> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.beatapi.io/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.beatapi.io/_mcp/server.

# Kling 3.0

POST https://api.beatapi.io/v1/videos/tasks
Content-Type: application/json

根据文本或一到两帧画面，生成 std 或 pro 档、时长 3–15 秒的视频，支持多镜头分镜和可复用的元素；按秒计费。- 异步：创建请求返回任务 ID，任务成功后才能拿到视频。
- 三种输入方式：纯文本、一张首帧图，或首帧加尾帧。该模型不接受参考图、参考视频或音频。
- `resolution` 是档位：`std` 以 720p 渲染，`pro`（默认）以 1080p 渲染。
- 多镜头：基于一张首帧图，最多五个镜头，每个镜头有各自的提示词和时长。各镜头时长之和必须等于 `duration`。
- 元素：用 `elements` 一次性定义最多三个有名字的主体。
- 按所选档位下的视频秒数计费。失败的任务不收费。POST/v1/videos/tasks试一试在调试窗口里打开本模型，填入你的 BeatAPI API 密钥即可创建任务。调用是真实的，费用从你自己的余额中扣除。## 接口与鉴权`POST https://api.beatapi.io/v1/videos/tasks`Authorization
string
必需你的 BeatAPI API 密钥，以 `Bearer <BEATAPI_API_KEY>` 形式发送。在[控制台](https://beatapi.io/dashboard)创建密钥。密钥只能保存在你的服务端，不要放进浏览器或移动端应用。请求体使用 JSON，并设置 `Content-Type: application/json`。`Idempotency-Key` 为可选：每个逻辑请求发送一个唯一值（最长 255 个字符），仅在重试完全相同的请求体时复用。24 小时内，用相同的键和请求体重试会再次返回第一次的响应，并带上 `Idempotent-Replayed: true`；相同的键搭配不同的请求体则返回 `409 idempotency_conflict`。非 2xx 的响应不会被保存，因此 400 或 402 之后的重试会重新执行。## 请求流程向接口 `POST` 下方的参数。返回 `201` 表示任务已被接受，其价格已从你的余额中预留；任务在后台运行。保存 `data.id`。调用 `GET /v1/tasks/{task_id}`，两次调用之间等待 `data.poll_after_seconds` 秒（图片 5 秒，视频 8 秒），直到 `status` 为 `succeeded` 或 `failed`。也可以为 `task.succeeded` 和 `task.failed` 注册 [Webhook](/webhooks)；仍需保留轮询作为兜底，因为因处理超时而终止的任务不会发送事件。状态为 `succeeded` 时，下载每个 `data.output.media[].url` 并保存你需要的文件；BeatAPI 不承诺结果链接的保留时长。状态为 `failed` 时，读取 `data.error_code` 和 `data.error_message`：预扣的金额已退回你的余额，`data.retryable` 表示再次发送相同请求是否可能成功。## 输入模式| 模式    | 必填输入                                                                   | 说明                               |
| ----- | ---------------------------------------------------------------------- | -------------------------------- |
| 文生视频  | `model`、`prompt`                                                       | 不要传 `images`。                    |
| 首帧    | `model`、`prompt`、`images`（1 个链接）                                       | 视频从这张图开始。                        |
| 首帧和尾帧 | `model`、`prompt`、`images`（2 个链接）                                       | `images[0]` 是首帧，`images[1]` 是尾帧。 |
| 多镜头   | `model`、`prompt`、`images`（恰好 1 个链接）、`multi_shots: true`、`multi_prompt` | 各镜头时长之和必须等于 `duration`（不传则为 5）。  |
| 元素    | `model`、`prompt`、`elements`                                            | 可与上述任一模式组合。最多三个元素。               |## 请求参数model
string
必需要运行的模型。**取值**：`kling-v3`**取值有误时**- 未传：`"model" is required`
- 把图片模型发到了这个端点：`"model" nano-banana-2 is served by POST /v1/images/tasks, not this endpoint`prompt
string
必需视频里发生什么：主体、动作、运镜和风格。**长度**：1–5000 个字符- 长度按字符数计算（一个中日韩字符算一个字符）。
- 所有模式都必须传，包括多镜头；多镜头时，每个镜头还要在 `multi_prompt` 中各有自己的提示词。**取值有误时**- 未传：`"prompt" is required`
- 为空或超过长度上限：`"prompt" has an unsupported length`images
string[]
可选一张首帧，或一张首帧加一张尾帧。**数量**：1–2  \
每一项都必须是公网 `https://` 链接。本地文件请先[上传](/quick-guide#upload-an-input-file)（`POST /v1/files`），再传入返回的 `data.url`。- 一个链接：视频从这张图开始。两个链接：`images[0]` 是首帧，`images[1]` 是尾帧。
- 多镜头（`multi_shots: true`）只接受恰好一张图片。
- 该模型没有参考图字段；某个主体的图片请放在 `elements` 中。**取值有误时**- 多于两个链接：`"images" accepts at most 2 items`
- 空数组：`"images" requires at least 1 item`
- 不是 https\:// 链接：`"images[0]" must be a public HTTPS URL`
- `multi_shots: true` 但没有图片或有两张图片：`Kling V3 multi-shot mode requires exactly one image`duration
integer
可选默认值: 5视频时长，单位为秒，须为整数。计费以它为准。**默认值**：`5`  \
**范围**：3–15- 不传时使用并按 `5` 计费。
- 使用 `multi_shots: true` 时，`multi_prompt` 中各镜头的 `duration` 之和必须恰好等于这个数。若不传 `duration`，则之和必须为 5。**取值有误时**- 超出范围、不是整数，或以字符串传入：`"duration" is outside its supported range`
- 多镜头时长之和不等于 `duration`：`Kling V3 shot durations must sum to duration`aspect_ratio
string
可选默认值: 16:9视频的宽高比（宽:高）。**可选值**：`16:9`, `9:16`, `1:1`  \
**默认值**：`16:9`- 默认值为 `16:9`。**取值有误时**- 取值不在列表中：`"aspect_ratio" must be one of: [16:9 9:16 1:1]`resolution
string
可选默认值: pro画质档位：`std` 以 720p 渲染，`pro` 以 1080p 渲染。`pro` 每秒价格更高。取值是 `std` 和 `pro`，不是像素尺寸。**可选值**：`std`, `pro`  \
**默认值**：`pro`- 不传时使用并按 `pro` 计费。
- 不接受 `4K`、`720p` 和 `1080p`：请传 `std` 或 `pro`。**取值有误时**- 取值不在列表中（例如 `720p` 或 `4K`）：`"resolution" must be one of: [std pro]`sound
boolean
可选视频是否带有生成的配乐。- 不传时，声音跟随 `multi_shots`：多镜头请求开启，其他情况关闭。传 `true` 或 `false` 可自行决定。**取值有误时**- 不是 true 或 false：`"sound" must be a boolean`multi_shots
boolean
可选默认值: false开启分镜模式：视频由 `multi_prompt` 中列出的镜头组成。默认值为 `false`。**默认值**：`false`- 需要在 `images` 中恰好有一张图片，并且 `multi_prompt` 的各镜头时长之和等于 `duration`。没有 `multi_shots: true` 时，`multi_prompt` 会被拒绝。
- 检查按以下顺序进行：先看是否恰好一张图片，再看有没有 `multi_prompt`，最后看时长。**取值有误时**- 不是 true 或 false：`"multi_shots" must be a boolean`
- 没有图片或多于一张图片：`Kling V3 multi-shot mode requires exactly one image`
- `multi_prompt` 缺失：`Kling V3 multi-shot mode requires multi_prompt`
- 各镜头时长之和不等于 `duration`：`Kling V3 shot durations must sum to duration`multi_prompt
object[]
可选多镜头视频的各个镜头，按顺序排列：一到五个对象，每个都有自己的提示词和时长。**数量**：1–5- 每个镜头是一个对象，有两个必填字段，不接受其他字段：
- `multi_prompt[].prompt`（字符串，必填）：这个镜头里发生什么，1 到 500 个字符。
- `multi_prompt[].duration`（整数，必填）：这个镜头的时长，单位为整数秒，1 到 12。
- 各镜头时长之和必须等于请求的 `duration`（不传 `duration` 时为 5），且总和不超过 15。
- 仅在 `multi_shots: true` 时有效。**取值有误时**- 没有 `multi_shots: true` 却传了：`"multi_prompt" requires multi_shots=true`
- 多于五个镜头：`"multi_prompt" accepts at most 5 items`
- 空数组：`"multi_prompt" requires at least 1 item`
- 某个镜头缺少 `prompt`：`"prompt" is required in "multi_prompt[0]"`
- 某个镜头缺少 `duration`：`"duration" is required in "multi_prompt[0]"`
- 某个镜头的提示词为空或超过 500 个字符：`"multi_prompt[0].prompt" has an unsupported length`
- 某个镜头时长不在 1 到 12 之间或不是整数：`"multi_prompt[0].duration" is outside its supported range`
- 出现 `prompt` 和 `duration` 之外的键：`field "name" is not supported in "multi_prompt[0]"`
- 各镜头时长之和不等于 `duration`：`Kling V3 shot durations must sum to duration`elements
object[]
可选最多三个有名字的主体（角色、产品、道具），每个用图片一次性定义。**数量**：≤ 3- 最多三个对象的数组。每个对象接受以下键，不接受其他键：
- `elements[].name`（字符串，必填）：元素的名字，至少 1 个字符。
- `elements[].description`（字符串，可选）：这个元素是什么。不传则用 `name` 作为描述。
- `elements[].element_input_urls`（字符串数组，必填）：1 到 4 个展示该元素的公开 HTTPS 链接。
- `elements[].element_input_audio_urls`（字符串数组，可选）：该元素恰好一个公开 HTTPS 音频链接。
- `elements[].start_time` 和 `elements[].end_time`（整数，可选）：时间，单位为毫秒，各自为 0 到 30000 的整数。要么都传，要么都不传。`end_time` 必须大于 `start_time`，且 `end_time - start_time` 必须在 3000 到 8000 之间（3 到 8 秒）。
- 链接数量的限制对每个元素分别适用：每个条目都可以有自己的四个链接和一个音频链接。**取值有误时**- 多于三个元素：`"elements" accepts at most 3 items`
- 元素不是对象：`"elements[0]" must be an object`
- 元素缺少 `name`：`"name" is required in "elements[0]"`
- 元素缺少 `element_input_urls`：`"element_input_urls" is required in "elements[0]"`
- `name` 为空：`"elements[0].name" has an unsupported length`
- 多于四个链接：`"elements[0].element_input_urls" accepts at most 4 items`
- `element_input_urls` 为空数组：`"elements[0].element_input_urls" requires at least 1 item`
- 链接不是 https\://：`"elements[0].element_input_urls[1]" must be a public HTTPS URL`
- 多于一个音频链接：`"elements[0].element_input_audio_urls" accepts at most 1 items`
- `start_time` 或 `end_time` 不在 0 到 30000 之间，或不是整数：`"elements[0].start_time" is outside its supported range`
- 元素中出现不接受的键：`field "color" is not supported in "elements[0]"`
- 只传了 `start_time` 和 `end_time` 之一、`end_time` 不晚于 `start_time`，或片段短于 3 秒或长于 8 秒：`Kling V3 element segment must provide a 3-8 second start_time/end_time range`## 输入素材限制网关会在创建任务之前读取每一项输入，超出这些限制的输入会被拒绝，并返回点名该输入的 `400 bad_request`。不扣费。- 网关在创建任务前只检查每张图片、元素链接和音频链接是否为公开 HTTPS 链接，不会检查大小、格式或尺寸。因此模型无法使用的输入会在提交后导致任务失败；失败信息会说明需要修改什么，并全额退还预扣费用。
