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

Creatify Boreal 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 name creatify-boreal
Type Video generation (text-to-video)
Endpoint POST /v1/tasks
Pricing See HiAPI Pricing

Creatify Boreal turns one prompt into product, UGC and presenter videos with native speech and sound, optionally guided by a reference image or audio, 1–20 seconds at 720p, 1080p or 2K in 5 aspect ratios plus auto.

Production guidance

Production guidance
  • For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
  • GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
  • Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Product videos

Animate one product photo with camera and light movement plus a spoken line.

image_urlprompt
UGC and presenters

Write the lines in [SPEECH] and get a vertical clip of someone talking to camera.

promptaspect_ratio
Audio-driven explainers

Give a presenter image and narration audio; the presenter speaks along with it.

image_urlaudio_urlduration

Request parameters

model string required

Fixed value creatify-boreal.

example creatify-boreal
input object required

Business parameters. Put Creatify Boreal-specific configuration here.

prompt string required

Direction for visuals, spoken lines, sounds and on-screen text. Best results with [VISUAL], [SPEECH], [SOUNDS] and [TEXT] sections; English prompts are recommended.

image_url string optional

Optional http(s) URL of a reference image to animate. With aspect_ratio auto the video follows the image ratio; a named ratio centre-crops the image.

audio_url string optional

Optional http(s) URL of narration, dialogue or a soundtrack. The first duration seconds are kept in the output; shorter audio is padded with silence.

negative_prompt string optional

Content or artifacts to avoid.

default ""
resolution enum optional

Output tier: 720p, 1080p or 2k (2016 px long edge for 16:9 and 9:16; 1440p tier for 1:1, 4:3 and 3:4).

default 720p enum: 720p1080p2k
aspect_ratio enum optional

auto follows the reference image, or 16:9 without one.

default auto enum: auto16:99:161:14:33:4
duration integer optional

Video length in whole seconds, 1-20. Billing uses the requested duration.

default 10
manifest_disclosure boolean optional

Add a visible AI-generated label to the video.

default false
callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

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

Callback trigger timing. Use final.

default final enum: final

Example requests

Vertical UGC talking clip

Text-to-video at 8 seconds, 720p, 9:16.

Request body
{
  "model": "creatify-boreal",
  "input": {
    "prompt": "[VISUAL] Vertical selfie video: a young woman in a bright bedroom holds up a pastel lip balm. [SPEECH] \"Okay, this is the only lip balm that survived my winter.\" [SOUNDS] Natural room tone.",
    "resolution": "720p",
    "aspect_ratio": "9:16",
    "duration": 8
  }
}
Product photo to video

Image-to-video at 5 seconds, 1080p; the ratio follows the image.

Request body
{
  "model": "creatify-boreal",
  "input": {
    "prompt": "The sneaker slowly rotates on the concrete floor as soft studio light sweeps across it; a calm voice says: \"Built for the long run.\"",
    "image_url": "https://example.com/sneaker.png",
    "resolution": "1080p",
    "duration": 5
  }
}
Audio-driven presenter

Reference image plus narration audio at 12 seconds, 720p, 9:16.

Request body
{
  "model": "creatify-boreal",
  "input": {
    "prompt": "The presenter talks warmly to the camera, natural gestures, lip-synced to the narration.",
    "image_url": "https://example.com/presenter.png",
    "audio_url": "https://example.com/narration.mp3",
    "aspect_ratio": "9:16",
    "duration": 12
  }
}

Getting the result

  1. The response returns a taskId immediately without waiting for generation to finish.
  2. In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
  3. When status=success, download the generated video from output[].url.
  4. When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

Does the video include sound?

Yes. The model generates matching speech and sound; when you pass audio_url, your audio is used.

How should I write the prompt?

Use [VISUAL], [SPEECH], [SOUNDS] and [TEXT] sections for visuals, lines, sound and on-screen text. English prompts are recommended.

What if my audio is longer than the duration?

Only the first duration seconds are kept; set duration to at least the audio length to keep the full narration.

How is it billed?

By requested duration in seconds and resolution. See the live prices on the HiAPI pricing page. View pricing

Next steps