kling-v2-6

This page groups Kling 2.6 creation, query, and management operations by capability. Each request and response example is aligned with its related fields.

Text to video
Image to video
Motion control
Voice management

Create task

POST /kling/v1/videos/text2video

cURL

curl --request POST \
  --url https://www.anyfast.ai/kling/v1/videos/text2video \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model_name": "kling-2.6",
    "prompt": "A corgi runs along a beach at sunset as waves cross the sand",
    "negative_prompt": "blurry, shaky",
    "duration": "5",
    "mode": "pro",
    "sound": "on",
    "aspect_ratio": "16:9",
    "watermark_info": {"enabled": false}
  }'

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Data exchange format. Use application/json.

Request body

string

required

Must be kling-2.6.

string

required

Positive prompt, up to 2,500 characters.

string

Content to avoid, up to 2,500 characters.

object[]

Up to two voices. Each item contains a voice_id returned by Voice management. Reference them as <<<voice_1>>> and <<<voice_2>>> in list order, and set sound to on.

string

default:"off"

on or off. Must be on when voice_list is used.

string

default:"std"

std for 720p or pro for 1080p.

string

default:"5"

Fixed duration: 5 or 10 seconds.

string

default:"16:9"

16:9, 9:16, or 1:1.

object

Preset or custom camera movement.

object

Use enabled to request an additional watermarked result.

Camera control

camera_control.type supports simple, down_back, forward_up, right_turn_forward, and left_turn_forward. In simple mode, set one nonzero property in config: horizontal, vertical, pan, tilt, roll, or zoom. Each property ranges from -10 to 10.

Create response

200

{
  "id": "860260753860210752",
  "task_id": "860260753860210752",
  "object": "video",
  "model": "kling-v2-6",
  "status": "queued",
  "progress": 0,
  "created_at": 1773130665
}

string

AnyFast task ID.

string

Task ID, equal to id.

string

Object type, always video.

string

Public model ID used for the task.

string

Initial status, always queued.

integer

Initial progress, always 0.

integer

Creation time as a Unix timestamp in seconds.

Query task by ID

GET /kling/v1/videos/text2video/{task_id}

cURL

curl --request GET \
  --url https://www.anyfast.ai/kling/v1/videos/text2video/TASK_ID \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json'

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Data exchange format. Use application/json.

Path parameters

string

required

The text-to-video task ID returned by the create endpoint.

Task result

200

{
  "code": 0,
  "message": "",
  "data": {
    "task_id": "asyntask_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "task_status": "succeed",
    "task_result": {
      "videos": [
        {"url": "https://example.com/result.mp4", "duration": "5"}
      ]
    },
    "created_at": 1784720890000,
    "updated_at": 1784720949000
  }
}

integer

0 indicates that the query succeeded.

string

Error information; empty for a successful query.

string

Queried task ID.

string

submitted, processing, succeed, or failed.

string

Failure details when the task fails.

object[]

Generated videos, returned after success.

string

Temporary generated-video URL.

string

Actual duration in seconds.

integer

Creation Unix timestamp in milliseconds.

integer

Last update Unix timestamp in milliseconds.

Generated result URLs are removed after 30 days. Save the files promptly.

Create task

POST /kling/v1/videos/image2video

cURL

curl --request POST \
  --url https://www.anyfast.ai/kling/v1/videos/image2video \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model_name": "kling-2.6",
    "image": "https://example.com/first-frame.png",
    "image_tail": "https://example.com/end-frame.png",
    "prompt": "The camera slowly pulls back as the person smiles",
    "duration": "5",
    "mode": "pro",
    "sound": "off"
  }'

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Data exchange format. Use application/json.

Request body

string

required

Must be kling-2.6.

string

Start-frame URL or raw Base64. At least one of image and image_tail is required.

string

End frame. It cannot be combined with dynamic_masks, static_mask, or camera_control.

string

Positive prompt, up to 2,500 characters.

string

Negative prompt, up to 2,500 characters.

object[]

Up to two items containing voice_id; set sound to on when used.

string

default:"off"

on or off.

string

default:"std"

std for 720p or pro for 1080p.

string

default:"5"

5 or 10 seconds.

string

Static motion mask as a URL or raw Base64.

object[]

Up to six dynamic motion-brush masks.

string

required

A dynamic-area mask matching the input image dimensions.

object[]

required

Trajectory coordinates. A 5-second video accepts 2–77 points.

integer

required

X coordinate, using the image bottom-left corner as the origin.

integer

required

Y coordinate, using the image bottom-left corner as the origin.

object

Preset or custom camera movement.

object

Use enabled to request an additional watermarked result.