- 只有本地文件？先用 `POST /v1/files` 上传，再传入返回的 `data.url`。## 多镜头规则创建任务时按以下顺序检查；违反任一规则的请求会被 `400 bad_request` 拒绝，且不收费。| 规则                                          | 报错信息                                                  |
| ------------------------------------------- | ----------------------------------------------------- |
| 传了 `multi_prompt`，但 `multi_shots` 不是 `true` | `"multi_prompt" requires multi_shots=true`            |
| `multi_shots: true`，但 `images` 中不是恰好一张图片    | `Kling V3 multi-shot mode requires exactly one image` |
| `multi_shots: true`，但没有 `multi_prompt`      | `Kling V3 multi-shot mode requires multi_prompt`      |
| 各镜头时长之和不等于 `duration`（不传则为 5）               | `Kling V3 shot durations must sum to duration`        |- 不支持纯文本的多镜头：多镜头视频总是从一张图片开始。
- 多镜头请求按 `duration` 秒计费，即各镜头时长之和。## 该模型不接受的字段传入下列字段会在扣费前被拒绝，而不是被忽略：- `reference_images`、`reference_videos`、`reference_audios`、`generate_audio`、`seed`、`quality`、`watermark`、`task_type`、`output_format` → `field "reference_images" is not supported by model kling-v3`（其中是你传入的字段名）。
- 其他任何未知字段 → `unknown field: <name>`。## 请求示例```bash title="cURL"
curl --request POST \
  --url https://api.beatapi.io/v1/videos/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "kling-v3",
  "prompt": "A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections",
  "duration": 5,
  "aspect_ratio": "16:9",
  "resolution": "pro",
  "sound": true
}'
``````python title="Python"
import os
import requests

response = requests.post(
    "https://api.beatapi.io/v1/videos/tasks",
    headers={"Authorization": f"Bearer {os.environ['BEATAPI_API_KEY']}"},
    json={
      "model": "kling-v3",
      "prompt": "A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections",
      "duration": 5,
      "aspect_ratio": "16:9",
      "resolution": "pro",
      "sound": True
    },
    timeout=60,
)
body = response.json()
if not response.ok:
    raise RuntimeError(f"{response.status_code} {body['error']['code']}: {body['error']['message']}")
task = body["data"]
print(task["id"], task["status"])
``````javascript title="JavaScript"
const response = await fetch('https://api.beatapi.io/v1/videos/tasks', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.BEATAPI_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "kling-v3",
    "prompt": "A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections",
    "duration": 5,
    "aspect_ratio": "16:9",
    "resolution": "pro",
    "sound": true
  }),
});
const body = await response.json();
if (!response.ok) throw new Error(`${response.status} ${body.error.code}: ${body.error.message}`);
console.log(body.data.id, body.data.status);
```### 文生视频pro 档（1080p）、带声音的 5 秒片段。```bash
curl --request POST \
  --url https://api.beatapi.io/v1/videos/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "kling-v3",
  "prompt": "A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections",
  "duration": 5,
  "aspect_ratio": "16:9",
  "resolution": "pro",
  "sound": true
}'
```### 首帧视频从这张图开始。```bash
curl --request POST \
  --url https://api.beatapi.io/v1/videos/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "kling-v3",
  "prompt": "The bottle slowly rotates on its pedestal while reflections move across the glass",
  "images": [
    "https://media.beatapi.io/samples/smart-bottle.png"
  ],
  "duration": 5,
  "resolution": "pro",
  "sound": true
}'
```### 首帧和尾帧视频从第一张图过渡到第二张图，使用更便宜的 std 档（720p）。```bash
curl --request POST \
  --url https://api.beatapi.io/v1/videos/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "kling-v3",
  "prompt": "The camera moves from the bottle on the table to the singer on a neon stage in one continuous shot",
  "images": [
    "https://media.beatapi.io/samples/smart-bottle.png",
    "https://media.beatapi.io/samples/neon-singer.png"
  ],
  "duration": 5,
  "resolution": "std"
}'
```### 多镜头基于一张首帧图的两个 3 秒镜头。镜头时长之和（3 + 3）等于 `duration`（6）。```bash
curl --request POST \
  --url https://api.beatapi.io/v1/videos/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "kling-v3",
  "prompt": "A two-shot cinematic product reveal",
  "images": [
    "https://media.beatapi.io/samples/smart-bottle.png"
  ],
  "duration": 6,
  "aspect_ratio": "16:9",
  "resolution": "pro",
  "sound": true,
  "multi_shots": true,
  "multi_prompt": [
    {
      "prompt": "Macro detail shot of the bottle with moving reflections",
      "duration": 3
    },
    {
      "prompt": "Wide hero reveal of the bottle on a dark pedestal",
      "duration": 3
    }
  ]
}'
```### 可复用的元素用两张图片定义一个有名字的元素。该元素名为 `product`，描述是可选的。```bash
curl --request POST \
  --url https://api.beatapi.io/v1/videos/tasks \
  --header "Authorization: Bearer $BEATAPI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "kling-v3",
  "prompt": "A slow cinematic camera orbit around the product",
  "duration": 5,
  "resolution": "pro",
  "elements": [
    {
      "name": "product",
      "description": "The featured water bottle",
      "element_input_urls": [
        "https://media.beatapi.io/samples/smart-bottle.png",
        "https://media.beatapi.io/samples/neon-singer.png"
      ]
    }
  ]
}'
```## 响应### 创建任务（201）任务对象。任务成功之前 `output` 为 `null`。标注“运行中”的字段会在任务结束后消失。```json
{
  "data": {
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "object": "task",
    "task_kind": "video",
    "capability_id": "kling-v3",
    "capability_version": 1,
    "media_type": "video",
    "model": "kling-v3",
    "status": "queued",
    "stage": "queued",
    "created_at": 1791993600,
    "updated_at": 1791993600,
    "completed_at": null,
    "poll_after_seconds": 8,
    "output": null,
    "usage": {
      "credits_reserved": 0.65,
      "credits_settled": 0,
      "credits_refunded": 0,
      "credits_charged": 0.65,
      "billable_duration_seconds": 5
    },
    "request_id": "req_5f0c2a9e4b7d4e31",
    "error_code": null,
    "error_message": null
  }
}
```| 字段                                     | 类型                | 说明                                                                        |
| -------------------------------------- | ----------------- | ------------------------------------------------------------------------- |
| `data.id`                              | `string`          | 任务 ID：`task_` 后接 32 位字母和数字。用于轮询以及匹配 Webhook 事件。                           |
| `data.object`                          | `string`          | 固定为 `task`。                                                               |
| `data.task_kind`                       | `string`          | `image` 或 `video`。                                                        |
| `data.capability_id`                   | `string`          | 你发送的模型 ID。                                                                |
| `data.capability_version`              | `integer`         | 模型的契约版本，当前为 `1`。                                                          |
| `data.media_type`                      | `string`          | `image` 或 `video`。                                                        |
| `data.model`                           | `string`          | 你发送的模型 ID（与 `capability_id` 相同）。                                          |
| `data.status`                          | `string`          | `queued`、`processing`、`succeeded` 或 `failed`。只有后两个是终态。                    |
