> ## Documentation Index
> Fetch the complete documentation index at: https://api.xcompute.us/llms.txt
> Use this file to discover all available pages before exploring further.

# VEO3 官方视频生成

* 异步处理模式，返回任务ID用于后续查询
* 支持文本转视频、图生视频（首帧/首尾帧控制）
* 支持 720P 和 1080P 分辨率
* 支持 4/6/8 秒视频时长
* 支持生成音频轨道
* 支持人物生成策略控制

<RequestExample>
  ```bash cURL theme={null} theme={null}
  curl --request POST \
    --url https://xcompute.us/v1/videos/generations \
    --header 'Authorization: Bearer <token>' \
    --header 'Content-Type: application/json' \
    --data '{
      "model": "veo3.1-fast-official",
      "prompt": "a golden retriever running on the beach, sunset, cinematic",
      "duration": 8,
      "aspect_ratio": "16:9"
    }'
  ```

  ```python Python theme={null} theme={null}
  import requests

  url = "https://xcompute.us/v1/videos/generations"

  payload = {
      "model": "veo3.1-fast-official",
      "prompt": "a golden retriever running on the beach, sunset, cinematic",
      "duration": 8,
      "aspect_ratio": "16:9"
  }

  headers = {
      "Authorization": "Bearer <token>",
      "Content-Type": "application/json"
  }

  response = requests.post(url, json=payload, headers=headers)

  print(response.json())
  ```

  ```javascript JavaScript theme={null} theme={null}
  const url = "https://xcompute.us/v1/videos/generations";

  const payload = {
    model: "veo3.1-fast-official",
    prompt: "a golden retriever running on the beach, sunset, cinematic",
    duration: 8,
    aspect_ratio: "16:9"
  };

  const headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
  };

  fetch(url, {
    method: "POST",
    headers: headers,
    body: JSON.stringify(payload)
  })
    .then(response => response.json())
    .then(data => console.log(data))
    .catch(error => console.error('Error:', error));
  ```

  ```go Go theme={null} theme={null}
  package main

  import (
      "bytes"
      "encoding/json"
      "fmt"
      "io/ioutil"
      "net/http"
  )

  func main() {
      url := "https://xcompute.us/v1/videos/generations"

      payload := map[string]interface{}{
          "model":        "veo3.1-fast-official",
          "prompt":       "a golden retriever running on the beach, sunset, cinematic",
          "duration":     8,
          "aspect_ratio": "16:9",
      }

      jsonData, _ := json.Marshal(payload)

      req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
      req.Header.Set("Authorization", "Bearer <token>")
      req.Header.Set("Content-Type", "application/json")

      client := &http.Client{}
      resp, err := client.Do(req)
      if err != nil {
          panic(err)
      }
      defer resp.Body.Close()

      body, _ := ioutil.ReadAll(resp.Body)
      fmt.Println(string(body))
  }
  ```

  ```java Java theme={null} theme={null}
  import java.net.http.HttpClient;
  import java.net.http.HttpRequest;
  import java.net.http.HttpResponse;
  import java.net.URI;

  public class Main {
      public static void main(String[] args) throws Exception {
          String url = "https://xcompute.us/v1/videos/generations";

          String payload = """
          {
            "model": "veo3.1-fast-official",
            "prompt": "a golden retriever running on the beach, sunset, cinematic",
            "duration": 8,
            "aspect_ratio": "16:9"
          }
          """;

          HttpClient client = HttpClient.newHttpClient();
          HttpRequest request = HttpRequest.newBuilder()
              .uri(URI.create(url))
              .header("Authorization", "Bearer <token>")
              .header("Content-Type", "application/json")
              .POST(HttpRequest.BodyPublishers.ofString(payload))
              .build();

          HttpResponse<String> response = client.send(request,
              HttpResponse.BodyHandlers.ofString());

          System.out.println(response.body());
      }
  }
  ```

  ```php PHP theme={null} theme={null}
  <?php

  $url = "https://xcompute.us/v1/videos/generations";

  $payload = [
      "model" => "veo3.1-fast-official",
      "prompt" => "a golden retriever running on the beach, sunset, cinematic",
      "duration" => 8,
      "aspect_ratio" => "16:9"
  ];

  $ch = curl_init($url);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
  curl_setopt($ch, CURLOPT_POST, true);
  curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
  curl_setopt($ch, CURLOPT_HTTPHEADER, [
      "Authorization: Bearer <token>",
      "Content-Type: application/json"
  ]);

  $response = curl_exec($ch);
  curl_close($ch);

  echo $response;
  ?>
  ```

  ```ruby Ruby theme={null} theme={null}
  require 'net/http'
  require 'json'
  require 'uri'

  url = URI("https://xcompute.us/v1/videos/generations")

  payload = {
    model: "veo3.1-fast-official",
    prompt: "a golden retriever running on the beach, sunset, cinematic",
    duration: 8,
    aspect_ratio: "16:9"
  }

  http = Net::HTTP.new(url.host, url.port)
  http.use_ssl = true

  request = Net::HTTP::Post.new(url)
  request["Authorization"] = "Bearer <token>"
  request["Content-Type"] = "application/json"
  request.body = payload.to_json

  response = http.request(request)
  puts response.body
  ```

  ```swift Swift theme={null} theme={null}
  import Foundation

  let url = URL(string: "https://xcompute.us/v1/videos/generations")!

  let payload: [String: Any] = [
      "model": "veo3.1-fast-official",
      "prompt": "a golden retriever running on the beach, sunset, cinematic",
      "duration": 8,
      "aspect_ratio": "16:9"
  ]

  var request = URLRequest(url: url)
  request.httpMethod = "POST"
  request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
  request.setValue("application/json", forHTTPHeaderField: "Content-Type")
  request.httpBody = try? JSONSerialization.data(withJSONObject: payload)

  let task = URLSession.shared.dataTask(with: request) { data, response, error in
      if let error = error {
          print("Error: \(error)")
          return
      }

      if let data = data, let responseString = String(data: data, encoding: .utf8) {
          print(responseString)
      }
  }

  task.resume()
  ```

  ```csharp C# theme={null} theme={null}
  using System;
  using System.Net.Http;
  using System.Text;
  using System.Threading.Tasks;

  class Program
  {
      static async Task Main(string[] args)
      {
          var url = "https://xcompute.us/v1/videos/generations";

          var payload = @"{
              ""model"": ""veo3.1-fast-official"",
              ""prompt"": ""a golden retriever running on the beach, sunset, cinematic"",
              ""duration"": 8,
              ""aspect_ratio"": ""16:9""
          }";

          using var client = new HttpClient();
          client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");

          var content = new StringContent(payload, Encoding.UTF8, "application/json");
          var response = await client.PostAsync(url, content);
          var result = await response.Content.ReadAsStringAsync();

          Console.WriteLine(result);
      }
  }
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null} theme={null}
  {
    "code": 200,
    "data": [
      {
        "status": "submitted",
        "task_id": "task_xxxxxxxxxx"
      }
    ]
  }
  ```

  ```json 400 theme={null} theme={null}
  {
    "error": {
      "code": 400,
      "message": "请求参数无效",
      "type": "invalid_request_error"
    }
  }
  ```

  ```json 401 theme={null} theme={null}
  {
    "error": {
      "code": 401,
      "message": "身份验证失败，请检查您的API密钥",
      "type": "authentication_error"
    }
  }
  ```

  ```json 402 theme={null} theme={null}
  {
    "error": {
      "code": 402,
      "message": "账户余额不足，请充值后再试",
      "type": "payment_required"
    }
  }
  ```

  ```json 429 theme={null} theme={null}
  {
    "error": {
      "code": 429,
      "message": "请求过于频繁，请稍后再试",
      "type": "rate_limit_error"
    }
  }
  ```

  ```json 500 theme={null} theme={null}
  {
    "error": {
      "code": 500,
      "message": "服务器内部错误，请稍后重试",
      "type": "server_error"
    }
  }
  ```
</ResponseExample>

