跳转到内容

Kling AI Avatar 2.0 Pro

集成

模型 id kling-video/ai-avatar/v2/pro
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/kling-video/ai-avatar/v2/pro?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

与示例类似的文件: $1.15 1,150 API 积分 运行前会测量你的文件 在此页面运行

获取 API 密钥

在 Doitong 上制作

Doitong 社区使用 Kling Avatar 制作的公开作品。一键复用提示词。

显示的公开作品:2
A realistic young Caucasian-looking woman wearing a modest hijab is walking through a modern city... 视频

A realistic young Caucasian-looking woman wearing a modest hijab is walking through a modern city street. She is speaking naturally (audio will be added separately) and expressing admiration and pr...

A realistic young Caucasian-looking woman in a modest hijab is walking calmly through the modern ... 视频

A realistic young Caucasian-looking woman in a modest hijab is walking calmly through the modern city of Grozny. The architecture around her is clean, modern, and impressive, with Dubai-style build...

构建请求

控件根据模型架构生成。更改控件时,代码和价格会同步更新。

默认 .

生成视频时使用的提示词。

•必填 image_url
拖放文件,或

指向用作头像的图像的 URL。

•必填 audio_url
拖放文件,或

指向音频文件的 URL。

POST /run/kling-video/ai-avatar/v2/pro?wait=20 报价 → $1.15
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/kling-video/ai-avatar/v2/pro?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

运行此请求

你的密钥会保留在此浏览器中:仅发送到 Doitong API;只有勾选“记住”后才会保存到 localStorage。 获取 API 密钥

关于 Kling AI Avatar 2.0 Pro

Kling AI Avatar 将人物或角色的单张照片制作成动画,使其根据给定音频说话,并匹配 嘴形、表情和头部动作;可选的提示词用于控制情绪和手势。片段时长与 音频相同。

参数

发送规范名称或原生名称之一,不要同时发送两者。 规范名称

名称类型 默认值允许值 描述
image_url必填 image
类型url · image
指向用作头像的图像的 URL。
audio_url必填 audio
类型url · audio
指向音频文件的 URL。
prompt可选
类型string
默认值.
生成视频时使用的提示词。
必填 规范名称,也可接受

文件参数接受公开的 https:// URL、最大 10 MB 的 data: URI,或上传文件的 file_url。 文件

输出

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "kling-video/ai-avatar/v2/pro",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 1150,
    "usd": "1.15",
    "charged": 1150,
    "refunded": 0
  },
  "input": {
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "duration": 5
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
你的文件,由你选择每个 outputs[].url 都是存储中的副本:可永久保存(按 GB-月付费),也可免费保存 7 天,由账户设置或 ?storage= 决定。
每个模型的结构相同图像、视频和音频均包含 type、url、content_type、width、height 和 duration。output 是模型自身的结果对象。
输出字段
video
object {url, content_type, file_name, file_size}模型生成的视频。
duration
number输出视频时长,以秒为单位。

更多模型:唇形同步与数字人

对于 AI 代理:此页面的 Markdown 版本位于 https://doitong.com/zh/developers/models/kling-video/ai-avatar/v2/pro.md. 所有模型和指南: https://doitong.com/developers/llms.txt