Create a video
create_videoCreate (enqueue) a new AI faceless video from a topic. Returns immediately with a video id and status "PENDING"; the render runs asynchronously — poll get_video every 20-30 seconds until status is "COMPLETED" (playable videoUrl) or "FAILED". Costs 40 credits with the default voice (+25 for a language only ElevenLabs speaks, e.g. Persian); art style does not change the price. A short balance is refused up front with 402 INSUFFICIENT_CREDITS stating credits needed, available and a top-up URL. 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. (Standard 30-second style; niche, art style and motion do not apply to it.) Set prompt_handling to "as_written" to use my words exactly. If the model refuses a scene, it fails instead of being reworded. Requires the "video:create" scope on the API key. OPTIONAL AI MOTION: pass motion_scenes (0-3, default 0 = a normal video) to turn that many scenes, starting with the first, into a 5-second AI video clip instead of a still image. Price: 115 credits per motion scene EXTRA (so 1 scene = 155 credits in total with the default voice). Call quote_video first and tell the user the price before creating. Any account with enough credits can use it: there is no plan or trial limit. A clip that cannot be made falls back to the still image and its 115 credits are refunded. Content is checked first: children, real people, sexual content, protected characters and lip-sync/deepfakes are refused (422 PROMPT_BLOCKED, nothing charged). For a pasted cinematic video prompt (camera, lens, lighting, one shot) use generate_motion_clip instead: it sends the prompt as written and makes one silent clip, with no script or voice.
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": "create_video"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| niche | No | Optional content niche. Call list_niches for the authoritative list with labels. | |
| topic | Yes | What the video is about. The full script is AI-generated from this. e.g. "3 tiny habits that quietly change your life". | |
| artStyle | No | Optional visual art style. Defaults to AUTOSHORTS (cinematic). Call list_niches for the full list. | |
| duration | No | Target length in seconds for the multi-scene faceless video: 30, 60 or 90 (default 30). | |
| language | No | Optional BCP-47 language code (e.g. "en", "vi", "es"). Defaults to "auto". | |
| motion_scenes | No | Optional. How many scenes (from the first) to animate as AI clips. 115 credits each, on top of the video price. Default 0. | |
| prompt_handling | No | "as_written": Use my words exactly. If the model refuses a scene, it fails instead of being reworded. Scenes the user wrote nothing for are still generated. "assist" (default): the product may reword picture text, as before. |