Step 4: Concept & Script
Add scenes with visual descriptions, dialogue, and speaker assignments.
What is the Concept & Script step?
The Concept & Script step is where you define what your video will say and show. Add scenes with visual descriptions and dialogue, assign speakers, and monitor the estimated duration against your duration target from Step 1.
- Scene Description
- The visual setting, action, and framing for each scene. Describes what the viewer sees.
- Script / Dialogue
- The spoken words for each scene — what the speaker says.
- Speaker
- Name the speaker for each scene (e.g., Host, Narrator). Useful for multi-scene videos with more than one voice.
- Duration Estimate
- Automatically calculated from your script length (and any per-scene duration hints). Shown against the duration target from Step 1, with a warning color when you're over.
Configuring Concept & Script
- 1
Add scenes
Click 'Add Scene' to create scene cards. Each scene has a visual description and dialogue. Single-scene layouts show one simplified scene editor.
- 2
Write dialogue
Enter the spoken script for each scene. Keep it conversational — short sentences work best.
- 3
Assign speakers
Set a speaker name per scene (e.g., 'Host') for multi-scene videos.
- 4
Review duration
Check the estimated duration meta row. It turns amber when the total exceeds your duration target from Step 1.
Tip
Most AI video models cap out at 8-15 seconds per generation, so scripts should be short and punchy — roughly 2-3 short sentences for an 8-second video.
Do
- Write natural, conversational dialogue
- Use short sentences for punchier delivery
- Include a clear call-to-action
- Match script length to your duration target
Don't
- Use industry jargon without context
- Write walls of text without scene breaks
- Write a 60-second script for a 8-second video
- Forget the scene description — visuals matter as much as words
Was this article helpful?