Digital Human Video

This document explains how to use Kling Avatar v2 async digital human video generationEndpoint.

Supported models:

Model name	Type	Suitable scenarios	Billing mode
kling-avatar-v2-standard	digital human video	standard narration, customer-service explanation, course introduction, marketing short video	billed by output video duration
kling-avatar-v2-pro	digital human video	higher-quality digital-human narration, formal promotional video, brand video, important course content	billed by output video duration

Endpoint async task mode:

Operation	Method	Path
submitdigital human videotask	POST	/v1/video/generations
querydigital human videotask	GET	/v1/video/generations/{task_id}

---

1. Authentication

Endpoint requires request headers API Key:

Authorization: Bearer sk-xxxxxxxxxxxxxxxx
Content-Type: application/json

Example:

https://api.xxx.xx

---

2. Model overview

Kling Avatar v2 imageandaudio generationdigital human video. userrequiresprovidesone imageandaaudio, Model generation and action video.

supports:

Model	Note
kling-avatar-v2-standard	standard, standard narrationand generation
kling-avatar-v2-pro	Pro, stable

---

3. submitdigital human videotask

POST https://api.xxx.xx/v1/video/generations

3.1 Request Parameters

Parameters	Type	Required	Note
model	string	Yes	kling-avatar-v2-standard or kling-avatar-v2-pro
image_url	string	Yes	image URL
audio_url	string	Yes	audio URL,
audio_duration_seconds	number	Yes	audioduration, submit billing
prompt	string	No	style, scenario, Status, camera

Note:

• audio_duration_seconds pass.
• Field submit, billing.
• pass inaudio duration, cost and task.

3.2 submitResponse Examples

{
  "id": "task_xxxxxxxxxxxxx",
  "task_id": "task_xxxxxxxxxxxxx",
  "object": "video.generation.job",
  "status": "queued"
}

Field Reference:

Field	Note
id/task_id	async task ID, query result
status	task status, value queued, processing, completed, failed

---

4. querydigital human videotask

GET https://api.xxx.xx/v1/video/generations/{task_id}

queryExample:

curl -X GET "https://api.xxx.xx/v1/video/generations/task_xxxxxxxxxxxxx" \
 -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxx"

Completed Response Example:

{
  "id": "task_xxxxxxxxxxxxx",
  "task_id": "task_xxxxxxxxxxxxx",
  "object": "video.generation.job",
  "status": "completed",
  "video_url": "https://api.xxx.xx/media/xxxxx.mp4",
  "result": {
    "outputs": [
      "https://api.xxx.xx/media/xxxxx.mp4"
    ]
  }
}

---

5. Request Examples

5.1 Standard generationcustomer-service explanationvideo

curl -X POST "https://api.xxx.xx/v1/video/generations" \
 -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxx" \
 -H "Content-Type: application/json" \
 -d '{"model": "kling-avatar-v2-standard",
 "image_url": "https://cdn.example.com/avatar/customer-service.png",
 "audio_url": "https://cdn.example.com/audio/customer-intro.mp3",
 "audio_duration_seconds": 12,
 "prompt": "friendly customer service presenter, natural expression, clean studio lighting"}'

5.2 Standard generationcourse introduction

curl -X POST "https://api.xxx.xx/v1/video/generations" \
 -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxx" \
 -H "Content-Type: application/json" \
 -d '{"model": "kling-avatar-v2-standard",
 "image_url": "https://cdn.example.com/avatar/teacher.png",
 "audio_url": "https://cdn.example.com/audio/course-opening.mp3",
 "audio_duration_seconds": 18.5,
 "prompt": "professional teacher, warm smile, stable camera, natural lip sync"}'

5.3 Pro generation video

curl -X POST "https://api.xxx.xx/v1/video/generations" \
 -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxx" \
 -H "Content-Type: application/json" \
 -d '{"model": "kling-avatar-v2-pro",
 "image_url": "https://cdn.example.com/avatar/brand-host.png",
 "audio_url": "https://cdn.example.com/audio/brand-message.mp3",
 "audio_duration_seconds": 24,
 "prompt": "premium corporate spokesperson video, clean studio background, confident expression"}'

5.4 Pro generationnews broadcast

curl -X POST "https://api.xxx.xx/v1/video/generations" \
 -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxx" \
 -H "Content-Type: application/json" \
 -d '{"model": "kling-avatar-v2-pro",
 "image_url": "https://cdn.example.com/avatar/news-anchor.png",
 "audio_url": "https://cdn.example.com/audio/news-briefing.mp3",
 "audio_duration_seconds": 32.7,
 "prompt": "news anchor style, formal tone, stable frontal shot, neutral expression"}'

---

6. Common Errors

6.1 image_url

digital human video provides image:

{
  "image_url": "https://cdn.example.com/avatar.png"
}

6.2 audio_url

digital human video provides audio:

{
  "audio_url": "https://cdn.example.com/voice.mp3"
}

6.3 audio_duration_seconds

Error:

{
  "model": "kling-avatar-v2-standard",
  "image_url": "https://cdn.example.com/avatar.png",
  "audio_url": "https://cdn.example.com/voice.mp3"
}

audioduration:

{
  "audio_duration_seconds": 12.5
}

---

7. recommended

1. image.
2. use TTS or generate aaudio.
3. audio duration.
4. submit /v1/video/generations, pass in image_url, audio_url, audio_duration_seconds.
5. poll /v1/video/generations/{task_id}.
6. task completed read video_url.

---

8. Minimum Valid Request

8.1 Avatar Standard

curl -X POST "https://api.xxx.xx/v1/video/generations" \
 -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxx" \
 -H "Content-Type: application/json" \
 -d '{"model": "kling-avatar-v2-standard",
 "image_url": "https://cdn.example.com/avatar.png",
 "audio_url": "https://cdn.example.com/voice.mp3",
 "audio_duration_seconds": 10}'

8.2 Avatar Pro

curl -X POST "https://api.xxx.xx/v1/video/generations" \
 -H "Authorization: Bearer sk-xxxxxxxxxxxxxxxx" \
 -H "Content-Type: application/json" \
 -d '{"model": "kling-avatar-v2-pro",
 "image_url": "https://cdn.example.com/avatar.png",
 "audio_url": "https://cdn.example.com/voice.mp3",
 "audio_duration_seconds": 10}'