Make an AI video
create_videoMake an AI video from the user's prompt with a chosen MakeViral Create model (Seedance, Kling, Veo, Wan, Grok Imagine, MiniMax...): from text, from a start frame photo (and an end frame on some models), or from references (photos, clips and sounds), with Kling multi-shot and elements. It spends credits from the user's MakeViral account (a failed video gives them back). A video takes a few minutes: this call returns at once, then call get_creation with wait true until it is ready and give the user the link. Before calling: 1) pick the model and check what it takes with get_model, 2) tell the user the price in credits, 3) with photos or clips, ask the user to confirm the people in them are them or agreed, and that no one is a child. Files: pass files the user attached in this chat (startFrame, endFrame, referencePhotos, referenceSounds), or public https links in the *Url fields. Clips must be links (MP4 or MOV). Never use photos of a public figure or of someone who did not agree. Calling again with the same input within 10 minutes returns the first video; pass a new requestId to make another.
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": {
"model": "<model>"
},
"name": "create_video"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| seed | No | Wan only: repeat a result | |
| count | No | How many videos (each one is charged). Default 1. | |
| model | Yes | Video model id (list_models). seedance-2-5 is a good default. | |
| shots | No | Kling multi-shot: each shot's prompt and length; they add up to the video length | |
| sound | No | Sound on or off where the model has the choice. Default on. | |
| aspect | No | Shape. Default 9:16 (vertical). With a start frame most models follow the photo's shape. | |
| motion | No | Grok Imagine only | |
| prompt | No | What happens in the video. With references, name them as get_model says (e.g. [Image 1]). | |
| clipMode | No | Kling Omni with a clip: 'edit' changes the clip itself (default), 'reference' makes a new video from it | |
| elements | No | Kling 3.0 elements: people or things from 2-4 photos each | |
| endFrame | No | The last frame (models with an end frame), with a start frame | |
| autoShots | No | Kling Omni: the model plans the shots itself | |
| requestId | No | Optional id (8-64 letters, digits, - or _). The same id never charges twice. | |
| webSearch | No | Seedance, text to video only: look things up online | |
| resolution | No | Size. Default: the model's smallest. | |
| startFrame | No | The first frame: a photo the user attached in the chat | |
| durationSec | No | Length in seconds (get_model lists them). Default: the model's default. | |
| endFrameUrl | No | The last frame as a public https photo link | |
| elementPhotos | No | The element photos attached in the chat, element by element in order | |
| keepClipSound | No | With a clip: put the clip's own sound on the result | |
| photosConsent | No | Needed with photos or clips: true only after the user confirmed everyone in them is the user or agreed, and no one is a child | |
| startFrameUrl | No | The first frame as a public https photo link | |
| referenceClips | No | Reference clips (MP4 or MOV) as files, where the chat can attach them | |
| referencePhotos | No | Reference photos attached in the chat (people, products, a style). Never with frames. | |
| referenceSounds | No | Reference sounds (MP3 or WAV) attached in the chat | |
| referenceClipUrls | No | Reference clips as public https links to an MP4 or MOV file | |
| referencePhotoUrls | No | Reference photos as public https links | |
| referenceSoundUrls | No | Reference sounds as public https links |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| creations | Yes |