| `data.stage`                           | `string`          | 与 `status` 相同；为旧版客户端保留。                                                   |
| `data.created_at`                      | `integer`         | 任务创建时间，Unix 秒。                                                            |
| `data.updated_at`                      | `integer`         | 最后一次变更时间，Unix 秒。                                                          |
| `data.completed_at`                    | `integer \| null` | 任务结束时间，Unix 秒；运行中为 `null`。                                                |
| `data.poll_after_seconds`              | `integer`         | 运行中：下一次轮询前需要等待的秒数（图片 5，视频 8）。                                             |
| `data.typical_seconds`                 | `object`          | 运行中且近期样本足够时出现：在最近的 `window` 内，根据 `samples` 个任务统计的完成时间 `p50` 和 `p90`，单位为秒。 |
| `data.output`                          | `object \| null`  | 任务结果；`status` 为 `succeeded` 之前为 `null`。见下方输出字段。                           |
| `data.usage.credits_reserved`          | `number`          | 创建任务时从你的余额中预扣的美元金额。                                                       |
| `data.usage.credits_charged`           | `number`          | 该任务的费用（美元）；失败的任务为 `0`。                                                    |
| `data.usage.credits_settled`           | `number`          | 最终结算扣除的美元金额；任务成功时设置，否则为 `0`。                                              |
| `data.usage.credits_refunded`          | `number`          | 退回你余额的美元金额；失败的任务在退款记录完成后等于预扣金额。                                           |
| `data.usage.billable_duration_seconds` | `integer`         | 仅视频：计价所依据的秒数。模型未上报时长时不出现。                                                 |
| `data.request_id`                      | `string`          | 请求 ID。联系支持时请附上。                                                           |
| `data.error_code`                      | `string \| null`  | 失败码；任务未失败时为 `null`。                                                       |
| `data.error_message`                   | `string \| null`  | 出了什么问题以及该改什么；任务未失败时为 `null`。                                              |### 任务完成`GET /v1/tasks/{task_id}` 返回 HTTP 200 和 `status: "succeeded"`，结果在 `data.output` 中。```json
{
  "data": {
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "object": "task",
    "task_kind": "video",
    "capability_id": "kling-v3",
    "capability_version": 1,
    "media_type": "video",
    "model": "kling-v3",
    "status": "succeeded",
    "stage": "succeeded",
    "created_at": 1791993600,
    "updated_at": 1791993690,
    "completed_at": 1791993690,
    "output": {
      "media": [
        {
          "type": "video",
          "url": "https://media.beatapi.io/outputs/task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ/0.mp4",
          "mime_type": "video/mp4"
        }
      ],
      "r2_url": "https://media.beatapi.io/outputs/task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ/0.mp4"
    },
    "usage": {
      "credits_reserved": 0.65,
      "credits_settled": 0.65,
      "credits_refunded": 0,
      "credits_charged": 0.65,
      "billable_duration_seconds": 5
    },
    "request_id": "req_5f0c2a9e4b7d4e31",
    "error_code": null,
    "error_message": null
  }
}
```#### 输出字段| 字段                         | 类型         | 说明                                 |
| -------------------------- | ---------- | ---------------------------------- |
| `output.media`             | `object[]` | 生成的文件；该模型只有一个视频。                   |
| `output.media[].type`      | `string`   | 固定为 `video`。                       |
| `output.media[].url`       | `string`   | 已存储视频的 HTTPS 链接。请下载并自行保存，不承诺保留期限。  |
| `output.media[].mime_type` | `string`   | 文件的媒体类型，通常为 `video/mp4`。           |
| `output.r2_url`            | `string`   | 再次给出视频 URL，供旧版客户端使用。请改为读取 `media`。 |### 任务失败失败的任务在 `GET /v1/tasks/{task_id}` 上仍然是 HTTP 200：失败信息在响应体里。预扣金额会全额退回，因此不会扣费。```json
{
  "data": {
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "object": "task",
    "task_kind": "video",
    "capability_id": "kling-v3",
    "capability_version": 1,
    "media_type": "video",
    "model": "kling-v3",
    "status": "failed",
    "stage": "failed",
    "created_at": 1791993600,
    "updated_at": 1791993690,
    "completed_at": 1791993690,
    "output": null,
    "usage": {
      "credits_reserved": 0.65,
      "credits_settled": 0,
      "credits_refunded": 0.65,
      "credits_charged": 0,
      "billable_duration_seconds": 5
    },
    "retryable": true,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "error_code": "processing_failed",
    "error_message": "The task failed during processing on our side. Retry; a failed task is refunded."
  }
}
```| 字段                   | 类型        | 说明                                                                                                                                                                          |
| -------------------- | --------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `data.error_code`    | `string`  | `bad_request` 和 `content_policy_violation`（需修改请求）之一，或 `processing_unavailable`、`processing_timeout`、`processing_failed` 和 `result_transfer_failed`（稍后重试）之一。见[错误码](/errors)。 |
| `data.error_message` | `string`  | 一句话，指出问题和处理方式。                                                                                                                                                              |
| `data.retryable`     | `boolean` | 仅在任务失败时出现：为 `true` 表示再次发送相同请求可能成功。                                                                                                                                          |
| `data.usage`         | `object`  | 退款记录完成后（通常就在任务失败的那一刻）：`credits_charged` 和 `credits_settled` 为 `0`；`credits_refunded` 等于 `credits_reserved`。                                                                 |## 完整示例创建任务，按服务端给出的轮询提示等待，然后打印结果链接。请在环境变量中设置 `BEATAPI_API_KEY` 并安装 `requests`。```python
import os
import time
import uuid

import requests

API = "https://api.beatapi.io"
HEADERS = {"Authorization": f"Bearer {os.environ['BEATAPI_API_KEY']}"}


def create_task(body: dict) -> dict:
    # One Idempotency-Key per logical request: a retry with the same key cannot create a second task.
    headers = {**HEADERS, "Idempotency-Key": str(uuid.uuid4())}
    for attempt in range(3):
        response = requests.post(f"{API}/v1/videos/tasks", headers=headers, json=body, timeout=60)
        if response.status_code in (429, 503) and attempt < 2:
            time.sleep(int(response.headers.get("Retry-After", 10)))
            continue
        break
    try:
        payload = response.json()
    except ValueError:  # an edge error page is not JSON
        response.raise_for_status()
        raise
    if not response.ok:
        error = payload["error"]
        raise RuntimeError(f"{response.status_code} {error['code']}: {error['message']} (request_id={error.get('request_id')})")
    return payload["data"]


def wait_for_task(task_id: str, timeout_seconds: int = 1800) -> dict:
    deadline = time.monotonic() + timeout_seconds
    while time.monotonic() < deadline:
        response = requests.get(f"{API}/v1/tasks/{task_id}", headers=HEADERS, timeout=30)
        if response.status_code == 429 or response.status_code >= 500:
