Skip to main content
POST
Kling V3 Text-to-Video

Authorizations

Authorization
string
header
required

All APIs require Bearer Token authentication

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json
model
string
default:kling-v3-text-to-video
required

kling-v3-text-to-video: Pure text driven video generation, supports 720p / 1080p / 4k

Example:

"kling-v3-text-to-video"

prompt
string
required

Text prompt describing the video content you want to generate

Notes:

  • Maximum 2500 characters
  • Supports both Chinese and English
Maximum string length: 2500
Example:

"An ancient Japanese courtyard, raindrops slowly falling into a pond, creating ripples"

resolution
string
default:720p

Output resolution

Options:

  • 720p — 720P SD
  • 1080p — 1080P HD
  • 4k — Native 4K UHD (independent tier, billing not affected by generate_audio / voice_ids)
Example:

"720p"

generate_audio
boolean
default:false

Whether to generate accompanying audio

Notes:

  • When enabled, the video will include AI-generated sound effects/music
  • Disabled by default
Example:

false

negative_prompt
string
default:""

Negative prompt, describing elements you don't want to appear

Notes:

  • Separate multiple keywords with commas
  • Common: blurry, low quality, watermark, text overlay

Do not pass this parameter unless necessary.

Example:

"blurry, low quality, watermark, text overlay"

aspect_ratio
string
default:16:9

Output video aspect ratio

Available values:

  • 16:9 — Landscape (default)
  • 9:16 — Portrait
  • 1:1 — Square
Example:

"16:9"

duration
integer
default:5

Output video duration (seconds)

Available values:

  • 5 — 5-second short video (default)
  • 10 — 10-second video
Example:

5

voice_ids
string[] | null

Voice ID list for voice control

Notes:

  • Maximum 2 voices
  • Use <<<voice_1>>> / <<<voice_2>>> in prompt to reference
  • Obtain voice_id via the kling-video-create-voice endpoint
  • generate_audio must be true when using this parameter

Do not pass this parameter unless necessary.

Example:
multi_prompt
object[] | null

Multi-prompt sequence

Notes:

  • Each segment contains its own prompt and duration
  • The sum of all segment durations should equal the total duration

Do not pass this parameter unless necessary.

Response

Task created successfully

created
integer

Task creation timestamp

Example:

1757165031

id
string

Task ID

Example:

"task-unified-1757165031-uyujaw3d"

model
string

Actual model name used

object
enum<string>

Specific task type

Available options:
video.generation.task
progress
integer

Task progress percentage (0-100)

Required range: 0 <= x <= 100
Example:

0

status
enum<string>

Task status

Available options:
pending,
processing,
completed,
failed
Example:

"pending"

task_info
object

Async task information

type
enum<string>

Task output type

Available options:
video
Example:

"video"