> ## Documentation Index
> Fetch the complete documentation index at: https://docs.leapx-hub.com/llms.txt
> Use this file to discover all available pages before exploring further.

# 文生视频-提交任务

## 简介

提交文生视频生成任务，用于根据文本描述生成视频。

## 认证

<ParamField header="Authorization" type="string" required>
  Bearer Token，如 `Bearer eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9...`
  获取方法：依照左侧最上面认证模块的post接口获取，`https://docs.leapx-hub.com/cn/leapx-lab-v4/endpoint/get-token`
</ParamField>

## 请求参数

<ParamField body="model" type="string" required>
  模型名称
</ParamField>

<ParamField body="prompt" type="string" required>
  视频生成的文本提示词
</ParamField>

<ParamField body="duration" type="string" required>
  视频时长，支持格式：3，5, 8, 10, 12
</ParamField>

<ParamField body="aspect_ratio" type="string" required>
  画面比例
</ParamField>

<ParamField body="resolution" type="string">
  视频分辨率
</ParamField>

<ParamField body="return_url" type="boolean">
  是否返回视频URL
</ParamField>

<ParamField body="req_key" type="string">
  请求标识
</ParamField>

### 示例代码

<Tabs>
  <Tab title="cURL示例">
    ```bash theme={null}
    curl -X POST "https://leapx-hub.com/prod-api/nebula/v4/api/nebulaVideoCompletions" \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer sk-xxxxxxxxxx" \
      -d '{
        "model": "video-model-v1",
        "prompt": "一只可爱的小猫在草地上玩耍",
        "duration": 5,
        "aspect_ratio": "16:9"
      }'
    ```
  </Tab>

  <Tab title="Python示例">
    ```python theme={null}
    import requests
    import json

    url = "https://leapx-hub.com/prod-api/nebula/v4/api/nebulaVideoCompletions"
    headers = {
        "Content-Type": "application/json",
        "Authorization": "Bearer sk-xxxxxxxxxx"
    }
    data = {
        "model": "video-model-v1",
        "prompt": "一只可爱的小猫在草地上玩耍",
        "duration": 5,
        "aspect_ratio": "16:9"
    }

    response = requests.post(url, headers=headers, data=json.dumps(data))
    print(response.json())
    ```
  </Tab>
</Tabs>

### 响应示例

<ResponseExample>
  ```json theme={null}
  {
    "code": 200,
    "msg": "操作成功",
    "data": {
      "task_id": "task-1234567890"
    }
  }
  ```
</ResponseExample>