            time.sleep(int(response.headers.get("Retry-After", 10)))
            continue
        response.raise_for_status()
        task = response.json()["data"]
        if task["status"] in ("succeeded", "failed"):
            return task
        time.sleep(task.get("poll_after_seconds", 5))
    raise TimeoutError(f"task {task_id} is still running; keep polling later")


task = create_task({
  "model": "kling-v3",
  "prompt": "A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections",
  "duration": 5,
  "aspect_ratio": "16:9",
  "resolution": "pro",
  "sound": True
})
print("created", task["id"])
task = wait_for_task(task["id"])
if task["status"] == "failed":
    raise SystemExit(f"{task['error_code']}: {task['error_message']}")
for item in task["output"]["media"]:
    print(item["url"])
```## 计费- `sound` 不影响价格：价格只取决于 `duration` 和 `resolution`，因此无论是否开启声音，都适用下方的价格行。
- 按所选档位下的视频秒数计费：下方列表显示的是 8 秒片段的价格，除以 8 即为每秒单价（`std` 约 $0.11 每秒，`pro` 约 $0.13）。
- 秒数即 `duration`，不传则为 5；多镜头请求则是各镜头时长之和，也就等于 `duration`。任务上的 `usage.billable_duration_seconds` 会显示该值。
- 价格在创建任务时预扣，视频生成完成后结算。任务失败（包括提交后被内容审核拒绝）会全额退款。## 常见错误| 错误或现象                                                                              | 原因                                                                                             | 处理方式                                                   |
| ---------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
| 400 `"resolution" must be one of: [std pro]`                                       | 传了 `720p`、`1080p` 或 `4K` 这样的像素尺寸。该模型接受的是档位。                                                    | 传 `std`（以 720p 渲染）或 `pro`（以 1080p 渲染）。                 |
| 400 `Kling V3 multi-shot mode requires exactly one image`                          | `multi_shots: true` 但没有图片，或有两张图片。                                                              | 在 `images` 中传一张图片。不支持纯文本的多镜头。                          |
| 400 `Kling V3 shot durations must sum to duration`                                 | `multi_prompt` 各镜头时长之和不等于 `duration`；不传 `duration` 时，之和不等于 5。                                  | 让各镜头时长之和恰好等于 `duration`，例如 `duration: 6` 时用 3 + 3。     |
| 400 `"multi_prompt" requires multi_shots=true`                                     | 传了 `multi_prompt`，但没有传 `multi_shots: true`。                                                    | 加上 `multi_shots: true`，或删除 `multi_prompt`。             |
| 400 `Kling V3 multi-shot mode requires multi_prompt`                               | `multi_shots: true` 但没有 `multi_prompt`。                                                        | 加上包含一到五个镜头的 `multi_prompt`。                            |
| 400 `Kling V3 element segment must provide a 3-8 second start_time/end_time range` | 某个元素只传了 `start_time` 和 `end_time` 之一，或 `end_time` 不晚于 `start_time`，或片段短于 3 秒或长于 8 秒。两者的单位都是毫秒。 | 两者都传，单位为毫秒，且 `end_time - start_time` 在 3000 到 8000 之间。 |
| 400 `"elements[0].element_input_urls" accepts at most 4 items`                     | 一个元素里有多于四个链接。                                                                                  | 每个元素最多保留四个链接；把不同主体拆成不同元素（最多三个）。                        |
| 400 `field "reference_images" is not supported by model kling-v3`                  | 该模型没有参考类字段（`generate_audio`、`seed`、`quality` 同理）。                                              | 删除该字段。某个主体的图片请放在 `elements` 中。                         |
| 400 `"duration" is outside its supported range`                                    | 不是 3 到 15 的整数，或以字符串传入。                                                                         | 传整数，例如 `5`。                                            |
| 任务 `failed`，原因为 `content_policy_violation`                                         | 提示词、输入图片或生成结果被内容审核拒绝。                                                                          | 修改提示词或图片。原样重试仍会失败；不收费。                                 |
| 402 `insufficient_credits`                                                         | 余额低于该时长和档位所需的预扣金额。                                                                             | 充值、缩短 `duration`，或使用 `std`。                            |## HTTP 错误速查任务生成之前的错误会以非 2xx 响应返回，不扣费。请根据 `error.code` 或 `error.retryable` 判断处理方式；`message` 会指出问题所在。完整列表和重试策略见[错误码](/errors)。```json
{
  "error": {
    "code": "bad_request",
    "message": "\"prompt\" is required",
    "retryable": false,
    "request_id": "req_5f0c2a9e4b7d4e31"
  }
}
```| HTTP 状态码 | `error.code`                                                                                  | 处理方式                                                   |
| -------- | --------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
| 400      | `bad_request`, `content_policy_violation`                                                     | 修改请求；message 会点名出错的字段。不要原样重试。                          |
| 401      | `missing_api_key`, `invalid_api_key`（旧版客户端可能看到 `unauthorized`）                                | 以 `Authorization: Bearer <key>` 发送有效的密钥。               |
| 402      | `insufficient_credits`                                                                        | 充值，或提高密钥的额度，然后重新发送。                                    |
| 403      | `forbidden`                                                                                   | 该密钥或账户不能使用此模型（例如免费额度只覆盖部分模型）。不要原样重试。                   |
| 404      | `not_found`                                                                                   | 在 `GET /v1/tasks/{task_id}` 上：该任务在此密钥所属账户下不存在。请检查 ID。  |
| 409      | `idempotency_conflict`                                                                        | 换一个新的 `Idempotency-Key`，或等待使用该键的第一个请求完成。               |
| 429      | `rate_limit_exceeded`                                                                         | 等待 `Retry-After` 秒（也见 `error.retry_after_seconds`）后重试。 |
| 500      | `internal_error`                                                                              | 退避重试；若持续出现，请带上 `request_id` 联系支持。                      |
| 503      | `processing_unavailable`, `processing_timeout`, `processing_failed`, `result_transfer_failed` | 未扣费。使用指数退避重试。                                          |

Reference: https://docs.beatapi.io/api-reference/video-api/kling-3

## Authentication

- `Authorization` header (bearer token, required) — Send your API key as `Authorization: Bearer <BEATAPI_API_KEY>`.

## Servers

- `https://api.beatapi.io` (Direct, default)
- `https://api.beatapi.io` (API)

## Request

### Headers

- `Idempotency-Key` (string, optional) — 请求体使用 JSON，并设置 `Content-Type: application/json`。`Idempotency-Key` 为可选：每个逻辑请求发送一个唯一值（最长 255 个字符），仅在重试完全相同的请求体时复用。24 小时内，用相同的键和请求体重试会再次返回第一次的响应，并带上 `Idempotent-Replayed: true`；相同的键搭配不同的请求体则返回 `409 idempotency_conflict`。非 2xx 的响应不会被保存，因此 400 或 402 之后的重试会重新执行。

### Body (application/json)

This endpoint expects a Kling3VideoRequest.

- `model` (enum, required) — 要运行的模型。 **取值**：`kling-v3` **取值有误时** - 未传：`"model" is required` - 把图片模型发到了这个端点：`"model" nano-banana-2 is served by POST /v1/images/tasks, not this endpoint`
  - Allowed values: `kling-v3`
- `prompt` (string, required) — 视频里发生什么：主体、动作、运镜和风格。 **长度**：1–5000 个字符 - 长度按字符数计算（一个中日韩字符算一个字符）。 - 所有模式都必须传，包括多镜头；多镜头时，每个镜头还要在 `multi_prompt` 中各有自己的提示词。 **取值有误时** - 未传：`"prompt" is required` - 为空或超过长度上限：`"prompt" has an unsupported length`
