Kandinsky 6.0 Pro Text to Video API

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

Copy Page

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	kandinsky-6.0-pro/text-to-video
Capability	Text to video with synchronized audio
Resolution	480p (16:9 delivered at 864×480)
Length	Fixed 5 seconds

Turn a prompt into a 5-second 480p video with synchronized audio in five aspect ratios. Billed per video.

Production guidance

Calling tips

• Write one clause each for subject, action, camera and sound; keep a 5-second shot to one idea.
• Use 16:9 for landscape placements, 9:16 for vertical feeds, and 1:1 or 4:3 / 3:4 for square and portrait crops.
• Switch to kandinsky-6.0-pro/image-to-video when the subject must stay locked to a first frame.
• Use callback.url for completion or failure notifications; result URLs expire, so copy clips to your own storage.

Best suited for

Ad and product openers

One prompt covers camera move, material and sound for a ready-to-edit 5-second opener.

promptaspect_ratio

Vertical social clips

9:16 output ready for short-video feeds and brand placements.

aspect_ratio

Storyboards and previz

Check pacing and framing quickly across frames and camera descriptions.

promptseed

Request parameters

</> Generate example code

model string required

Model ID.

example kandinsky-6.0-pro/text-to-video

input object required

Text-to-video parameters.

prompt string required

Describe the subject, action, camera and sound. Up to 6,000 characters; English or Russian works best.

negative_prompt string optional

Content or artifacts to avoid, up to 2,000 characters.

aspect_ratio enum optional

Output frame: 16:9 landscape, 9:16 vertical, 1:1 square, 4:3 or 3:4.

default 16:9 enum: 16:99:161:14:33:4

seed integer optional

Random seed for reproducing a generation. Omit for a random seed.

guidance_scale number optional

How closely the result follows the prompt; a number from 1 to 10, default 5. Higher values follow the text more strictly.

default 5

callback object optional

Sends a notification when the task succeeds or fails; read the task object from data in query responses and directly from the callback body.

url string required

HTTPS URL that receives task success or failure notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Triggers when the task succeeds or fails.

default final enum: final

Input requirements

• prompt is required, up to 6,000 characters; negative_prompt is up to 2,000 characters.
• Length is fixed at 5 seconds and resolution at 480p; no duration, resolution, step-count or upscale parameter is exposed.
• aspect_ratio only accepts 16:9, 9:16, 1:1, 4:3 or 3:4; a 16:9 clip is delivered at 864×480.
• Video and synchronized audio are generated together; audio is always on. Output is a 24fps MP4.
• guidance_scale accepts numbers from 1 to 10; seed is an integer.

Example requests

Landscape night train

16:9, fixed 5 seconds at 480p with synchronized audio.

Request body⧉

{
  "model": "kandinsky-6.0-pro/text-to-video",
  "input": {
    "prompt": "A night train crosses a tall stone viaduct under a full moon, a plume of steam trailing into the valley, the camera cranes up from the river below, rhythmic wheels on the rails and a distant whistle",
    "aspect_ratio": "16:9"
  }
}

Vertical product shot

9:16 with a negative prompt to keep the frame clean.

Request body⧉

{
  "model": "kandinsky-6.0-pro/text-to-video",
  "input": {
    "prompt": "A ceramic pour-over coffee dripper on a dark counter, steam rising, camera slowly pushes in",
    "aspect_ratio": "9:16",
    "negative_prompt": "text, watermark, logo"
  }
}

Getting the result

1. Read data.taskId from the create-task response.
2. Wait for the callback or query GET /v1/tasks/:id; polling puts the task under data.
3. When status=success, read the video URL from output type=video; a callback reads output directly.

FAQ

How long are the videos and which resolutions are available?

Fixed at 5 seconds and 480p. Duration, resolution, step count and upscaling are not exposed, and the price is fixed for this tier.

Can I turn the audio off?

No. Synchronized audio is always generated together with the picture.

Does it support vertical video?

Yes. Set aspect_ratio to 9:16; 1:1, 4:3 and 3:4 are also available.

What are the actual output dimensions?

A 16:9 request is delivered at 864×480, 24fps, in an MP4 container.

Which prompt languages work best?

English and Russian are natively supported. Translate Chinese prompts into English for more reliable results.

Can I reproduce a result?

Pass the same seed and parameters to reproduce the same shot as closely as possible; small differences can remain between runs.

How is it billed?

Per video: each successful generation is charged one fixed tier price. See the pricing page for the current amount.

Do result links expire?

Yes. Download or copy clips to your own storage if you need to keep them.

Next steps

• Image to Video
• View live pricing