Prepare AI Video
prepare_ai_videoPrepare a text-to-video clip with Abracadabrax from a scene description: visual style, landscape (YouTube), vertical (TikTok, Reels, Shorts) or square format, length in seconds and video model (Kling, Seedance, Sora, Veo). Returns the settings and the credits required; nothing is generated and no credits are spent. No sign-in is needed to prepare. Text only: do not use it for uploaded, attached or reference images or videos (editing, background removal, upscaling, image-to-video); for those, point the user to the Abracadabrax workspace.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"scene": "<scene>"
},
"name": "prepare_ai_video"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| scene | Yes | What happens in the clip: subject, action, setting, camera movement, lighting. | |
| style | No | Visual style, e.g. cinematic, anime, 3D animation, documentary, claymation. | |
| format | No | landscape 16:9 (default), vertical 9:16 or square 1:1 (square only on Kling and Seedance). | |
| duration | No | Length in seconds; must be one the model supports (Kling 5 or 10, Seedance 5-12, Sora 4/8/12, Veo 4/6/8). | |
| model_id | No | Optional video model id: kling-3-pro (default), kling-3-standard, seedance-1-5-pro, seedance-1-lite, sora-2, veo-3-1-fast, veo-3-1. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| job | No | ||
| state | Yes | ||
| balance | No | ||
| message | Yes | ||
| project | Yes | ||
| dashboard_url | Yes | ||
| credits_required | Yes |