- `aspect_ratio` (enum, optional, default: 16:9) — 视频的宽高比（宽:高）。 **可选值**：`16:9`, `9:16`, `1:1` **默认值**：`16:9` - 默认值为 `16:9`。 **取值有误时** - 取值不在列表中：`"aspect_ratio" must be one of: [16:9 9:16 1:1]`
  - Allowed values: `16:9`, `9:16`, `1:1`
- `duration` (integer, optional, default: 5) — 视频时长，单位为秒，须为整数。计费以它为准。 **默认值**：`5` **范围**：3–15 - 不传时使用并按 `5` 计费。 - 使用 `multi_shots: true` 时，`multi_prompt` 中各镜头的 `duration` 之和必须恰好等于这个数。若不传 `duration`，则之和必须为 5。 **取值有误时** - 超出范围、不是整数，或以字符串传入：`"duration" is outside its supported range` - 多镜头时长之和不等于 `duration`：`Kling V3 shot durations must sum to duration`
- `elements` (list of Kling3VideoRequestElementsItems, optional) — 最多三个有名字的主体（角色、产品、道具），每个用图片一次性定义。 **数量**：≤ 3 - 最多三个对象的数组。每个对象接受以下键，不接受其他键： - `elements[].name`（字符串，必填）：元素的名字，至少 1 个字符。 - `elements[].description`（字符串，可选）：这个元素是什么。不传则用 `name` 作为描述。 - `elements[].element_input_urls`（字符串数组，必填）：1 到 4 个展示该元素的公开 HTTPS 链接。 - `elements[].element_input_audio_urls`（字符串数组，可选）：该元素恰好一个公开 HTTPS 音频链接。 - `elements[].start_time` 和 `elements[].end_time`（整数，可选）：时间，单位为毫秒，各自为 0 到 30000 的整数。要么都传，要么都不传。`end_time` 必须大于 `start_time`，且 `end_time - start_time` 必须在 3000 到 8000 之间（3 到 8 秒）。 - 链接数量的限制对每个元素分别适用：每个条目都可以有自己的四个链接和一个音频链接。 **取值有误时** - 多于三个元素：`"elements" accepts at most 3 items` - 元素不是对象：`"elements[0]" must be an object` - 元素缺少 `name`：`"name" is required in "elements[0]"` - 元素缺少 `element_input_urls`：`"element_input_urls" is required in "elements[0]"` - `name` 为空：`"elements[0].name" has an unsupported length` - 多于四个链接：`"elements[0].element_input_urls" accepts at most 4 items` - `element_input_urls` 为空数组：`"elements[0].element_input_urls" requires at least 1 item` - 链接不是 https://：`"elements[0].element_input_urls[1]" must be a public HTTPS URL` - 多于一个音频链接：`"elements[0].element_input_audio_urls" accepts at most 1 items` - `start_time` 或 `end_time` 不在 0 到 30000 之间，或不是整数：`"elements[0].start_time" is outside its supported range` - 元素中出现不接受的键：`field "color" is not supported in "elements[0]"` - 只传了 `start_time` 和 `end_time` 之一、`end_time` 不晚于 `start_time`，或片段短于 3 秒或长于 8 秒：`Kling V3 element segment must provide a 3-8 second start_time/end_time range`
- `images` (list of string, optional) — 一张首帧，或一张首帧加一张尾帧。 **数量**：1–2 每一项都必须是公网 `https://` 链接。本地文件请先[上传](/quick-guide#upload-an-input-file)（`POST /v1/files`），再传入返回的 `data.url`。 - 一个链接：视频从这张图开始。两个链接：`images[0]` 是首帧，`images[1]` 是尾帧。 - 多镜头（`multi_shots: true`）只接受恰好一张图片。 - 该模型没有参考图字段；某个主体的图片请放在 `elements` 中。 **取值有误时** - 多于两个链接：`"images" accepts at most 2 items` - 空数组：`"images" requires at least 1 item` - 不是 https:// 链接：`"images[0]" must be a public HTTPS URL` - `multi_shots: true` 但没有图片或有两张图片：`Kling V3 multi-shot mode requires exactly one image`
- `multi_prompt` (list of Kling3VideoRequestMultiPromptItems, optional) — 多镜头视频的各个镜头，按顺序排列：一到五个对象，每个都有自己的提示词和时长。 **数量**：1–5 - 每个镜头是一个对象，有两个必填字段，不接受其他字段： - `multi_prompt[].prompt`（字符串，必填）：这个镜头里发生什么，1 到 500 个字符。 - `multi_prompt[].duration`（整数，必填）：这个镜头的时长，单位为整数秒，1 到 12。 - 各镜头时长之和必须等于请求的 `duration`（不传 `duration` 时为 5），且总和不超过 15。 - 仅在 `multi_shots: true` 时有效。 **取值有误时** - 没有 `multi_shots: true` 却传了：`"multi_prompt" requires multi_shots=true` - 多于五个镜头：`"multi_prompt" accepts at most 5 items` - 空数组：`"multi_prompt" requires at least 1 item` - 某个镜头缺少 `prompt`：`"prompt" is required in "multi_prompt[0]"` - 某个镜头缺少 `duration`：`"duration" is required in "multi_prompt[0]"` - 某个镜头的提示词为空或超过 500 个字符：`"multi_prompt[0].prompt" has an unsupported length` - 某个镜头时长不在 1 到 12 之间或不是整数：`"multi_prompt[0].duration" is outside its supported range` - 出现 `prompt` 和 `duration` 之外的键：`field "name" is not supported in "multi_prompt[0]"` - 各镜头时长之和不等于 `duration`：`Kling V3 shot durations must sum to duration`
- `multi_shots` (boolean, optional, default: false) — 开启分镜模式：视频由 `multi_prompt` 中列出的镜头组成。默认值为 `false`。 **默认值**：`false` - 需要在 `images` 中恰好有一张图片，并且 `multi_prompt` 的各镜头时长之和等于 `duration`。没有 `multi_shots: true` 时，`multi_prompt` 会被拒绝。 - 检查按以下顺序进行：先看是否恰好一张图片，再看有没有 `multi_prompt`，最后看时长。 **取值有误时** - 不是 true 或 false：`"multi_shots" must be a boolean` - 没有图片或多于一张图片：`Kling V3 multi-shot mode requires exactly one image` - `multi_prompt` 缺失：`Kling V3 multi-shot mode requires multi_prompt` - 各镜头时长之和不等于 `duration`：`Kling V3 shot durations must sum to duration`
- `resolution` (enum, optional, default: pro) — 画质档位：`std` 以 720p 渲染，`pro` 以 1080p 渲染。`pro` 每秒价格更高。取值是 `std` 和 `pro`，不是像素尺寸。 **可选值**：`std`, `pro` **默认值**：`pro` - 不传时使用并按 `pro` 计费。 - 不接受 `4K`、`720p` 和 `1080p`：请传 `std` 或 `pro`。 **取值有误时** - 取值不在列表中（例如 `720p` 或 `4K`）：`"resolution" must be one of: [std pro]`
  - Allowed values: `std`, `pro`
- `sound` (boolean, optional) — 视频是否带有生成的配乐。 - 不传时，声音跟随 `multi_shots`：多镜头请求开启，其他情况关闭。传 `true` 或 `false` 可自行决定。 **取值有误时** - 不是 true 或 false：`"sound" must be a boolean`

## Response

### 201

任务对象。任务成功之前 `output` 为 `null`。标注“运行中”的字段会在任务结束后消失。

- `map from string to any`

## Errors

### 400 Bad Request Error

`bad_request`, `content_policy_violation` 修改请求；message 会点名出错的字段。不要原样重试。

- `map from string to any`

### 401 Unauthorized Error

`missing_api_key`, `invalid_api_key`（旧版客户端可能看到 `unauthorized`） 以 `Authorization: Bearer <key>` 发送有效的密钥。

- `map from string to any`

### 402 Payment Required Error

`insufficient_credits` 充值，或提高密钥的额度，然后重新发送。

- `map from string to any`

### 403 Forbidden Error

`forbidden` 该密钥或账户不能使用此模型（例如免费额度只覆盖部分模型）。不要原样重试。

- `map from string to any`

### 409 Conflict Error

`idempotency_conflict` 换一个新的 `Idempotency-Key`，或等待使用该键的第一个请求完成。

- `map from string to any`

### 429 Too Many Requests Error

`rate_limit_exceeded` 等待 `Retry-After` 秒（也见 `error.retry_after_seconds`）后重试。

- `map from string to any`

### 500 Internal Server Error

`internal_error` 退避重试；若持续出现，请带上 `request_id` 联系支持。

- `map from string to any`

### 503 Service Unavailable Error

`processing_unavailable`, `processing_timeout`, `processing_failed`, `result_transfer_failed` 未扣费。使用指数退避重试。

- `map from string to any`

## Types

### Kling3VideoRequestElementsItems

- `element_input_urls` (list of string, required) — `elements[].element_input_urls`（字符串数组，必填）：1 到 4 个展示该元素的公开 HTTPS 链接。 **数量**：1–4 每一项都必须是公网 `https://` 链接。本地文件请先[上传](/quick-guide#upload-an-input-file)（`POST /v1/files`），再传入返回的 `data.url`。
- `name` (string, required) — `elements[].name`（字符串，必填）：元素的名字，至少 1 个字符。 **长度**：≥ 1 个字符
- `description` (string, optional) — `elements[].description`（字符串，可选）：这个元素是什么。不传则用 `name` 作为描述。
- `element_input_audio_urls` (list of string, optional) — `elements[].element_input_audio_urls`（字符串数组，可选）：该元素恰好一个公开 HTTPS 音频链接。 **数量**：1–1 每一项都必须是公网 `https://` 链接。本地文件请先[上传](/quick-guide#upload-an-input-file)（`POST /v1/files`），再传入返回的 `data.url`。
- `end_time` (integer, optional) — `elements[].start_time` 和 `elements[].end_time`（整数，可选）：时间，单位为毫秒，各自为 0 到 30000 的整数。要么都传，要么都不传。`end_time` 必须大于 `start_time`，且 `end_time - start_time` 必须在 3000 到 8000 之间（3 到 8 秒）。 **范围**：0–30000
- `start_time` (integer, optional) — `elements[].start_time` 和 `elements[].end_time`（整数，可选）：时间，单位为毫秒，各自为 0 到 30000 的整数。要么都传，要么都不传。`end_time` 必须大于 `start_time`，且 `end_time - start_time` 必须在 3000 到 8000 之间（3 到 8 秒）。 **范围**：0–30000

### Kling3VideoRequestMultiPromptItems

- `duration` (integer, required) — `multi_prompt[].duration`（整数，必填）：这个镜头的时长，单位为整数秒，1 到 12。 **范围**：1–12
- `prompt` (string, required) — `multi_prompt[].prompt`（字符串，必填）：这个镜头里发生什么，1 到 500 个字符。 **长度**：1–500 个字符

## Examples

### 文生视频

**Request**

