Agentic Video Generation

POST

https://api.zebracat.ai/v1/video/agentic

Agents

Submit a prompt and let the AI agent decide the best video type, visual style, mood, voice, aspect ratio, and all production parameters automatically.

The agent follows this pipeline:

Detects input type (idea, URL, or script)

Uses LLM to recommend video type, visual style, mood, and prompt style

Picks the best voice using score-based matching

Determines aspect ratio from context keywords

Builds a complete video plan and starts generation

You can optionally override any of the agent's decisions by providing explicit values for video_type, duration, language, mood, visual_style, aspect_ratio, or voice_id.

Credit: An AVPC (Agentic Video Plan Cost) credit is charged for the AI planning step. Additional generation credits are charged during rendering.

Use the returned task_id to poll status via GET /api/public/video/status.

Request

Authorization

API Key

Add parameter in header

X-API-KEY

Example:

X-API-KEY: ********************

Body Params application/jsonRequired

Examples

Responses

🟢202

application/json

Agentic video task created.

Body

🟠400

🟠401

🟠402

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST 'https://api.zebracat.ai/v1/video/agentic' \
--header 'X-API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "prompt": "string",
    "video_type": "ai_avatar",
    "duration": 15,
    "language": "string",
    "mood": "energetic",
    "visual_style": "Default",
    "aspect_ratio": "vertical",
    "voice_id": "string",
    "should_render": false
}'

Response Example

202 - Example 1

{
    "task_id": "string",
    "status": "string",
    "video_plan": {
        "input_type": "string",
        "video_type": "string",
        "visual_style": "string",
        "mood": "string",
        "aspect_ratio": "string",
        "duration": 0,
        "language": "string",
        "voice": {},
        "prompt_style": "string"
    }
}

List Templates

Audio to Video