Run an AI Text To Video task.

Request

AI tasks are asynchronous. Prefer webhook-based completion handling when the feature supports webhooks. Configure your webhook endpoint, verify webhook signatures, and use the received task_id to query the task result after a success or error notification. See the webhook integration guide for setup and verification details.

If webhooks are not supported or cannot be used in your integration, implement polling. After submitting an AI task, poll the status endpoint at regular intervals (e.g., every 10 seconds) until the task status is success or error.

Security

BearerAuthenticationV2

Bodyapplication/jsonrequired

modelstring

Model name.

Default:"youcam-video-v2"

Value:"youcam-video-v2"

promptstring, [ 1 .. 5000 ] charactersrequired

Text prompt describing the video content and visual style. Supports Chinese and English. Each character or letter counts as one.

Example:"A kitten running in the moonlight."

negative_promptstring, [ 1 .. 500 ] characters

Negative prompt describing content to exclude from the video, constraining the output. Supports Chinese and English.

Example:"low resolution, error, worst quality, low quality, disfigured, extra fingers, bad proportions."

resolutionstring

Resolution tier of the generated video, controlling clarity (total pixels).

Default:"1080P"

Enum:"720P""1080P"

Example:"1080P"

ratiostring

Aspect ratio of the generated video.

Output video resolutions (width*height) for each aspect ratio appear in the table below.:

Resolution tier	Aspect ratio	Output video resolution (width*height)
720P	16:9	1280*720
720P	9:16	720*1280
720P	1:1	960*960
720P	4:3	1104*832
720P	3:4	832*1104
1080P	16:9	1920*1080
1080P	9:16	1080*1920
1080P	1:1	1440*1440
1080P	4:3	1648*1248
1080P	3:4	1248*1648

Default:"16:9"

Enum:"16:9""9:16""1:1""4:3""3:4"

Example:"16:9"

dst_durationinteger, [ 2 .. 15 ]required

Duration of the generated video (seconds).

Default:5

Example:5

prompt_extendboolean

Enable prompt rewriting. When enabled, a Large Language Model rewrites the input prompt intelligently. This improves results for short prompts but increases latency.

Default:true

Enum:truefalse

Example:true

POST

/s2s/v2.0/task/text-to-video/youcam

curl -i -X POST \
  https://yce-api-01.makeupar.com/s2s/v2.0/task/text-to-video/youcam \
  -H 'Authorization: Bearer <YOUR_TOKEN_HERE>' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "youcam-video-v2",
    "prompt": "A kitten running in the moonlight.",
    "negative_prompt": "low resolution, error, worst quality, low quality, disfigured, extra fingers, bad proportions.",
    "resolution": "1080P",
    "ratio": "16:9",
    "dst_duration": 5,
    "prompt_extend": true
  }'

Responses

Successful execution of the task

Bodyapplication/json

statusinteger

Response status

Example:200

dataobject

Response

{
  "status": 200,
  "data": {
    "task_id": "grH0CvsgXuAIHLUzD0V1Ol34hoet3R1tvdbtiVHrDb6_UqCLKIejAIajwxrhOAfe"
  }
}