```json
{
  "model": "kling-v3",
  "prompt": "A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections",
  "aspect_ratio": "16:9",
  "duration": 5,
  "resolution": "pro",
  "sound": true
}
```

**Response**

```json
{
  "data": {
    "capability_id": "kling-v3",
    "capability_version": 1,
    "completed_at": null,
    "created_at": 1791993600,
    "error_code": null,
    "error_message": null,
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "media_type": "video",
    "model": "kling-v3",
    "object": "task",
    "output": null,
    "poll_after_seconds": 8,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "stage": "queued",
    "status": "queued",
    "task_kind": "video",
    "updated_at": 1791993600,
    "usage": {
      "billable_duration_seconds": 5,
      "credits_charged": 0.65,
      "credits_refunded": 0,
      "credits_reserved": 0.65,
      "credits_settled": 0
    }
  }
}
```

**SDK Code**

```python 文生视频
import requests

url = "https://api.beatapi.io/v1/videos/tasks"

payload = {
    "model": "kling-v3",
    "prompt": "A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections",
    "aspect_ratio": "16:9",
    "duration": 5,
    "resolution": "pro",
    "sound": True
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.json())
```

```javascript 文生视频
const url = 'https://api.beatapi.io/v1/videos/tasks';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"kling-v3","prompt":"A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections","aspect_ratio":"16:9","duration":5,"resolution":"pro","sound":true}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go 文生视频
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.beatapi.io/v1/videos/tasks"

	payload := strings.NewReader("{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections\",\n  \"aspect_ratio\": \"16:9\",\n  \"duration\": 5,\n  \"resolution\": \"pro\",\n  \"sound\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby 文生视频
require 'uri'
require 'net/http'

url = URI("https://api.beatapi.io/v1/videos/tasks")

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 = "{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections\",\n  \"aspect_ratio\": \"16:9\",\n  \"duration\": 5,\n  \"resolution\": \"pro\",\n  \"sound\": true\n}"

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

```java 文生视频
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.beatapi.io/v1/videos/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections\",\n  \"aspect_ratio\": \"16:9\",\n  \"duration\": 5,\n  \"resolution\": \"pro\",\n  \"sound\": true\n}")
  .asString();
```

```php 文生视频
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.beatapi.io/v1/videos/tasks', [
  'body' => '{
  "model": "kling-v3",
  "prompt": "A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections",
  "aspect_ratio": "16:9",
  "duration": 5,
  "resolution": "pro",
  "sound": true
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp 文生视频
using RestSharp;

var client = new RestClient("https://api.beatapi.io/v1/videos/tasks");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections\",\n  \"aspect_ratio\": \"16:9\",\n  \"duration\": 5,\n  \"resolution\": \"pro\",\n  \"sound\": true\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift 文生视频
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "model": "kling-v3",
  "prompt": "A dramatic product reveal of a glass water bottle, slow orbiting camera, soft studio reflections",
  "aspect_ratio": "16:9",
  "duration": 5,
  "resolution": "pro",
  "sound": true
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.beatapi.io/v1/videos/tasks")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### 首帧

**Request**

```json
{
  "model": "kling-v3",
  "prompt": "The bottle slowly rotates on its pedestal while reflections move across the glass",
  "duration": 5,
  "images": [
    "https://media.beatapi.io/samples/smart-bottle.png"
  ],
  "resolution": "pro",
  "sound": true
}
```

**Response**

```json
{
  "data": {
    "capability_id": "kling-v3",
    "capability_version": 1,
    "completed_at": null,
    "created_at": 1791993600,
    "error_code": null,
    "error_message": null,
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "media_type": "video",
    "model": "kling-v3",
    "object": "task",
    "output": null,
    "poll_after_seconds": 8,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "stage": "queued",
    "status": "queued",
    "task_kind": "video",
    "updated_at": 1791993600
  }
}
```

**SDK Code**

```python 首帧
import requests

url = "https://api.beatapi.io/v1/videos/tasks"

payload = {
    "model": "kling-v3",
    "prompt": "The bottle slowly rotates on its pedestal while reflections move across the glass",
    "duration": 5,
    "images": ["https://media.beatapi.io/samples/smart-bottle.png"],
    "resolution": "pro",
    "sound": True
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.json())
```

```javascript 首帧
const url = 'https://api.beatapi.io/v1/videos/tasks';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"kling-v3","prompt":"The bottle slowly rotates on its pedestal while reflections move across the glass","duration":5,"images":["https://media.beatapi.io/samples/smart-bottle.png"],"resolution":"pro","sound":true}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go 首帧
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.beatapi.io/v1/videos/tasks"

	payload := strings.NewReader("{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"The bottle slowly rotates on its pedestal while reflections move across the glass\",\n  \"duration\": 5,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"resolution\": \"pro\",\n  \"sound\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby 首帧
require 'uri'
require 'net/http'

url = URI("https://api.beatapi.io/v1/videos/tasks")

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 = "{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"The bottle slowly rotates on its pedestal while reflections move across the glass\",\n  \"duration\": 5,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"resolution\": \"pro\",\n  \"sound\": true\n}"

