Video Generation

Once the storyboard is planned and the per-slide images and narration audio are generated, the platform assembles everything into a single video file. There are two assembly modes: a standard slideshow (the default) and an animated mode that adds motion between slides.

How to Launch a Video Job

1. Navigate to Studio and open your project.
2. Select New Video.
3. Configure the options:
   • Format — Explainer (full coverage) or Brief (shorter summary).
   • Visual Style — Classic, Dark, Whiteboard, Neon, or Watercolor.
   • Language — the target language for narration (default: English).
   • Steering Prompt (optional) — up to 500 characters to focus the content.
   • Title (optional) — auto-generated if not set.
   • Animated (optional) — enable animated transitions between slides.
   • Source File Filter (optional) — restrict to specific files in the project.
4. Click Generate Video.

Standard Mode (Default)

In standard mode, each slide image is displayed for the duration of its narration audio. The slides and audio are combined into a single video file. This is the reliable default and works without any additional configuration.

Animated Mode (Optional)

With animated mode enabled, the platform generates short motion clips between slides to create a more dynamic, flowing video. Animated mode falls back to the standard slideshow automatically if a transition clip cannot be generated for any slide, so the job will always complete.

Note

Animated mode requires access to the animated video generation service. If your organisation does not have this enabled, the standard mode will be used regardless of this setting.

What You Get

When the video job completes, the artifact includes:

• The video file — the assembled video with narration audio.
• A narration audio track — the full audio as a standalone file.
• A captions file — the narration text for each slide.
• A grounding report — an audit trail mapping the spoken content to your source documents.

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.