Skip to content
HiAPI Docs
HiAPI
Playground Get API Key
English
English 中文

Kling 4.0 Text to Video API

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model kling-4.0/text-to-video
Type Video generation (text to video)
Endpoint POST /v1/tasks
Price See HiAPI pricing

Kling 4.0 text-to-video API by Kuaishou Kling. Turn a prompt into a 3–30 second cinematic clip with synchronized audio generated in the same pass, at 720p or 1080p in 16:9, 9:16, 1:1 or 21:9.

Production guidance

Production notes
  • Send callback.url in the request body in production so HiAPI notifies your service when the task reaches a terminal state instead of polling on a timer.
  • 1080p and long clips queue noticeably longer; set client timeouts to at least 30 minutes.
  • Keep callback.when at final for now. Both success and fail can trigger the terminal notification, so handlers must be idempotent per taskId.

Best suited for

Clips with sound

Picture and synchronized audio are generated together, so ambience, engines or instruments written into the prompt arrive with the shot.

prompt
Single continuous takes

Any whole duration from 3 to 30 seconds, suited to one-take product demos, atmosphere shots and narrative openers.

duration
Multi-platform framing

16:9, 9:16, 1:1 and 21:9 ultrawide cover feed ads, vertical social video and widescreen in one prompt.

aspect_ratio
High-resolution output

Validate composition at 720p, then ship at 1080p. Per-second billing with no minimum keeps short tests cheap.

resolutionduration

Request parameters

model string required

Always kling-4.0/text-to-video.

example kling-4.0/text-to-video
input object required

Business parameters. All Kling 4.0 text-to-video options live here.

prompt string required

What the shot shows: subject, action and camera movement, up to 2500 characters. Put the ambience and sound sources you want in this same description.

resolution enum optional

Output resolution. Higher resolution costs more per second and renders noticeably slower.

default 720p enum: 720p1080p
duration integer optional

Clip length in seconds, any whole number from 3 to 30. Billed per output second with no minimum.

default 5
aspect_ratio enum optional

Framing of the output. 21:9 gives an ultrawide cinematic frame.

default 16:9 enum: 16:99:161:121:9
callback object optional

Optional callback. When set, HiAPI notifies your service as soon as the task reaches a terminal state, so you can poll less.

url string required

Required when callback is present: the HTTPS endpoint that receives the terminal-state notification.

example https://your-domain.com/hiapi/callback
when enum optional

When to fire the callback. Keep it at final for now.

default final enum: final

Example requests

Steam train at dawn

720p / 16:9 / 5s, testing layered steam, low golden light and engine sound.

Request body
{
  "model": "kling-4.0/text-to-video",
  "input": {
    "prompt": "An old steam train pulls slowly out of a mountain station at dawn, thick white steam billowing into low golden sunlight, pine forest on both sides, slow lateral tracking shot, cinematic depth of field, natural engine rumble and distant birdsong",
    "resolution": "720p",
    "duration": 5,
    "aspect_ratio": "16:9"
  }
}
Rooftop violinist at night

1080p / 16:9 / 5s, checking rain highlights, neon bokeh and the instrument sound.

Request body
{
  "model": "kling-4.0/text-to-video",
  "input": {
    "prompt": "A lone violinist plays on a rain-soaked rooftop at blue hour, neon signs blurring behind her, rain droplets catching rim light, slow push-in, shallow depth of field, cinematic",
    "resolution": "1080p",
    "duration": 5,
    "aspect_ratio": "16:9"
  }
}
Vertical short ad

720p / 9:16 / 8s for vertical placements at a lower cost.

Request body
{
  "model": "kling-4.0/text-to-video",
  "input": {
    "prompt": "Vertical close-up of iced coffee pouring into a glass on a sunlit counter, condensation sliding down the glass, camera locked off, soft cafe ambience",
    "resolution": "720p",
    "duration": 8,
    "aspect_ratio": "9:16"
  }
}

Getting the result

  1. The create call returns a taskId immediately; generation continues in the background.
  2. In production, wait for the callback.url notification. For local debugging, poll GET /v1/tasks/:id.
  3. When status is success, download the video from output[].url.
  4. When status is fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

Which resolutions and durations does Kling 4.0 text-to-video support?

720p and 1080p, with any whole duration from 3 to 30 seconds (5s by default). Billing is per output second and per resolution tier, with no minimum charge. See the pricing page for live prices.

Does the output include audio?

Yes. Audio is produced in the same pass as the picture and the MP4 ships with a soundtrack. There is no separate audio switch: describe the ambience and sound sources you want in the prompt.

How do I retrieve the finished video?

The create call returns a taskId immediately. Once the task reaches a terminal state, download the video from output[].url. In production send callback.url so HiAPI pushes the terminal state instead of you polling.

Does it support image-to-video?

This model is text-only. Use kling-4.0/image-to-video when a specific first frame has to start the clip.

Next steps