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

```java 首帧
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.beatapi.io/v1/videos/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"The bottle slowly rotates on its pedestal while reflections move across the glass\",\n  \"duration\": 5,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"resolution\": \"pro\",\n  \"sound\": true\n}")
  .asString();
```

```php 首帧
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.beatapi.io/v1/videos/tasks', [
  'body' => '{
  "model": "kling-v3",
  "prompt": "The bottle slowly rotates on its pedestal while reflections move across the glass",
  "duration": 5,
  "images": [
    "https://media.beatapi.io/samples/smart-bottle.png"
  ],
  "resolution": "pro",
  "sound": true
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp 首帧
using RestSharp;

var client = new RestClient("https://api.beatapi.io/v1/videos/tasks");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"The bottle slowly rotates on its pedestal while reflections move across the glass\",\n  \"duration\": 5,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"resolution\": \"pro\",\n  \"sound\": true\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift 首帧
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "model": "kling-v3",
  "prompt": "The bottle slowly rotates on its pedestal while reflections move across the glass",
  "duration": 5,
  "images": ["https://media.beatapi.io/samples/smart-bottle.png"],
  "resolution": "pro",
  "sound": true
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.beatapi.io/v1/videos/tasks")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### 首帧和尾帧

**Request**

```json
{
  "model": "kling-v3",
  "prompt": "The camera moves from the bottle on the table to the singer on a neon stage in one continuous shot",
  "duration": 5,
  "images": [
    "https://media.beatapi.io/samples/smart-bottle.png",
    "https://media.beatapi.io/samples/neon-singer.png"
  ],
  "resolution": "std"
}
```

**Response**

```json
{
  "data": {
    "capability_id": "kling-v3",
    "capability_version": 1,
    "completed_at": null,
    "created_at": 1791993600,
    "error_code": null,
    "error_message": null,
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "media_type": "video",
    "model": "kling-v3",
    "object": "task",
    "output": null,
    "poll_after_seconds": 8,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "stage": "queued",
    "status": "queued",
    "task_kind": "video",
    "updated_at": 1791993600
  }
}
```

**SDK Code**

```python 首帧和尾帧
import requests

url = "https://api.beatapi.io/v1/videos/tasks"

payload = {
    "model": "kling-v3",
    "prompt": "The camera moves from the bottle on the table to the singer on a neon stage in one continuous shot",
    "duration": 5,
    "images": ["https://media.beatapi.io/samples/smart-bottle.png", "https://media.beatapi.io/samples/neon-singer.png"],
    "resolution": "std"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.json())
```

```javascript 首帧和尾帧
const url = 'https://api.beatapi.io/v1/videos/tasks';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"kling-v3","prompt":"The camera moves from the bottle on the table to the singer on a neon stage in one continuous shot","duration":5,"images":["https://media.beatapi.io/samples/smart-bottle.png","https://media.beatapi.io/samples/neon-singer.png"],"resolution":"std"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go 首帧和尾帧
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.beatapi.io/v1/videos/tasks"

	payload := strings.NewReader("{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"The camera moves from the bottle on the table to the singer on a neon stage in one continuous shot\",\n  \"duration\": 5,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\",\n    \"https://media.beatapi.io/samples/neon-singer.png\"\n  ],\n  \"resolution\": \"std\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby 首帧和尾帧
require 'uri'
require 'net/http'

url = URI("https://api.beatapi.io/v1/videos/tasks")

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 = "{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"The camera moves from the bottle on the table to the singer on a neon stage in one continuous shot\",\n  \"duration\": 5,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\",\n    \"https://media.beatapi.io/samples/neon-singer.png\"\n  ],\n  \"resolution\": \"std\"\n}"

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

```java 首帧和尾帧
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.beatapi.io/v1/videos/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"The camera moves from the bottle on the table to the singer on a neon stage in one continuous shot\",\n  \"duration\": 5,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\",\n    \"https://media.beatapi.io/samples/neon-singer.png\"\n  ],\n  \"resolution\": \"std\"\n}")
  .asString();
```

```php 首帧和尾帧
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.beatapi.io/v1/videos/tasks', [
  'body' => '{
  "model": "kling-v3",
  "prompt": "The camera moves from the bottle on the table to the singer on a neon stage in one continuous shot",
  "duration": 5,
  "images": [
    "https://media.beatapi.io/samples/smart-bottle.png",
    "https://media.beatapi.io/samples/neon-singer.png"
  ],
  "resolution": "std"
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp 首帧和尾帧
using RestSharp;

var client = new RestClient("https://api.beatapi.io/v1/videos/tasks");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"The camera moves from the bottle on the table to the singer on a neon stage in one continuous shot\",\n  \"duration\": 5,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\",\n    \"https://media.beatapi.io/samples/neon-singer.png\"\n  ],\n  \"resolution\": \"std\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift 首帧和尾帧
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "model": "kling-v3",
  "prompt": "The camera moves from the bottle on the table to the singer on a neon stage in one continuous shot",
  "duration": 5,
  "images": ["https://media.beatapi.io/samples/smart-bottle.png", "https://media.beatapi.io/samples/neon-singer.png"],
  "resolution": "std"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.beatapi.io/v1/videos/tasks")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### 多镜头

**Request**

```json
{
  "model": "kling-v3",
  "prompt": "A two-shot cinematic product reveal",
  "aspect_ratio": "16:9",
  "duration": 6,
  "images": [
    "https://media.beatapi.io/samples/smart-bottle.png"
  ],
  "multi_prompt": [
    {
      "duration": 3,
      "prompt": "Macro detail shot of the bottle with moving reflections"
    },
    {
      "duration": 3,
      "prompt": "Wide hero reveal of the bottle on a dark pedestal"
    }
  ],
  "multi_shots": true,
  "resolution": "pro",
  "sound": true
}
```

**Response**

```json
{
  "data": {
    "capability_id": "kling-v3",
    "capability_version": 1,
    "completed_at": null,
    "created_at": 1791993600,
    "error_code": null,
    "error_message": null,
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "media_type": "video",
    "model": "kling-v3",
    "object": "task",
    "output": null,
    "poll_after_seconds": 8,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "stage": "queued",
    "status": "queued",
    "task_kind": "video",
    "updated_at": 1791993600
  }
}
```

**SDK Code**

```python 多镜头
import requests

url = "https://api.beatapi.io/v1/videos/tasks"

payload = {
    "model": "kling-v3",
    "prompt": "A two-shot cinematic product reveal",
    "aspect_ratio": "16:9",
    "duration": 6,
    "images": ["https://media.beatapi.io/samples/smart-bottle.png"],
    "multi_prompt": [
        {
            "duration": 3,
            "prompt": "Macro detail shot of the bottle with moving reflections"
        },
        {
            "duration": 3,
            "prompt": "Wide hero reveal of the bottle on a dark pedestal"
        }
    ],
    "multi_shots": True,
    "resolution": "pro",
    "sound": True
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.json())
```

```javascript 多镜头
const url = 'https://api.beatapi.io/v1/videos/tasks';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"kling-v3","prompt":"A two-shot cinematic product reveal","aspect_ratio":"16:9","duration":6,"images":["https://media.beatapi.io/samples/smart-bottle.png"],"multi_prompt":[{"duration":3,"prompt":"Macro detail shot of the bottle with moving reflections"},{"duration":3,"prompt":"Wide hero reveal of the bottle on a dark pedestal"}],"multi_shots":true,"resolution":"pro","sound":true}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go 多镜头
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.beatapi.io/v1/videos/tasks"

	payload := strings.NewReader("{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A two-shot cinematic product reveal\",\n  \"aspect_ratio\": \"16:9\",\n  \"duration\": 6,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"multi_prompt\": [\n    {\n      \"duration\": 3,\n      \"prompt\": \"Macro detail shot of the bottle with moving reflections\"\n    },\n    {\n      \"duration\": 3,\n      \"prompt\": \"Wide hero reveal of the bottle on a dark pedestal\"\n    }\n  ],\n  \"multi_shots\": true,\n  \"resolution\": \"pro\",\n  \"sound\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby 多镜头
require 'uri'
require 'net/http'

url = URI("https://api.beatapi.io/v1/videos/tasks")

