kling-v3 & kling-v3-omni

Create Task

POST /kling/v1/videos/text2videoGenerate video from text with model_name: "kling-3.0". Multi-shot storyboards, camera movement, sound, and voice references are supported.

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-3.0",
    "prompt": "A rabbit wearing glasses reads a newspaper at a table",
    "duration": "5",
    "mode": "pro",
    "sound": "on",
    "aspect_ratio": "1:1"
  }'

Create response

200

{
  "id": "860260753860210752",
  "task_id": "860260753860210752",
  "object": "video",
  "model": "kling-v3",
  "status": "",
  "progress": 0,
  "created_at": 1773130665
}

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 parameters

string

required

Use kling-3.0.

string

Positive prompt, up to 2,500 characters; required for a single shot or intelligent storyboard.

string

Negative prompt, up to 2,500 characters.

boolean

default:false

Enable multi-shot generation.

string

With multi-shot, use customize or intelligence.

object[]

One to six custom shots whose durations add up to duration.

object[]

Up to two voice references.

string

default:"off"

Use on or off; voice references require on.

string

default:"std"

std for 720p, pro for 1080p, or 4k.

string

default:"5"

Video duration from 3 to 15 seconds.

string

default:"16:9"

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

number

Prompt adherence from 0 to 1.

object

Preset or custom camera movement.

object

Platform watermark configuration through enabled.

Storyboards, voices, and camera movement

When multi_shot is true, set shot_type to customize and supply multi_prompt, or use intelligence with prompt. Each custom shot contains index, prompt, and duration; each shot lasts at least 1 second and its prompt is at most 512 characters.Voice references use <<<voice_1>>> and <<<voice_2>>> in list order. Supply at most two voice_id values from voice management and set sound to on.camera_control.type supports simple, down_back, forward_up, right_turn_forward, and left_turn_forward. For simple, only one of horizontal, vertical, pan, tilt, roll, and zoom may be nonzero; every value ranges from -10 to 10.

Interactive request parameters

Fill in and test the full Legacy request body.

Query Task

Single task: GET /kling/v1/videos/text2video/{task_id}. Status progresses from submitted or processing to succeed or failed.
Task list: GET /kling/v1/videos/text2video?pageNum=1&pageSize=30. pageNum is 1–1000 and pageSize is 1–500.

Create Task

POST /kling/v1/videos/image2videoGenerate video from a first frame, an end frame, or both with model_name: "kling-3.0".

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-3.0",
    "image": "https://example.com/first-frame.png",
    "prompt": "The character turns and walks toward the window",
    "duration": "5",
    "mode": "pro",
    "sound": "off"
  }'

200

{"id":"860260753860210752","task_id":"860260753860210752","object":"video","model":"kling-v3","status":"","progress":0,"created_at":1773130665}

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 parameters

string

required

Use kling-3.0.

string

First frame as URL or raw Base64; at least one frame is required.

string

End frame; mutually exclusive with motion brush and camera control.

string

Positive prompt, up to 2,500 characters.

string

Negative prompt, up to 2,500 characters.

boolean

default:false

Enable multi-shot generation.

string

Use customize or intelligence.

object[]

One to six custom shots.

object[]

Up to three elements; mutually exclusive with voice_list.

object[]

Up to two voices; requires sound: "on".

string

Static motion-brush mask.

object[]

Up to six dynamic masks.

object

Preset or simple camera movement.

string

default:"std"

Use std, pro, or 4k.

string

default:"5"

Video duration from 3 to 15 seconds.

number

Prompt adherence from 0 to 1.

object

Platform watermark setting.

integer

required

Shot index, starting from 1.

string

required

Shot prompt, up to 512 characters.

string

required

Shot duration, at least 1 second; the sum must equal top-level duration.

integer

required

Element ID returned by element management.

string

required

Voice ID returned by voice management.

string

required

Dynamic mask URL or raw Base64.

object[]

required

Motion trajectory coordinates.

integer

required

Horizontal coordinate from the bottom-left origin.

integer

required

Vertical coordinate from the bottom-left origin.

string

required

simple or one of four preset compound movements.

object

Simple movement configuration; only one of six values may be nonzero.

boolean

default:false

Add the platform watermark.

Create response

string

AnyFast task ID.

string

Task ID, equal to id.

string

Always video.

string

Model used by the task.

string

Initial task status.

integer

Initial progress.

integer

Creation Unix timestamp.

