Build with Kling 3.0
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": "kling-3.0/video",
"input": {
"duration": 5,
"mode": "std",
"aspect_ratio": "16:9",
"character_orientation": "image",
"keep_original_sound": true,
"generation_mode": "i2v",
"prompt": "<prompt>"
}
}'Inputs & settings
promptstringRequiredDescribe what you would like to create.
durationintegerVideo length (3-15 seconds)
modestringstd is standard quality, pro is higher quality
Options: std, pro
aspect_ratiostringVideo aspect ratio (text-to-video mode)
Options: 16:9, 9:16, 1:1
character_orientationstringimage: match photo pose (max 10s). video: match reference video pose (max 30s).
Options: image, video
keep_original_soundbooleanKeep audio from the motion reference video
generation_modestringOptions: i2v, t2v, v2v
image_urlsarrayUpload a file or enter one public HTTPS URL per line.
end_image_urlstringFull input schema
{
"required": [
"prompt"
],
"properties": {
"prompt": {
"type": "string",
"title": "Prompt",
"description": "Describe what you would like to create."
},
"duration": {
"type": "integer",
"title": "Duration (seconds)",
"default": 5,
"minimum": 3,
"maximum": 15,
"description": "Video length (3-15 seconds)"
},
"mode": {
"type": "string",
"title": "Quality",
"default": "std",
"enum": [
"std",
"pro"
],
"description": "std is standard quality, pro is higher quality"
},
"aspect_ratio": {
"type": "string",
"title": "Aspect Ratio",
"default": "16:9",
"enum": [
"16:9",
"9:16",
"1:1"
],
"description": "Video aspect ratio (text-to-video mode)"
},
"character_orientation": {
"type": "string",
"title": "Character Orientation",
"default": "image",
"enum": [
"image",
"video"
],
"description": "image: match photo pose (max 10s). video: match reference video pose (max 30s)."
},
"keep_original_sound": {
"type": "boolean",
"title": "Keep Reference Sound",
"default": true,
"description": "Keep audio from the motion reference video"
},
"generation_mode": {
"type": "string",
"title": "Mode",
"enum": [
"i2v",
"t2v",
"v2v"
],
"default": "i2v"
},
"image_urls": {
"type": "array",
"title": "Reference images",
"items": {
"type": "string",
"format": "uri"
},
"maxItems": 1,
"description": "Upload a file or enter one public HTTPS URL per line."
},
"end_image_url": {
"type": "string",
"title": "End frame URL",
"format": "uri"
}
}
}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.
