience/profile settings before re-running.
• If a job fails repeatedly, wait briefly and retry once; then escalate with the artifact or job context.

Frequently Asked Questions

Why did quality change between runs?

Different input context, settings, and model/runtime conditions can produce different outputs.

Should I regenerate or manually edit?

Regenerate when the core structure is wrong; manually edit when only wording, ordering, or style needs adjustment.

What is the best way to reduce iteration cycles?

Start with clear scope, run smaller batches, and use review checkpoints after each major step.