Image requirements

Use a public URL or raw Base64 without a data URI prefix. JPG, JPEG, and PNG are supported. Files must be no larger than 10 MB, both sides at least 300 px, and the aspect ratio between 1:2.5 and 2.5:1. End-frame control, motion brush, and camera control cannot be used together.

Create response

200

{
  "id": "860260753860210752",
  "task_id": "860260753860210752",
  "object": "video",
  "model": "kling-v2-6",
  "status": "queued",
  "progress": 0,
  "created_at": 1773130665
}

string

AnyFast task ID.

string

Task ID, equal to id.

string

Object type, always video.

string

Public model ID used for the task.

string

Initial status, always queued.

integer

Initial progress, always 0.

integer

Creation time as a Unix timestamp in seconds.

Query task by ID

GET /kling/v1/videos/image2video/{task_id}

cURL

curl --request GET \
  --url https://www.anyfast.ai/kling/v1/videos/image2video/TASK_ID \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json'

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Data exchange format. Use application/json.

Path parameters

string

required

The image-to-video task ID returned by the create endpoint.

Task result

200

{
  "code": 0,
  "message": "",
  "data": {
    "task_id": "asyntask_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "task_status": "succeed",
    "task_result": {
      "videos": [
        {"url": "https://example.com/result.mp4", "duration": "5"}
      ]
    },
    "created_at": 1784720890000,
    "updated_at": 1784720949000
  }
}

integer

0 indicates that the query succeeded.

string

Error information; empty for a successful query.

string

Queried task ID.

string

submitted, processing, succeed, or failed.

string

Failure details when the task fails.

object[]

Generated videos, returned after success.

string

Temporary generated-video URL.

string

Actual duration in seconds.

integer

Creation Unix timestamp in milliseconds.

integer

Last update Unix timestamp in milliseconds.

Generated result URLs are removed after 30 days. Save the files promptly.

Create task

POST /kling/v1/videos/motion-control

cURL

curl --request POST \
  --url https://www.anyfast.ai/kling/v1/videos/motion-control \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model_name": "kling-2.6",
    "image_url": "https://example.com/character.png",
    "video_url": "https://example.com/motion.mp4",
    "prompt": "Preserve the character and reproduce the reference motion",
    "character_orientation": "video",
    "keep_original_sound": "yes",
    "mode": "pro"
  }'

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Data exchange format. Use application/json.

Request body

string

required

Must be kling-2.6.

string

Additional visual or camera instructions, up to 2,500 characters.

string

required

Character image URL or raw Base64.

string

required

Public URL for the motion reference video.

object[]

Up to one Legacy element. When used, character_orientation must be video.

string

required

Element ID returned by the Legacy Element Management API.

string

default:"yes"

Keep reference-video audio: yes or no.

string

required

Character orientation source: image or video.

string

default:"std"

std or pro.

object

Use enabled to request an additional watermarked result.

Media requirements

Images support JPG/JPEG/PNG up to 10 MB, 300–65,536 px per side, and aspect ratio 1:2.5 to 2.5:1. Videos support MP4/MOV up to 100 MB, 340–3,850 px per side, and at least 3 seconds. Maximum duration is 10 seconds for character_orientation: "image" and 30 seconds for character_orientation: "video".

Create response

200

{
  "code": 0,
  "message": "SUCCEED",
  "request_id": "request-id",
  "data": {"task_id": "task-id", "task_status": "submitted"}
}

integer

0 indicates that the request was accepted.

string

Response message.

string

Request tracing ID.

string

Motion-control task ID.

string

Initial task status.

Query task by ID

GET /kling/v1/videos/motion-control/{task_id}

cURL

curl --request GET \
  --url https://www.anyfast.ai/kling/v1/videos/motion-control/TASK_ID \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json'

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Data exchange format. Use application/json.

Path parameters

string

required

The motion-control task ID returned by the create endpoint.

Task result

200

{
  "code": 0,
  "message": "",
  "data": {
    "task_id": "asyntask_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
    "task_status": "succeed",
    "task_result": {
      "videos": [
        {"url": "https://example.com/result.mp4", "duration": "5"}
      ]
    },
    "created_at": 1784720890000,
    "updated_at": 1784720949000
  }
}

integer

0 indicates that the query succeeded.

string

Error information; empty for a successful query.

string

Queried task ID.

string

submitted, processing, succeed, or failed.

string

Failure details when the task fails.

object[]

Generated videos, returned after success.

string

Temporary generated-video URL.

string

Actual duration in seconds.

integer

Creation Unix timestamp in milliseconds.

integer

Last update Unix timestamp in milliseconds.

Generated result URLs are removed after 30 days. Save the files promptly.

