Title100/100
Build an AI video prompt
The title clearly communicates the tool’s action and subject. Keep it concise.
Description94/100
Converts a video concept and optional production choices into a structured, model-agnostic text prompt for an AI video system. Returns prompt text, a negative prompt, and normalized generation settings. It generates text only; it does not create media, access accounts, or save data.
The description explains the capability, when to use it, and what to expect.
Inputs95/100
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
idea
The video concept in a sentence or two. Name the subject, what it does, and where.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
style_id
Optional style id from list_video_prompt_styles. Supplies camera, lighting, visual style and mood defaults. An unrecognized id is ignored and noted in the result.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
generation_mode
text_to_video builds a scene from nothing; image_to_video animates an existing image and preserves its subject. Defaults to text_to_video.
Clear enough to supply this argument.
destination
Where the clip will be published. Affects composition and aspect ratio only. Defaults to general.
Clear enough to supply this argument.
aspect_ratio
Frame shape. Defaults to 9:16 for tiktok, instagram_reels and youtube_shorts, otherwise 16:9.
Clear enough to supply this argument.
duration_seconds
Intended clip length in whole seconds. Defaults to 8.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
subject
Who or what is on screen, if the idea should be sharpened.
Clear enough to supply this argument.
action
The single main thing happening. One clear action works best.
Clear enough to supply this argument.
setting
Location plus time of day or weather.
Clear enough to supply this argument.
camera
Shot size and camera movement, for example "low tracking shot".
Clear enough to supply this argument.
lighting
Light source and quality, for example "neon reflections on wet streets".
Clear enough to supply this argument.
visual_style
Medium, look and grade, for example "cinematic 35mm".
Clear enough to supply this argument.
mood
Emotional tone of the shot.
Clear enough to supply this argument.
composition
Explicit framing instruction, overriding the aspect-ratio default.
Clear enough to supply this argument.
motion_strength
How much movement to ask for. Defaults to balanced, or subtle for image_to_video.
Clear enough to supply this argument.
avoid
Things to exclude, added to the standard negative prompt. Plain terms such as "brand logos".
Clear enough to supply this argument.
Annotations100/100
All four behavior hints are declared.
{
"title": "Build an AI video prompt",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}Output schema81/100
The output schema explains the structured result.
View output schema
{
"type": "object",
"required": [
"prompt",
"negative_prompt",
"structure",
"settings",
"notes"
],
"properties": {
"notes": {
"type": "array",
"items": {
"type": "string"
},
"description": "Assumptions the compiler made, in plain language. Empty when nothing was assumed."
},
"prompt": {
"type": "string",
"description": "The positive prompt, ready to paste into a video model."
},
"settings": {
"type": "object",
"required": [
"generation_mode",
"destination",
"aspect_ratio",
"duration_seconds"
],
"properties": {
"style_id": {
"type": "string"
},
"destination": {
"enum": [
"general",
"tiktok",
"instagram_reels",
"youtube_shorts",
"youtube",
"advertisement"
],
"type": "string"
},
"aspect_ratio": {
"enum": [
"16:9",
"9:16",
"1:1"
],
"type": "string"
},
"generation_mode": {
"enum": [
"text_to_video",
"image_to_video"
],
"type": "string"
},
"duration_seconds": {
"type": "integer"
}
},
"description": "Normalized generation settings to use alongside the prompt.",
"additionalProperties": false
},
"structure": {
"type": "object",
"required": [
"idea",
"camera",
"lighting",
"visual_style",
"composition",
"motion"
],
"properties": {
"idea": {
"type": "string"
},
"mood": {
"type": "string"
},
"action": {
"type": "string"
},
"camera": {
"type": "string"
},
"motion": {
"type": "string"
},
"setting": {
"type": "string"
},
"subject": {
"type": "string"
},
"lighting": {
"type": "string"
},
"composition": {
"type": "string"
},
"visual_style": {
"type": "string"
}
},
"description": "The prompt broken into its parts, showing what was supplied and what was defaulted.",
"additionalProperties": false
},
"negative_prompt": {
"type": "string",
"description": "Comma-separated exclusions."
}
},
"additionalProperties": false
}