HappyHorse Text-to-Video API Reference

Provider: DataEyes
Base URL: https://platform.dataeyes.ai/ali
Version: v1
Last Updated: 2026-06-26

Overview

The HappyHorse Text-to-Video API enables you to generate videos from text prompts using DataEyes' HappyHorse video generation models. The API follows an asynchronous task-based workflow: you submit a generation request and then poll for results until the task completes.

Supported Models

Model ID	Description
`happyhorse-1.1-t2v`	HappyHorse v1.1 Text-to-Video
`happyhorse-1.0-t2v`	HappyHorse v1.0 Text-to-Video

Endpoint

Operation	Method	URL
Create Task	`POST`	`https://platform.dataeyes.ai/ali/api/v1/services/aigc/video-generation/video-synthesis`
Query Results	`GET`	`https://platform.dataeyes.ai/ali/api/v1/tasks/{task_id}`

Authentication

All requests must include an API key in the Authorization header using the Bearer scheme:

Authorization: Bearer sk-xxxx

Workflow

The Text-to-Video API uses an asynchronous two-step workflow:

                         +------------------+
                         |   Client         |
                         +--------+---------+
                                  |
                     Step 1: POST /video-synthesis
                     (prompt + parameters)
                                  |
                                  v
                         +------------------+
                         |   DataEyes API   |
                         +--------+---------+
                                  |
                        Returns task_id +
                        task_status: PENDING
                                  |
                                  v
                         +------------------+
                         |   Client         |
                         +--------+---------+
                                  |
                     Step 2: GET /tasks/{task_id}
                     (poll every ~15 seconds)
                                  |
                                  v
                         +------------------+
                         |   DataEyes API   |
                         +--------+---------+
                                  |
                    +-------------+-------------+
                    |                           |
             SUCCEEDED                    FAILED
             video_url returned           error returned

Create Task -- Submit a POST request with your prompt and parameters. The API returns a task_id immediately.

Query Results -- Poll the task status using GET /tasks/{task_id} at recommended intervals of 15 seconds until the status is SUCCEEDED or FAILED.

Step 1: Create Task

Request

Method: POST
URL: https://platform.dataeyes.ai/ali/api/v1/services/aigc/video-generation/video-synthesis

Headers

Header	Required	Value
`Content-Type`	Yes	`application/json`
`Authorization`	Yes	`Bearer sk-xxxx`
`X-DashScope-Async`	Yes	`enable`

Request Body

Field	Type	Required	Description
`model`	string	Yes	Model identifier. One of `happyhorse-1.1-t2v` or `happyhorse-1.0-t2v`.
`input`	object	Yes	Input object containing the prompt.
`parameters`	object	No	Generation parameters (resolution, ratio, duration, etc.).

`input` Object

Field	Type	Required	Description
`prompt`	string	Yes	Text description of the video to generate. Maximum 5000 non-Chinese characters or 2500 Chinese characters.

`parameters` Object

Field	Type	Required	Default	Description
`resolution`	string	No	`1080P`	Output video resolution. Values: `720P`, `1080P`.
`ratio`	string	No	`16:9`	Aspect ratio. Values: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `4:5`, `5:4`, `9:21`, `21:9`.
`duration`	integer	No	`5`	Video duration in seconds. Range: 3 -- 15.
`watermark`	boolean	No	`true`	Whether to include a watermark on the generated video.
`seed`	integer	No	--	Random seed for reproducible generation. Range: 0 -- 2,147,483,647.

cURL Example

Success Response

HTTP Status: 200 OK

{
  "output": {
    "task_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
    "task_status": "PENDING"
  },
  "request_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Error Response

HTTP Status: 4xx / 5xx

{
  "code": "InvalidParameter",
  "message": "The prompt exceeds the maximum allowed length.",
  "request_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Response Fields

Field	Type	Description
`output.task_id`	string	Unique identifier for the created task. Valid for 24 hours.
`output.task_status`	string	Initial task status (typically `PENDING`).
`request_id`	string	Unique identifier for this API request.
`code`	string	Error code (present only on failure).
`message`	string	Error message (present only on failure).

Step 2: Query Results

Request

Method: GET
URL: https://platform.dataeyes.ai/ali/api/v1/tasks/{task_id}

Replace {task_id} with the task_id returned from Step 1.

Headers

Header	Required	Value
`Authorization`	Yes	`Bearer sk-xxxx`

Polling Tips

Recommended poll interval: 15 seconds.

Query RPS limit: 20 requests per second.

The task_id is valid for 24 hours after creation.