Create custom voice

POST /kling/v1/general/custom-voices

cURL

curl --request POST \
  --url https://www.anyfast.ai/kling/v1/general/custom-voices \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "voice_name": "Narrator",
    "voice_url": "https://example.com/voice.mp3"
  }'

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Data exchange format. Use application/json.

Request body

string

required

Custom voice name, up to 20 characters.

string

Public MP3, WAV, MP4, or MOV URL. At least one of voice_url and video_id is required.

string

An eligible previously generated video ID. At least one of voice_url and video_id is required.

The source must contain one clear speaker and be 5–30 seconds long.

Create response

200

{
  "id": "860260753860210752",
  "task_id": "860260753860210752",
  "object": "video",
  "model": "kling-voices",
  "status": "queued",
  "progress": 0,
  "created_at": 1773130665
}

string

AnyFast task ID.

string

Task ID, equal to id.

string

Object type, always video.

string

Public model ID used for the task.

string

Initial status, always queued.

integer

Initial progress, always 0.

integer

Creation time as a Unix timestamp in seconds.

Query custom voice

GET /kling/v1/general/custom-voices/{id}

cURL

curl --request GET \
  --url https://www.anyfast.ai/kling/v1/general/custom-voices/VOICE_TASK_ID \
  --header 'Authorization: Bearer YOUR_API_KEY'

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

required

Task ID returned by the create custom voice endpoint.

Custom voice result

200

{
  "code": "0",
  "message": "",
  "requestId": "request-id",
  "data": {
    "task_id": "VOICE_TASK_ID",
    "task_status": "succeed",
    "task_result": {
      "voices": [{"voice_id": "voice-id", "voice_name": "Narrator", "trial_url": "https://example.com/trial.mp3", "owned_by": "self", "status": "succeed"}]
    }
  }
}

string

Business status code.

string

Response message.

string

Request tracing ID.

string

Voice task ID.

string

submitted, processing, succeed, or failed.

object[]

Voice results.

string

Voice ID for video requests.

string

Voice name.

string

Voice preview URL.

string

Custom voices return self; current preset voices return vod.

List preset voices

GET /kling/v1/general/presets-voices?pageNum=1&pageSize=30

cURL

curl --request GET \
  --url 'https://www.anyfast.ai/kling/v1/general/presets-voices?pageNum=1&pageSize=30' \
  --header 'Authorization: Bearer YOUR_API_KEY'

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

integer

default:1

Page number from 1 to 1,000.

integer

default:30

Page size from 1 to 1,000.

Preset voice result

200

{
  "code": "0",
  "message": "",
  "requestId": "request-id",
  "data": [
    {
      "task_id": "preset-task-id",
      "task_status": "succeed",
      "task_result": {
        "voices": [{"voice_id": "preset-voice-id", "voice_name": "Warm narrator", "trial_url": "https://example.com/preset.mp3", "owned_by": "vod", "status": "succeed"}]
      }
    }
  ]
}

string

Business status code.

string

Response message.

string

Request tracing ID.

string

Voice task ID.

string

submitted, processing, succeed, or failed.

object[]

Voice results.

string

Voice ID for video requests.

string

Voice name.

string

Voice preview URL.

string

Custom voices return self; current preset voices return vod.

This page uses the Kling Legacy request structure. AnyFast adds the /kling routing prefix to Legacy paths.

Overview

Native Compatible Endpoints

Model APIs

Create task

Request headers

Request body

Camera control

Create response

Query task by ID

Request headers

Path parameters

Task result

Create task

Request headers

Request body

Image requirements

Create response

Query task by ID

Request headers

Path parameters

Task result

Create task

Request headers

Request body

Media requirements

Create response

Query task by ID

Request headers

Path parameters

Task result

Create custom voice

Request headers

Request body

Create response

Query custom voice

Custom voice result

List preset voices

Preset voice result

​Create task

​Request headers

​Request body

​Camera control

​Create response

​Query task by ID

​Request headers

​Path parameters

​Task result

​Create task

​Request headers

​Request body

​Image requirements

​Create response

​Query task by ID

​Request headers

​Path parameters

​Task result

​Create task

​Request headers

​Request body

​Media requirements

​Create response

​Query task by ID

​Request headers

​Path parameters

​Task result

​Create custom voice

​Request headers

​Request body

​Create response

​Query custom voice

​Custom voice result

​List preset voices

​Preset voice result

Create task

Request headers

Request body

Camera control

Create response

Query task by ID

Request headers

Path parameters

Task result

Create task

Request headers

Request body

Image requirements

Create response

Query task by ID

Request headers

Path parameters

Task result

Create task

Request headers

Request body

Media requirements

Create response

Query task by ID

Request headers

Path parameters

Task result

Create custom voice

Request headers

Request body

Create response

Query custom voice

Custom voice result

List preset voices

Preset voice result