## 认证

<ParamField header="Authorization" type="string" required>
  所有接口均需要使用 Bearer Token 进行认证

  获取 API Key：

  访问 [API Key 管理页面](https://xcompute.us/keys) 获取您的 API Key

  使用时在请求头中添加：

  ```
  Authorization: Bearer YOUR_API_KEY
  ```
</ParamField>

## 请求参数

<ParamField body="model" type="string" required>
  视频生成模型名称

  支持的模型：

  * `veo3.1-fast-official` - Veo 3.1 官方快速版
  * `veo3.1-quality-official` - Veo 3.1 官方高质量版
</ParamField>

<ParamField body="prompt" type="string" required>
  正向文本提示词

  建议详细描述场景、动作、风格等，以获得更好的生成效果。建议使用英文提示词。

  示例：`"a golden retriever running on the beach, sunset, cinematic"`
</ParamField>

<ParamField body="negative_prompt" type="string">
  负面提示词，用于排除不想要的内容

  示例：`"blurry, low quality, watermark, text"`
</ParamField>

<ParamField body="duration" type="integer" default="8">
  视频时长（秒）

  建议使用：`4` / `6` / `8`

  默认值：`8`

  **⚠️ 注意：** 必须输入纯数字（如 `8`），不要加引号，否则会报错
</ParamField>

<ParamField body="aspect_ratio" type="string" default="16:9">
  视频宽高比

  可选值：

  * `16:9` - 横屏
  * `9:16` - 竖屏

  默认值：`16:9`
</ParamField>

<ParamField body="resolution" type="string" default="720p">
  视频分辨率

  可选值：

  * `720p` - 标准分辨率
  * `1080p` - 高清分辨率
  * `4K` - 超高清分辨率

  默认值：`720p`
</ParamField>

<ParamField body="first_frame_image" type="string">
  首帧图片 URL，用于图生视频

  <Warning>
    * 图片 URL 必须公开可访问，不能有防盗链
    * 建议使用对象存储 URL，而非临时下载地址
  </Warning>
</ParamField>