Image, storyboard, and motion-brush rules

image and image_tail accept a public URL or raw Base64 without a data URI prefix. Use JPG, JPEG, or PNG up to 10 MB, at least 300 px per side, with an aspect ratio from 1:2.5 to 2.5:1. At least one frame is required. An end frame, motion brush, and camera control are mutually exclusive.Dynamic motion brush supports up to 6 masks. Mask dimensions must match the input image and each other. For a 5-second video, each trajectory contains 2–77 coordinates measured from the bottom-left corner.Multi-shot, voice, and camera-control rules are the same as text-to-video. element_list and voice_list cannot be used together.

Interactive request parameters

Fill in and test every first/end-frame, storyboard, brush, element, voice, and camera field.

Query Task

Query by task ID

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

string

required

Task ID returned by creation.

The response includes AnyFast status fields and the original Kling task_status, task_status_msg, timestamps, and task_result.videos[]. A successful video contains id, url, watermark_url, and duration.

Query task list

GET /kling/v1/videos/image2video?pageNum=1&pageSize=30

integer

default:1

Page number, 1–1000.

integer

default:30

Items per page, 1–500.

Create Task

POST /kling/v1/videos/omni-videoUse model_name: "kling-3.0-omni" with text, images, video, and elements for generation or editing.

cURL

curl --request POST \
  --url https://www.anyfast.ai/kling/v1/videos/omni-video \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "model_name": "kling-3.0-omni",
    "prompt": "The character in <<<image_1>>> walks into a rainy neon street",
    "image_list": [{"image_url": "https://example.com/character.png"}],
    "duration": "5",
    "mode": "pro",
    "aspect_ratio": "16:9"
  }'

200

{"id":"860260753860210752","task_id":"860260753860210752","object":"video","model":"kling-v3-omni","status":"","progress":0,"created_at":1773130665}

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 parameters

string

required

Use kling-3.0-omni.

string

Up to 2,500 characters; reference media with the official placeholders.

object[]

Reference images and optional first/end frames.

At most one reference video, including refer_type and keep_original_sound.

object[]

Element count depends on whether a video is supplied.

boolean

default:false

Enable multi-shot generation.

string

Use customize or intelligence.

object[]

One to six custom shots.

string

default:"pro"

Use std, pro, or 4k.

string

Use 16:9, 9:16, or 1:1 when applicable.

string

default:"5"

3–15 seconds; ignored for refer_type: "base".

string

default:"off"

Must be off when video_list is present.

object

Platform watermark setting.

string

required

Reference image URL or raw Base64.

string

first_frame or end_frame; an end frame requires a first frame.

Reference video URL.

base edits the source video; feature references its characteristics.

Use yes or no.

integer

required

Element ID from element management.

integer

required

Shot index.

string

required

Shot prompt, up to 512 characters.

string

required

Shot duration, at least 1 second.

boolean

default:false

Add the platform watermark.

Create response

string

AnyFast task ID.

string

Task ID, equal to id.

string

Always video.

string

kling-v3-omni.

string

Initial task status.

integer

Initial progress.

integer

Creation Unix timestamp.

Media constraints

Images accept URL or raw Base64, JPG/JPEG/PNG, up to 10 MB, at least 300 px per side, and aspect ratio 1:2.5 to 2.5:1. An end frame requires a first frame. Without a reference video, images plus multi-image elements total at most 7 and video-character elements at most 3. With a reference video, those limits become 4 and 1.Reference video accepts MP4/MOV, 3–15.5 seconds, up to 200 MB, 24–60 fps, dimensions 700–4553 px, no more than 8,294,400 pixels, and aspect ratio 1:2.5 to 2.5:1.refer_type: "base" edits the original video, preserves its duration, and disables multi-shot and first/end-frame controls. refer_type: "feature" references content, motion, style, or camera movement and can use intelligent multi-shot. keep_original_sound controls source audio; new sound generation is unavailable whenever a reference video is present.

Interactive request parameters

Fill in and test the complete Omni Legacy request body.

Query Task

Query by task ID

GET /kling/v1/videos/omni-video/{task_id}

string

required

Task ID returned by creation.

The result includes the AnyFast wrapper and original Kling task_status, task_status_msg, task_result.videos[], and timestamps.

Query task list

GET /kling/v1/videos/omni-video?pageNum=1&pageSize=30

integer

default:1

Page number, 1–1000.

integer

default:30

Items per page, 1–500.

