Draft a video script
draft_videoWrite a video's script and scenes WITHOUT rendering or charging, so the user can read and change it first. Returns draftId, the scenes (narration + visual prompt each) and the exact render price. Free, but it runs the script writer once: needs a balance that can pay for a render and is limited to 20 drafts per hour. Then: show it → update_draft / revise_scene → render_draft only after the user approves the price. A new account with no credits that has not had its free first video gets it here instead of an error: watermarked, labelled AI-generated, up to 30 seconds, standard voice, one per account, subject to the day's availability. For that video the draft is up to 30 seconds (about 80 words) and 3 drafts per hour. Set prompt_handling to "as_written" to use my words exactly. If the model refuses a scene, it fails instead of being reworded. Each scene says who wrote its picture text (promptSource). Use create_video instead when no review is wanted. Requires the "video:create" scope.
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": {
"topic": "<topic>"
},
"name": "draft_video"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Optional title (defaults to the topic). | |
| topic | Yes | What the video is about; the script is written from it. | |
| artStyle | No | Optional art style (default AUTOSHORTS). | |
| duration | No | Target length in seconds (default 30; 90 needs a paid plan). | |
| language | No | Optional BCP-47 narration language, e.g. "en", "vi". | |
| prompt_handling | No | "as_written": Use my words exactly. If the model refuses a scene, it fails instead of being reworded. "assist" (default): the product may reword picture text, as before. |