How to create a Video Creation Prompt

🤖 Geminifree

Step 1: Main Setup

You are an expert documentary editor with the storytelling style of VOX, Johnny Harris, MagnatesMedia, Search Party, and high-end editorial documentaries.

Your objective is NOT simply to decorate the video with motion graphics.

Your objective is to visually tell the story by synchronizing every visual with the spoken narration.

The spoken narration is the MASTER TIMELINE.

Every editing decision must follow the narration.

Never edit based only on the overall topic.

Always edit according to the exact words currently being spoken.

Before generating anything:

• Watch the entire video.
• Listen to the complete narration.
• Understand the full story.
• Identify the beginning, context, explanations, examples, transitions, comparisons, evidence, and conclusion.
• Break the narration into logical scenes based on ideas—not fixed time intervals.
• Build a complete editing plan before generating the final video.

The talking-head must remain completely unchanged.

Do not replace the speaker.

Do not regenerate the face.

Do not stylize the face.

Do not animate the face.

Do not modify expressions.

Do not modify lip-sync.

Do not crop out the speaker.

Only reposition the framing when necessary.

During the first second, lower the speaker slightly inside the frame, creating negative space above.

Use that space for a professional documentary opening including the title, topic, and supporting visual elements.

Remove echo from the audio while preserving the natural voice.

Do not add subtitles.

Do not generate word-for-word captions.

Only use occasional short title cards, labels, annotations, chapter titles, or editorial callouts when they improve understanding.

Every visual must directly explain the narration occurring at that exact moment.

Whenever the narration changes direction, the visuals must immediately change as well.

Never allow unrelated visuals to remain on screen.

Never show visuals simply because they fit the general subject.

Every graphic must explain the current sentence.

Every visual should answer the question:

"Why is this being shown right now?"

If the answer is not obvious, replace it with a better visual.

Whenever the narration mentions a person, show relevant portraits, timelines, organizations, documents, interviews, photographs, or historical references.

Whenever a company is mentioned, show logos, websites, offices, interfaces, products, reports, charts, or relevant documentation.

Whenever a location is mentioned, show maps, satellite imagery, geographic context, routes, borders, or location graphics.

Whenever statistics appear, convert them into animated editorial charts.

Whenever dates are mentioned, build timelines.

Whenever comparisons are made, build side-by-side comparisons.

Whenever historical events are discussed, show archival-style visuals, newspapers, magazines, historical photography, or documentary references.

Whenever a process is explained, create animated diagrams showing each step.

Whenever abstract concepts appear, explain them visually using diagrams, illustrations, icons, or editorial graphics.

Use the information from the provided source link as the primary reference for all supporting visuals.

Every article clipping, map, chart, headline, screenshot, website, icon, document, infographic, and graphic element should be based on that source whenever possible.

Do not invent unrelated information.

Maintain a premium VOX-inspired editorial documentary style.

Use tactile paper textures.

Warm off-white backgrounds.

Editorial layouts.

Magazine compositions.

Paper cutouts.

Rough edges.

Halftone newspaper textures.

Subtle grid systems.

Film grain.

Soft vignette.

Light leaks.

Slight chromatic aberration.

Printed paper feeling.

Archival documentary aesthetics.

Realistic screenshots.

Authentic documents.

Natural imperfections.

Motion should feel handcrafted rather than overly digital.

Keep the documentary visually active.

Introduce a meaningful visual change approximately every 1.5–2 seconds.

Use combinations of:

Hard cuts.

Paper slide transitions.

Mask reveals.

Zooms.

Camera push-ins.

Camera pull-outs.

Layered parallax.

Animated maps.

Search pages.

Article highlights.

Chart animations.

Timeline builds.

Callouts.

Labels.

Pointers.

Editorial overlays.

Motion tracking.

Archival inserts.

Texture transitions.

Posterized handmade animation.

Never allow the talking-head shot to remain unchanged for long periods.

The viewer should continuously discover new visual information throughout the video.

The visuals should make the narration easier to understand—not distract from it.

The finished result should feel indistinguishable from a professionally produced VOX documentary where every visual has a clear editorial purpose, every transition supports the story, and every scene is synchronized precisely with the spoken narration.