Create Task

POST /kling/v1/videos/motion-controlTransfer movement from a reference video to a character image with model_name: "kling-3.0".

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-3.0",
    "image_url": "https://example.com/character.png",
    "video_url": "https://example.com/motion.mp4",
    "prompt": "The character performs the reference action in a studio",
    "keep_original_sound": "yes",
    "character_orientation": "image",
    "mode": "pro"
  }'

200

{"id":"860260753860210752","task_id":"860260753860210752","object":"video","model":"kling-v3","status":"","progress":0,"created_at":1773130665}

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 parameters

string

required

Use kling-3.0.

string

required

Character image as URL or raw Base64.

string

required

Motion reference video URL.

string

Scene, motion, or camera guidance, up to 2,500 characters.

object[]

At most one element.

string

default:"yes"

Use yes or no.

string

required

Use image or video.

string

required

Use std or pro.

object

Platform watermark setting.

integer

required

Element ID from element management; at most one.

boolean

default:false

Add the platform watermark.

Create response

string

AnyFast task ID.

string

Task ID, equal to id.

string

Always video.

string

kling-v3.

string

Initial task status.

integer

Initial progress.

integer

Creation Unix timestamp.

The character image must be JPG/JPEG/PNG up to 10 MB, dimensions 300–65,536 px, and aspect ratio 1:2.5 to 2.5:1. The MP4/MOV motion video can be up to 100 MB with dimensions 340–3850 px. With character_orientation: "image", the video may be 3–10 seconds; with video, it may be 3–30 seconds. Element references follow the video’s orientation.

Complex or fast motion can produce a result shorter than the uploaded video because the model only extracts valid continuous action segments. Generation can proceed once at least 3 seconds of usable continuous motion is found. Credits consumed in this case are non-refundable, so reduce the motion complexity or speed when necessary.

Interactive request parameters

Fill in and test the complete motion-control request body.

Query Task

Query by task ID

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

string

required

Task ID returned by creation.

The response status and task_result.videos[] match the other Kling Legacy video operations.

Query task list

GET /kling/v1/videos/motion-control?pageNum=1&pageSize=30

integer

default:1

Page number, 1–1000.

integer

default:30

Items per page, 1–500.

Element APIs

Operation	Method and path
Create custom element	`POST /kling/v1/general/custom-elements`
List custom elements	`GET /kling/v1/general/custom-elements`
List preset elements	`GET /kling/v1/general/presets-elements`

Create a custom element

cURL

curl --request POST \
  --url https://www.anyfast.ai/kling/v1/general/custom-elements \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
    "element_name": "my-character",
    "element_description": "The lead character",
    "element_frontal_image": "https://example.com/front.png",
    "element_refer_list": [
      {"image_url": "https://example.com/side.png"},
      {"image_url": "https://example.com/close-up.png"}
    ],
    "tag_list": [{"tag_id": "o_102"}]
  }'

200

{
  "code": 0,
  "message": "string",
  "request_id": "string",
  "data": {
    "element_id": 0,
    "element_name": "string",
    "element_description": "string",
    "element_frontal_image": "image_url_0",
    "element_refer_list": [{"image_url": "image_url_1"}],
    "tag_list": [{"id": "o_102", "name": "Character", "description": "string"}],
    "owned_by": "string"
  }
}

Request headers

string

required

Bearer authentication in the form Bearer YOUR_API_KEY.

string

default:"application/json"

required

Use application/json.

Request body

string

required

Element name, up to 20 characters.

string

required

Element description, up to 100 characters.

string

required

Front-view image as an accessible URL or raw Base64 without a data URI prefix.

object[]

required

One to three alternate-angle reference images.

string

required

Reference image URL or raw Base64 without a data URI prefix.

Element tags.

o_101 trend, o_102 character, o_103 animal, o_104 item, o_105 costume, o_106 scene, o_107 effect, or o_108 other.

Images support JPG, JPEG, and PNG, up to 10 MB each. Both dimensions must be at least 300 px and the aspect ratio must be between 1:2.5 and 2.5:1.

Create response

integer

Error code; 0 indicates success.

string

Error information or success message.

string

System-generated request ID for tracking and troubleshooting.

integer

Element ID used by supported video APIs.

string

Element name.

string

Element description.

string

Front-view reference image URL.

object[]

Alternate-angle reference images.

string

Reference image URL.

Element tags.

Tag ID.

Tag name.

Tag description.

string

Element owner; kling identifies an official preset.