<ParamField body="last_frame_image" type="string">
  尾帧图片 URL，用于图生视频

  与 `first_frame_image` 配合使用，实现首尾帧控制
</ParamField>

<ParamField body="seed" type="integer">
  随机种子，用于复现生成结果

  取值范围：`0` - `4294967295`
</ParamField>

<ParamField body="sample_count" type="integer" default="1">
  生成样本数量 1-4，当前建议填 `1`

  默认值：`1`
</ParamField>

<ParamField body="generate_audio" type="boolean" default="false">
  是否生成音频轨道
</ParamField>

<ParamField body="person_generation" type="string" default="allow_adult">
  人物生成策略

  可选值：

  * `allow_adult` - 只允许生成成人人物/成人面孔
  * `disallow` - 不允许生成人物或人脸

  默认值：`allow_adult`
</ParamField>

<ParamField body="resize_mode" type="string" default="pad">
  图片缩放策略（图生视频时生效）

  可选值：

  * `pad` - 填充模式
  * `crop` - 裁剪模式

  默认值：`pad`
</ParamField>

<ParamField body="enhance_prompt" type="boolean" default="true">
  是否启用上游提示词增强

  默认值：`true`

  <Warning>
    * 该参数只能设置为 `true`，设置为 `false` 会导致请求报错
    * 如不需要此参数，请勿传入
  </Warning>
</ParamField>

## 文生视频 vs 图生视频

系统通过是否传入图片参数自动判断模式：不传图片为文生视频，传图片为图生视频。

| 参数                  | 文生视频  | 图生视频     |
| ------------------- | ----- | -------- |
| `prompt`            | ✅ 必填  | ✅ 必填     |
| `first_frame_image` | ❌ 不传  | ✅ 至少传一个  |
| `last_frame_image`  | ❌ 不传  | ✅ 可选（尾帧） |
| `negative_prompt`   | ✅ 可选  | ✅ 可选     |
| `duration`          | ✅ 可选  | ✅ 可选     |
| `aspect_ratio`      | ✅ 可选  | ✅ 可选     |
| `resolution`        | ✅ 可选  | ✅ 可选     |
| `seed`              | ✅ 可选  | ✅ 可选     |
| `generate_audio`    | ✅ 可选  | ✅ 可选     |
| `person_generation` | ✅ 可选  | ✅ 可选     |
| `resize_mode`       | ❌ 不适用 | ✅ 可选     |
| `enhance_prompt`    | ✅ 可选  | ✅ 可选     |

## 响应

<ResponseField name="code" type="integer">
  响应状态码，成功时为 200
</ResponseField>

<ResponseField name="data" type="array">
  返回数据数组

  <Expandable title="数组元素">
    <ResponseField name="status" type="string">
      任务状态，初始提交时为 `submitted`
    </ResponseField>

    <ResponseField name="task_id" type="string">
      任务唯一标识符，用于查询任务状态和结果
    </ResponseField>
  </Expandable>
</ResponseField>

## 使用场景

### 场景 1：文生视频（基础）

```json theme={null} theme={null}
{
  "model": "veo3.1-fast-official",
  "prompt": "a golden retriever running on the beach, sunset, cinematic"
}
```

### 场景 2：文生视频（完整参数）

```json theme={null} theme={null}
{
  "model": "veo3.1-quality-official",
  "prompt": "a cinematic close-up of a ragdoll cat slowly walking through a sunlit living room",
  "negative_prompt": "blurry, low quality, watermark, text",
  "duration": 8,
  "aspect_ratio": "16:9",
  "resolution": "1080p",
  "seed": 12345,
  "generate_audio": true,
  "person_generation": "disallow",
  "enhance_prompt": true
}
```

### 场景 3：图生视频（单张首帧）

```json theme={null} theme={null}
{
  "model": "veo3.1-fast-official",
  "prompt": "the cat slowly walks forward and looks around",
  "first_frame_image": "https://example.com/cat.png",
  "duration": 8,
  "resolution": "720p"
}
```

### 场景 4：图生视频（首帧 + 尾帧）

```json theme={null} theme={null}
{
  "model": "veo3.1-quality-official",
  "prompt": "smooth cinematic transition from the first frame to the last frame",
  "first_frame_image": "https://example.com/frame-start.png",
  "last_frame_image": "https://example.com/frame-end.png",
  "duration": 8,
  "resolution": "1080p"
}
```

### 场景 5：生成带音频的视频

```json theme={null} theme={null}
{
  "model": "veo3.1-quality-official",
  "prompt": "a busy coffee shop with people chatting and barista making latte art",
  "duration": 8,
  "generate_audio": true,
  "aspect_ratio": "16:9"
}
```

<Note>
  **查询任务结果**

  视频生成为异步任务，提交后会返回 `task_id`。使用 [获取任务状态](/cn/api-reference/tasks/status) 接口查询生成进度和结果。
</Note>