Build with Veo Extend
Make your first request
Use your Sorceress API key on your server. The playground uses your signed-in account; your application uses the same model with an API key.
curl -X POST 'https://sorceress.games/api/v1/jobs' \
-H 'Authorization: Bearer $SORCERESS_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "veo-extend",
"input": {
"model": "fast",
"task_id": "<task_id>",
"prompt": "<prompt>"
}
}'Inputs & settings
seedsintegerA random seed parameter that controls the randomness of the generated content. Range: 10000-99999. The same seed will generate similar video content, while different seeds will generate different video content. If not specified, the system will automatically assign a random seed.
promptstringRequiredA text prompt describing the content of the extended video. It should detail how you want the video to be extended, including actions, scene changes, styles, etc.
task_idstringRequiredThe task ID of the original video generation. Must be a valid task ID returned by the video generation API.
watermarkstringWatermark text (optional). If provided, a watermark will be added to the generated video.
Full input schema
{
"type": "object",
"required": [
"task_id",
"prompt"
],
"properties": {
"model": {
"enum": [
"fast",
"quality",
"lite"
],
"type": "string",
"title": "Model",
"default": "fast",
"description": "Extension tier: \"fast\" (default), \"quality\" or \"lite\". Billed per extension at the chosen tier."
},
"seeds": {
"type": "integer",
"title": "Seeds",
"maximum": 99999,
"minimum": 10000,
"description": "A random seed parameter that controls the randomness of the generated content. Range: 10000-99999. The same seed will generate similar video content, while different seeds will generate different video content. If not specified, the system will automatically assign a random seed."
},
"prompt": {
"type": "string",
"title": "Prompt",
"description": "A text prompt describing the content of the extended video. It should detail how you want the video to be extended, including actions, scene changes, styles, etc."
},
"task_id": {
"type": "string",
"title": "Task ID",
"description": "The task ID of the original video generation. Must be a valid task ID returned by the video generation API."
},
"watermark": {
"type": "string",
"title": "Watermark",
"description": "Watermark text (optional). If provided, a watermark will be added to the generated video."
}
}
}Results, saved runs & billing
Media requests return a job ID. Poll GET /api/v1/jobs/:id until it succeeds or fails; keep the same ID while it is processing. Long chat requests can also return a saved job to poll. Completed outputs are stored in your account, and successful work is billed using your model's current rates.
A multi-step workflow may include separately billed successful actions. If a connection drops, check your saved run before submitting it again.