List custom elements

GET /kling/v1/general/custom-elements?pageNum=1&pageSize=30

integer

default:1

Page number from 1 to 1,000.

integer

default:30

Items per page from 1 to 500.

The response contains code, message, request_id, and data[]. Each item contains all element fields from the create response plus final_unit_deduction, the final units deducted for creation.

200

{
  "code": 0,
  "message": "string",
  "request_id": "string",
  "data": [{
    "element_id": 0,
    "element_name": "string",
    "element_description": "string",
    "element_frontal_image": "image_url_0",
    "element_refer_list": [{"image_url": "image_url_1"}],
    "tag_list": [{"id": "o_102", "name": "Character", "description": "string"}],
    "final_unit_deduction": "string",
    "owned_by": "string"
  }]
}

List preset elements

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

integer

default:1

Page number from 1 to 1,000.

integer

default:30

Items per page from 1 to 500.

The response matches the custom list without final_unit_deduction. Official preset elements have owned_by: "kling".

This page strictly documents the Kling Legacy element API.

Voice APIs

Operation	Method and path
Create custom voice	`POST /kling/v1/general/custom-voices`
Query custom voice	`GET /kling/v1/general/custom-voices/{id}`
List custom voices	`GET /kling/v1/general/custom-voices`
List preset voices	`GET /kling/v1/general/presets-voices`
Delete custom voice	`POST /kling/v1/general/delete-voices`

Create and query

voice_name is at most 20 characters. Supply at least one of voice_url or video_id. A voice URL may point to MP3, WAV, MP4, or MOV containing one clean speaker for 5–30 seconds. A qualifying historical generated video can be supplied through video_id under the same audio constraints.

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"
  }'

200

{"code":0,"message":"SUCCEED","request_id":"request-id","data":{"task_id":"850087542757535834","task_status":"submitted"}}

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 parameters

string

required

Custom voice name, up to 20 characters.

string

Public MP3, WAV, MP4, or MOV URL; at least one source is required.

string

Eligible historical generated-video ID; at least one source is required.

Create response

integer

0 indicates success.

string

Response message.

string

Request ID.

string

Voice creation task ID.

string

submitted, processing, succeed, or failed.

string

Failure reason.

object[]

Created voices.

Query custom voice

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

string

required

Task ID returned by voice creation.

Successful voice items contain voice_id, voice_name, trial_url, and owned_by.

List custom voices

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

integer

default:1

Page number, 1–1000.

integer

default:30

Items per page, 1–1000.

List preset voices

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

integer

default:1

Page number, 1–1000.

integer

default:30

Items per page, 1–1000.

Preset voices have owned_by: "kling" and cannot be deleted.

Delete custom voice

POST /kling/v1/general/delete-voices

string

required

Custom voice ID to delete.

The response contains code, message, request_id, and deletion task data.

Voice Management APIs

Open the interactive reference for each voice operation.

​Create Task

​Create response

​Request headers

​Request parameters

​Storyboards, voices, and camera movement

Interactive request parameters

​Query Task

​Create Task

​Request headers

​Request parameters

​Create response

​Image, storyboard, and motion-brush rules

Interactive request parameters

​Query Task

​Query by task ID

​Query task list

​Create Task

​Request headers

​Request parameters

​Create response

​Media constraints

Interactive request parameters

​Query Task

​Query by task ID

​Query task list

​Create Task

​Request headers

​Request parameters

​Create response

Interactive request parameters

​Query Task

​Query by task ID

​Query task list

​Element APIs

​Create a custom element

​Request headers

​Request body

​Create response

​List custom elements

​List preset elements

​Voice APIs

​Create and query

​Request headers

​Request parameters

​Create response

​Query custom voice

​List custom voices

​List preset voices

​Delete custom voice

Voice Management APIs

Create Task

Create response

Request headers

Request parameters

Storyboards, voices, and camera movement

Query Task

Create Task

Request headers

Request parameters

Create response

Image, storyboard, and motion-brush rules

Query Task

Query by task ID

Query task list

Create Task

Request headers

Request parameters

Create response

Media constraints

Query Task

Query by task ID

Query task list

Create Task

Request headers

Request parameters

Create response

Query Task

Query by task ID

Query task list

Element APIs

Create a custom element

Request headers

Request body

Create response

List custom elements

List preset elements

Voice APIs

Create and query

Request headers

Request parameters

Create response

Query custom voice

List custom voices

List preset voices

Delete custom voice