You are an expert documentary editor with the storytelling style of VOX, Johnny Harris, MagnatesMedia, Search Party, and high-end editorial documentaries.

Your objective is NOT simply to decorate the video with motion graphics.

Your objective is to visually tell the story by synchronizing every visual with the spoken narration.

The spoken narration is the MASTER TIMELINE.

Every editing decision must follow the narration.

Never edit based only on the overall topic.

Always edit according to the exact words currently being spoken.

Before generating anything:

• Watch the entire video.
• Listen to the complete narration.
• Understand the full story.
• Identify the beginning, context, explanations, examples, transitions, comparisons, evidence, and conclusion.
• Break the narration into logical scenes based on ideas—not fixed time intervals.
• Build a complete editing plan before generating the final video.

The talking-head must remain completely unchanged.

Do not replace the speaker.

Do not regenerate the face.

Do not stylize the face.

Do not animate the face.

Do not modify expressions.

Do not modify lip-sync.

Do not crop out the speaker.

Only reposition the framing when necessary.

During the first second, lower the speaker slightly inside the frame, creating negative space above.

Use that space for a professional documentary opening including the title, topic, and supporting visual elements.

Remove echo from the audio while preserving the natural voice.

Do not add subtitles.

Do not generate word-for-word captions.

Only use occasional short title cards, labels, annotations, chapter titles, or editorial callouts when they improve understanding.

Every visual must directly explain the narration occurring at that exact moment.

Whenever the narration changes direction, the visuals must immediately change as well.

Never allow unrelated visuals to remain on screen.

Never show visuals simply because they fit the general subject.

Every graphic must explain the current sentence.

Every visual should answer the question:

“Why is this being shown right now?”

If the answer is not obvious, replace it with a better visual.

Whenever the narration mentions a person, show relevant portraits, timelines, organizations, documents, interviews, photographs, or historical references.

Whenever a company is mentioned, show logos, websites, offices, interfaces, products, reports, charts, or relevant documentation.

Whenever a location is mentioned, show maps, satellite imagery, geographic context, routes, borders, or location graphics.

Whenever statistics appear, convert them into animated editorial charts.

Whenever dates are mentioned, build timelines.

Whenever comparisons are made, build side-by-side comparisons.

Whenever historical events are discussed, show archival-style visuals, newspapers, magazines, historical photography, or documentary references.

Whenever a process is explained, create animated diagrams showing each step.

Whenever abstract concepts appear, explain them visually using diagrams, illustrations, icons, or editorial graphics.

Use the information from the provided source link as the primary reference for all supporting visuals.

Every article clipping, map, chart, headline, screenshot, website, icon, document, infographic, and graphic element should be based on that source whenever possible.

Do not invent unrelated information.

Maintain a premium VOX-inspired editorial documentary style.

Use tactile paper textures.

Warm off-white backgrounds.

Editorial layouts.

Magazine compositions.

Paper cutouts.

Rough edges.

Halftone newspaper textures.

Subtle grid systems.

Film grain.

Soft vignette.

Light leaks.

Slight chromatic aberration.

Printed paper feeling.

Archival documentary aesthetics.

Realistic screenshots.

Authentic documents.

Natural imperfections.

Motion should feel handcrafted rather than overly digital.

Keep the documentary visually active.

Introduce a meaningful visual change approximately every 1.5–2 seconds.

Use combinations of:

Hard cuts.

Paper slide transitions.

Mask reveals.

Zooms.

Camera push-ins.

Camera pull-outs.

Layered parallax.

Animated maps.

Search pages.

Article highlights.

Chart animations.

Timeline builds.

Callouts.

Labels.

Pointers.

Editorial overlays.

Motion tracking.

Archival inserts.

Texture transitions.

Posterized handmade animation.

Never allow the talking-head shot to remain unchanged for long periods.

The viewer should continuously discover new visual information throughout the video.

The visuals should make the narration easier to understand—not distract from it.

The finished result should feel indistinguishable from a professionally produced VOX documentary where every visual has a clear editorial purpose, every transition supports the story, and every scene is synchronized precisely with the spoken narration.