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 = "{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A two-shot cinematic product reveal\",\n  \"aspect_ratio\": \"16:9\",\n  \"duration\": 6,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"multi_prompt\": [\n    {\n      \"duration\": 3,\n      \"prompt\": \"Macro detail shot of the bottle with moving reflections\"\n    },\n    {\n      \"duration\": 3,\n      \"prompt\": \"Wide hero reveal of the bottle on a dark pedestal\"\n    }\n  ],\n  \"multi_shots\": true,\n  \"resolution\": \"pro\",\n  \"sound\": true\n}"

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

```java 多镜头
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.beatapi.io/v1/videos/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A two-shot cinematic product reveal\",\n  \"aspect_ratio\": \"16:9\",\n  \"duration\": 6,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"multi_prompt\": [\n    {\n      \"duration\": 3,\n      \"prompt\": \"Macro detail shot of the bottle with moving reflections\"\n    },\n    {\n      \"duration\": 3,\n      \"prompt\": \"Wide hero reveal of the bottle on a dark pedestal\"\n    }\n  ],\n  \"multi_shots\": true,\n  \"resolution\": \"pro\",\n  \"sound\": true\n}")
  .asString();
```

```php 多镜头
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.beatapi.io/v1/videos/tasks', [
  'body' => '{
  "model": "kling-v3",
  "prompt": "A two-shot cinematic product reveal",
  "aspect_ratio": "16:9",
  "duration": 6,
  "images": [
    "https://media.beatapi.io/samples/smart-bottle.png"
  ],
  "multi_prompt": [
    {
      "duration": 3,
      "prompt": "Macro detail shot of the bottle with moving reflections"
    },
    {
      "duration": 3,
      "prompt": "Wide hero reveal of the bottle on a dark pedestal"
    }
  ],
  "multi_shots": true,
  "resolution": "pro",
  "sound": true
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp 多镜头
using RestSharp;

var client = new RestClient("https://api.beatapi.io/v1/videos/tasks");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A two-shot cinematic product reveal\",\n  \"aspect_ratio\": \"16:9\",\n  \"duration\": 6,\n  \"images\": [\n    \"https://media.beatapi.io/samples/smart-bottle.png\"\n  ],\n  \"multi_prompt\": [\n    {\n      \"duration\": 3,\n      \"prompt\": \"Macro detail shot of the bottle with moving reflections\"\n    },\n    {\n      \"duration\": 3,\n      \"prompt\": \"Wide hero reveal of the bottle on a dark pedestal\"\n    }\n  ],\n  \"multi_shots\": true,\n  \"resolution\": \"pro\",\n  \"sound\": true\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift 多镜头
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "model": "kling-v3",
  "prompt": "A two-shot cinematic product reveal",
  "aspect_ratio": "16:9",
  "duration": 6,
  "images": ["https://media.beatapi.io/samples/smart-bottle.png"],
  "multi_prompt": [
    [
      "duration": 3,
      "prompt": "Macro detail shot of the bottle with moving reflections"
    ],
    [
      "duration": 3,
      "prompt": "Wide hero reveal of the bottle on a dark pedestal"
    ]
  ],
  "multi_shots": true,
  "resolution": "pro",
  "sound": true
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.beatapi.io/v1/videos/tasks")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### 可复用的元素

**Request**

```json
{
  "model": "kling-v3",
  "prompt": "A slow cinematic camera orbit around the product",
  "duration": 5,
  "elements": [
    {
      "element_input_urls": [
        "https://media.beatapi.io/samples/smart-bottle.png",
        "https://media.beatapi.io/samples/neon-singer.png"
      ],
      "name": "product",
      "description": "The featured water bottle"
    }
  ],
  "resolution": "pro"
}
```

**Response**

```json
{
  "data": {
    "capability_id": "kling-v3",
    "capability_version": 1,
    "completed_at": null,
    "created_at": 1791993600,
    "error_code": null,
    "error_message": null,
    "id": "task_7Qm2Xc9LpR4vT8sKa1Nf6YbH3eWdJ0uZ",
    "media_type": "video",
    "model": "kling-v3",
    "object": "task",
    "output": null,
    "poll_after_seconds": 8,
    "request_id": "req_5f0c2a9e4b7d4e31",
    "stage": "queued",
    "status": "queued",
    "task_kind": "video",
    "updated_at": 1791993600
  }
}
```

**SDK Code**

```python 可复用的元素
import requests

url = "https://api.beatapi.io/v1/videos/tasks"

payload = {
    "model": "kling-v3",
    "prompt": "A slow cinematic camera orbit around the product",
    "duration": 5,
    "elements": [
        {
            "element_input_urls": ["https://media.beatapi.io/samples/smart-bottle.png", "https://media.beatapi.io/samples/neon-singer.png"],
            "name": "product",
            "description": "The featured water bottle"
        }
    ],
    "resolution": "pro"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.json())
```

```javascript 可复用的元素
const url = 'https://api.beatapi.io/v1/videos/tasks';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: '{"model":"kling-v3","prompt":"A slow cinematic camera orbit around the product","duration":5,"elements":[{"element_input_urls":["https://media.beatapi.io/samples/smart-bottle.png","https://media.beatapi.io/samples/neon-singer.png"],"name":"product","description":"The featured water bottle"}],"resolution":"pro"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go 可复用的元素
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.beatapi.io/v1/videos/tasks"

	payload := strings.NewReader("{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A slow cinematic camera orbit around the product\",\n  \"duration\": 5,\n  \"elements\": [\n    {\n      \"element_input_urls\": [\n        \"https://media.beatapi.io/samples/smart-bottle.png\",\n        \"https://media.beatapi.io/samples/neon-singer.png\"\n      ],\n      \"name\": \"product\",\n      \"description\": \"The featured water bottle\"\n    }\n  ],\n  \"resolution\": \"pro\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby 可复用的元素
require 'uri'
require 'net/http'

url = URI("https://api.beatapi.io/v1/videos/tasks")

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 = "{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A slow cinematic camera orbit around the product\",\n  \"duration\": 5,\n  \"elements\": [\n    {\n      \"element_input_urls\": [\n        \"https://media.beatapi.io/samples/smart-bottle.png\",\n        \"https://media.beatapi.io/samples/neon-singer.png\"\n      ],\n      \"name\": \"product\",\n      \"description\": \"The featured water bottle\"\n    }\n  ],\n  \"resolution\": \"pro\"\n}"

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

```java 可复用的元素
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.beatapi.io/v1/videos/tasks")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A slow cinematic camera orbit around the product\",\n  \"duration\": 5,\n  \"elements\": [\n    {\n      \"element_input_urls\": [\n        \"https://media.beatapi.io/samples/smart-bottle.png\",\n        \"https://media.beatapi.io/samples/neon-singer.png\"\n      ],\n      \"name\": \"product\",\n      \"description\": \"The featured water bottle\"\n    }\n  ],\n  \"resolution\": \"pro\"\n}")
  .asString();
```

```php 可复用的元素
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.beatapi.io/v1/videos/tasks', [
  'body' => '{
  "model": "kling-v3",
  "prompt": "A slow cinematic camera orbit around the product",
  "duration": 5,
  "elements": [
    {
      "element_input_urls": [
        "https://media.beatapi.io/samples/smart-bottle.png",
        "https://media.beatapi.io/samples/neon-singer.png"
      ],
      "name": "product",
      "description": "The featured water bottle"
    }
  ],
  "resolution": "pro"
}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp 可复用的元素
using RestSharp;

var client = new RestClient("https://api.beatapi.io/v1/videos/tasks");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"model\": \"kling-v3\",\n  \"prompt\": \"A slow cinematic camera orbit around the product\",\n  \"duration\": 5,\n  \"elements\": [\n    {\n      \"element_input_urls\": [\n        \"https://media.beatapi.io/samples/smart-bottle.png\",\n        \"https://media.beatapi.io/samples/neon-singer.png\"\n      ],\n      \"name\": \"product\",\n      \"description\": \"The featured water bottle\"\n    }\n  ],\n  \"resolution\": \"pro\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift 可复用的元素
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [
  "model": "kling-v3",
  "prompt": "A slow cinematic camera orbit around the product",
  "duration": 5,
  "elements": [
    [
      "element_input_urls": ["https://media.beatapi.io/samples/smart-bottle.png", "https://media.beatapi.io/samples/neon-singer.png"],
      "name": "product",
      "description": "The featured water bottle"
    ]
  ],
  "resolution": "pro"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.beatapi.io/v1/videos/tasks")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```