Gemini Omni 1.1 Flash
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 | gemini-omni-1.1-flash |
|---|---|
| Input modes | Text / reference images / frames / reference video |
| Duration | Without reference video: 4 / 6 / 8 / 10 seconds; with one: follows the reference clip |
| Resolution | 360p / 720p / 1080p / 4k |
Create video with ambient sound from text, reference images, frames or an existing clip for product showcases, social posts and storyboards. With a reference video, output length follows that clip.
Production guidance
Calling the API
- Check composition and motion at 360p or 720p before raising the resolution. With reference video, prepare a clip at your target length; duration, start and ends do not guarantee trimming the output.
- Read data.taskId after creating the task, then wait for the callback or poll GET /v1/tasks/:id; on success read output[].url and copy it into your own storage.
Best suited for
Text to video
A prompt alone produces a landscape or portrait clip with ambient sound.
promptaspect_ratioReference images
Guide appearance with product or character images, then describe the setting and motion in the prompt.
image_urlsFirst and last frames
Supply a first frame to guide the opening, with an optional last frame to guide the ending and the motion between them.
first_frame_urllast_frame_urlVideo to video
Use an existing clip as a composition and motion reference to explore a different palette, time of day or mood.
video_listRequest parameters
model string required Always gemini-omni-1.1-flash.
input object required Video generation parameters; choose an input approach for your material.
prompt string required Describe the picture, action, camera and sound in 1–20,000 characters. With reference media, say what to keep and what to change.
duration integer required Output length in seconds without a reference video. With video_list, length follows the reference clip; this field is still required but does not guarantee trimming.
image_urls string[] optional Reference images, 0–7, that the subject, scene or style should follow. Each up to 20MB; up to 5 when combined with video_list.
first_frame_url string optional An image used as the video's first frame. Cannot be combined with image_urls or video_list.
last_frame_url string optional An image used as the video's last frame; requires first_frame_url.
video_list object[] optional At most 1 reference clip to guide subject, composition and motion. The source can be up to 30 seconds and 100MB and uses 2 input slots. Output length follows the clip; upload one at your target length.
url string required Video URL.
start number optional Reference start time in seconds; does not guarantee trimming the output. Trim the source before uploading if you need a shorter clip.
ends number optional Reference end time in seconds; does not guarantee trimming the output. Upload a clip at your target length.
aspect_ratio enum optional Output aspect ratio: landscape 16:9 or portrait 9:16.
resolution enum optional Output video resolution.
seed integer optional Random seed from 0 to 2147483647 to adjust variation during generation.
callback object optional Notify your service when the task reaches a terminal status to reduce polling.
url string required HTTPS URL that receives terminal notifications.
when enum optional Notify when the task reaches a terminal status.
Example requests
Video to video
Restyle a lake-lantern clip as an indigo and amber night scene. Output length follows the reference clip.
Request body
{
"model": "gemini-omni-1.1-flash",
"input": {
"prompt": "Transform the reference video into a refined cinematic night sequence while preserving the lantern silhouette and smooth camera movement. Shift the palette from blue hour to deep indigo and warm amber, add slow drifting firefly-like reflections across the lake, keep the reflection physically coherent, one continuous shot, no people, no text, no logos, no watermark. Natural ambient sound: quiet water, soft glass resonance, and distant night wind.",
"duration": 8,
"video_list": [
{
"url": "https://static.hiapi.ai/admin-assets/gemini-omni-1-1-flash/2026/09/02/1788359834997-73681ce500c88b7c-gemini-omni-1-1-flash-golden.mp4",
"start": 0,
"ends": 8
}
],
"aspect_ratio": "16:9",
"resolution": "720p"
}
}Vertical text to video
Prompt only, producing a 4-second 9:16 vertical clip.
Request body
{
"model": "gemini-omni-1.1-flash",
"input": {
"prompt": "Vertical short-form video, one continuous handheld close-up: in a sunlit neighborhood cafe in the morning, a barista's hands pour steamed milk into a ceramic cup, a rosetta latte-art pattern blooms across the espresso, then the cup slides gently toward the camera on a wooden counter. Warm window light, shallow depth of field, soft steam, natural colors, no faces, no text, no logo, no watermark. Natural ambient sound: milk pouring, quiet cafe chatter, a cup set down on wood.",
"duration": 4,
"aspect_ratio": "9:16",
"resolution": "720p"
}
}Reference image to video
Send one product photo in image_urls so the same product appears in a new scene.
Request body
{
"model": "gemini-omni-1.1-flash",
"input": {
"prompt": "Use the celadon teapot from the reference image as the hero product. One continuous shot: the same teapot with its crackle glaze, bamboo handle and brass knob sits on a low walnut tea table beside a rain-streaked window on a quiet afternoon. Steam curls slowly from the spout while the camera makes a gentle half orbit from the front to the side, soft window light gliding across the glaze. Calm, tactile product film, no people, no text, no logo, no watermark. Natural ambient sound: soft rain on glass and a faint kettle hiss.",
"duration": 4,
"image_urls": [
"https://static.hiapi.ai/model-examples/gemini-omni-1.1-flash/v1/2026/10/07/1791363216388-f113bee8f81588f2-ref-teapot.png"
],
"aspect_ratio": "16:9",
"resolution": "720p"
}
}First and last frame
Use first and last frames that share framing and aspect ratio for a natural transition.
Request body
{
"model": "gemini-omni-1.1-flash",
"input": {
"prompt": "A smooth time-lapse in one continuous locked-off shot: in a quiet greenhouse, the closed pale pink peony bud slowly swells and unfurls into a full layered bloom while the cool misty dawn light warms into bright golden late-morning sun streaming through the glass. Leaves sway slightly, dust motes drift in the light. No people, no text, no logo, no watermark. Natural ambient sound: soft birdsong and a gentle greenhouse hum.",
"duration": 4,
"first_frame_url": "https://static.hiapi.ai/model-examples/gemini-omni-1.1-flash/v1/2026/10/07/1791363228597-ec8c296611a1d9be-first-frame-peony-bud.png",
"last_frame_url": "https://static.hiapi.ai/model-examples/gemini-omni-1.1-flash/v1/2026/10/07/1791363332896-44b2d8180fcab0d9-last-frame-peony-bloom.png",
"aspect_ratio": "16:9",
"resolution": "720p"
}
}Getting the result
- Read data.taskId from the create response.
- Wait for callback or poll GET /v1/tasks/:id.
- When status=success, read output[].url.
FAQ
How do I choose text, images, frames or video as input?
The media fields in input decide it: prompt only is text-to-video; image_urls is reference-image video; first_frame_url (optionally with last_frame_url) is frame-guided video; video_list is video-to-video.
How do I get my target length when reworking video?
Output length follows the reference video. Trim it to your target length before uploading; do not rely on duration, start or ends to trim the output. The source can be up to 30 seconds and 100MB; duration still requires 4, 6, 8 or 10.
Does the output include sound?
Yes, the output includes ambient sound. Describe the sound you want in the prompt.
Where can I check current costs?
See the live pricing page. The Playground shows an estimate for your settings before you submit. View live pricing