The video_url in the response is valid for 24 hours after generation completes. Download the video promptly.

cURL Example

Success Response (SUCCEEDED)

HTTP Status: 200 OK

{
  "output": {
    "task_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
    "task_status": "SUCCEEDED",
    "submit_time": "2026-06-26 10:00:00.000",
    "scheduled_time": "2026-06-26 10:00:01.000",
    "end_time": "2026-06-26 10:01:30.000",
    "video_url": "https://example.oss.aliyuncs.com/output/video.mp4",
    "orig_prompt": "A golden retriever running across a sunlit meadow, cinematic slow motion, 4K quality"
  },
  "usage": {
    "duration": 5,
    "input_video_duration": 0,
    "output_video_duration": 5,
    "video_count": 1,
    "SR": 0,
    "ratio": "16:9"
  },
  "request_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Failure Response (FAILED)

HTTP Status: 200 OK

{
  "output": {
    "task_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
    "task_status": "FAILED",
    "submit_time": "2026-06-26 10:00:00.000",
    "scheduled_time": "2026-06-26 10:00:01.000",
    "end_time": "2026-06-26 10:01:00.000",
    "code": "InvalidParameter",
    "message": "Generation failed due to invalid input parameters."
  },
  "request_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Expired Task Response

When querying a task_id that has expired (older than 24 hours):

{
  "code": "InvalidParameter",
  "message": "Task not found or has expired.",
  "request_id": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Response Fields

Field	Type	Description
`output.task_id`	string	Unique identifier for the task.
`output.task_status`	string	Current task status. See Task Status Reference.
`output.submit_time`	string	Timestamp when the task was submitted.
`output.scheduled_time`	string	Timestamp when the task was scheduled for processing.
`output.end_time`	string	Timestamp when the task completed (succeeded or failed).
`output.video_url`	string	URL of the generated video (MP4, H.264 codec). Valid for 24 hours. Present only when `task_status` is `SUCCEEDED`.
`output.orig_prompt`	string	The original prompt submitted with the task.
`output.code`	string	Error code (present only when `task_status` is `FAILED`).
`output.message`	string	Error message (present only when `task_status` is `FAILED`).
`usage.duration`	integer	Requested video duration in seconds.
`usage.input_video_duration`	integer	Input video duration in seconds. Fixed to `0` for text-to-video.
`usage.output_video_duration`	integer	Actual output video duration in seconds.
`usage.video_count`	integer	Number of videos generated. Fixed to `1`.
`usage.SR`	integer	Super-resolution flag.
`usage.ratio`	string	Aspect ratio used for generation (e.g., `"16:9"`).
`request_id`	string	Unique identifier for this API request.

Task Status Reference

Status	Description
`PENDING`	Task has been created and is waiting to be processed.
`RUNNING`	Task is currently being processed (video is being generated).
`SUCCEEDED`	Task completed successfully. The `video_url` is available.
`FAILED`	Task failed. Check `output.code` and `output.message` for details.
`CANCELED`	Task was canceled.
`UNKNOWN`	Task status is unknown.

Full Python Example

The following example demonstrates the complete workflow: creating a text-to-video task and polling until completion.

Important Notes

Asynchronous workflow required. The X-DashScope-Async: enable header is mandatory. The API does not support synchronous video generation.

Task ID validity. The task_id is valid for 24 hours after creation. After expiration, query requests will return an error.

Video URL validity. The video_url returned upon task completion is valid for 24 hours. Download or cache the video before the URL expires.

Poll interval. Use a minimum interval of 15 seconds between poll requests. The query endpoint has a rate limit of 20 requests per second.

Prompt length limits. The prompt supports a maximum of 5,000 non-Chinese characters or 2,500 Chinese characters. Exceeding this limit will result in an InvalidParameter error.

Video format. Generated videos are in MP4 format with H.264 codec.

Duration range. The duration parameter accepts integer values from 3 to 15 seconds (inclusive). The default is 5 seconds.

Watermark. By default, a watermark is applied to generated videos. Set "watermark": false to disable it.

Error Codes

Error Code	HTTP Status	Description	Recommended Action
`InvalidApiKey`	401	The API key is missing, malformed, or invalid.	Verify your API key and ensure the `Authorization` header uses the `Bearer` scheme.
`InvalidParameter`	400	One or more request parameters are invalid (e.g., unsupported resolution, prompt too long, expired task ID).	Check the error `message` for details and correct the request parameters.
`Throttling`	429	Request rate limit exceeded.	Reduce request frequency. For task queries, use the recommended 15-second poll interval.

This document is provided by DataEyes. For additional support, contact DataEyes technical support.

HappyHorse Text-to-Video

HappyHorse Text-to-Video API Reference#

Overview#

Supported Models#

Endpoint#

Authentication#

Workflow#

Step 1: Create Task#

Request#

Headers#

Request Body#

input Object#

parameters Object#

cURL Example#

Success Response#

Error Response#

Response Fields#

Step 2: Query Results#

Request#

Headers#

Polling Tips#

cURL Example#

Success Response (SUCCEEDED)#

Failure Response (FAILED)#

Expired Task Response#

Response Fields#

Task Status Reference#

Full Python Example#

Important Notes#

Error Codes#

HappyHorse Text-to-Video API Reference

Overview

Supported Models

Endpoint

Authentication

Workflow

Step 1: Create Task

Request

Headers

Request Body

`input` Object

`parameters` Object

cURL Example

Success Response

Error Response

Response Fields

Step 2: Query Results

Request

Headers

Polling Tips

cURL Example

Success Response (SUCCEEDED)

Failure Response (FAILED)

Expired Task Response

Response Fields

Task Status Reference

Full Python Example

Important Notes

Error Codes