Creatify Boreal API: turn one prompt into product, UGC and presenter videos with native speech and sound, with optional image or audio input, up to 20s and 2K.
Provider: Creatify
Category: video generation
Status: In progress
Creatify Boreal API: turn one prompt into product, UGC and presenter videos with native speech and sound, with optional image or audio input, up to 20s and 2K.
Turn one prompt into product, UGC and presenter videos with native speech and sound, optionally guided by an image or audio, up to 20 seconds and 2K.
Use [VISUAL] for the shot and camera, [SPEECH] for the line, [SOUNDS] for effects and music and [TEXT] for on-screen text. English prompts give the steadiest results.
A reference image sets the subject and composition, and auto ratio follows it; driving audio is kept as-is in the video.
Choose 720p, 1080p or 2K and a whole-second length from 1 to 20, then download when the task finishes.
curl -X POST 'https://api.hiapi.ai/v1/tasks' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "creatify-boreal",
"input": {
"prompt": "[VISUAL] Macro shot of a chilled sparkling-water can on wet black stone, slow orbit. [SPEECH] None [SOUNDS] Fizzing and ice clinks. [TEXT] None",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration": 8
}
}'Text, reference-image and audio-driven generation across landscape, vertical and square frames.
Text to video · 16:9
One prompt sets the shot and the sound; fizz and ice clinks land on the matching frames.
Macro product shot of a chilled sparkling-water can on wet black stone, condensation droplets sliding down, slow orbit camera, fizzing and ice clinking sounds, crisp commercial lighting.
Text to video · 9:16
A vertical talking-to-camera clip for feeds, with natural room tone.
Vertical selfie-style UGC video: a young woman in a bright bedroom holds up a pastel lip balm and says to camera: "Okay, this is the only lip balm that survived my winter." Natural room tone.
Text to video · 1:1
A square frame for product pages and social cards.
Square lifestyle clip: hands arrange fresh flowers in a linen-wrapped bouquet on a wooden table, morning sunlight, gentle paper rustling and soft acoustic guitar.
Image to video
With auto ratio the video keeps the reference image's ratio and the product's look.
Soft light moves across the serum bottle as a drop falls from the gold dropper and ripples; a gentle voice says: "Calm skin, all day." Light airy ambience.
Image to video · presenter
The image supplies the presenter; [SPEECH] supplies the line.
The woman smiles and talks to the camera in her kitchen: "I swapped my coffee for this oat latte mix and honestly, I am not going back." Natural kitchen ambience.
Audio driven
The uploaded audio is kept in the video; the duration setting decides how much of it is used.
The presenter speaks the narration to the camera, friendly and relaxed, small hand gestures, cozy bookshop background.
VIDEO WITH NATIVE SOUND
Creatify Boreal: picture, line and sound in one prompt, delivered as one finished clip
Creatify Boreal is a video model built for ads and content: the shot, the spoken line, the sound and on-screen text live in one prompt, and the result arrives with audio, with no separate voice-over or mixing step.
It covers text-to-video, image-to-video and audio-driven generation for product showcases, UGC pitches and explainers. Output is 24fps MP4 with C2PA metadata and an invisible watermark, and a visible AI-generated label can be switched on.
[VISUAL], [SPEECH], [SOUNDS] and [TEXT] describe the shot, the line, the sound and on-screen text; write None for parts you do not need. Separate sections are easier for the model to follow than one mixed paragraph.
With a reference image, the subject's look, outfit and composition follow the image. Auto ratio keeps the image's ratio; a named ratio centre-crops it.
If you already have narration, dialogue or a soundtrack, upload it and the video keeps it; longer audio is trimmed to the duration and shorter audio is padded with silence.
Pick 9:16 and write the line in [SPEECH] to get a vertical talking-to-camera clip with ambient sound, ready for feeds and short-video platforms.
Auto, 16:9, 9:16, 1:1, 4:3 and 3:4 let one idea become a landscape ad, a vertical short and a square card.
Choose 720p, 1080p or 2K and any whole-second length from 1 to 20 to match each project.
The same prompt and 5 seconds at 720p and 1080p. Settle the shot and line at 720p, then render the final cut at a higher tier; 2K is available when you need more detail.
One product photo and a prompt produce showcase videos for product pages and ads at scale.
Vertical talking-to-camera clips with a natural feel for short-video feeds.
Drive a presenter with narration audio to turn out explainers quickly.
Picture, sound and on-screen text in one pass for launches and social posts.
Creatify Boreal generates picture, speech and sound from one prompt and also accepts a reference image and driving audio. If you only need a portrait photo to speak along with audio, you can also compare the photo-avatar and audio-driven portrait models on HiAPI.
Write a four-part prompt in the Playground above and get a video with sound in a few minutes.
A prompt is required; one reference image and one driving audio file are optional. Use the prompt alone or combine all three.
Use four sections: [VISUAL] for the shot and camera, [SPEECH] for the line, [SOUNDS] for effects and music and [TEXT] for on-screen text. Write None for sections you do not need.
English prompts give the steadiest results today; other languages are not guaranteed, so start in English.
1 to 20 whole seconds, 10 by default.
720p, 1080p and 2K, 720p by default. 2K is 2016 px on the long edge for 16:9 and 9:16 and the 1440p tier for 1:1, 4:3 and 3:4.
Choose auto, 16:9, 9:16, 1:1, 4:3 or 3:4. Auto follows the reference image, or 16:9 without one; a named ratio with a reference image centre-crops the image.
Upload narration, dialogue or a soundtrack and the video keeps it. Only the first duration seconds are used, and shorter audio is padded with silence.
It sets the subject's look, outfit and composition, so a product photo or portrait can become a video.
MP4 (H.264 video + AAC audio, 24fps) with generated speech and sound.
Every video carries C2PA metadata and an invisible watermark; turning on the AI label also adds a visible AI-generated mark.
By the requested duration and the chosen resolution; see the live price on this page. Failed tasks are refunded in full.
Submit a task to POST /v1/tasks with model creatify-boreal, then poll the task for the video URL. See the API docs for details.