Kling 3.0 Omni is Kuaishou's unified Kling model, and the Kling 3.0 Omni API brings text to video, image to video, reference to video, and video editing together at one endpoint. Add up to seven reference images for consistent characters, restyle or edit an existing clip with a reference video, and co-generate native audio — then receive every generated video through async jobs and webhooks. The Kling 3.0 Omni API runs on Apiframe with no separate Kling AI account to manage.
Integrate Kling 3.0 Omni with a single API call — one key, one unified endpoint, and shared billing across every model on Apiframe.
model: "kling-3.0-omni" Kling 3.0 Omni collapses text to video, image to video, reference to video, and video editing into a single model. The Kling 3.0 Omni API picks the right mode from the inputs you send — a prompt alone, a start image, reference images, or a reference video — so one integration covers every kind of video generation behind a single Kling video model.
Attach up to seven reference images and address them positionally in the prompt as `<<<image_1>>>`, `<<<image_2>>>`, and so on. The Kling 3.0 Omni API carries each subject, product, or location into the generated video, so subject consistency and character consistency hold across shots — ideal for series, ads, and campaigns.
Send a short reference video with a `feature` type to transfer its style and camera language, or a `base` type to edit and restyle that clip directly. The Kling 3.0 Omni API turns an existing clip into new video content without a separate editor, keeping motion and continuity intact.
Kling 3.0 Omni co-generates synchronized sound with the video, so the Kling 3.0 Omni API delivers native audio: music, sound effects, and ambience in the same pass, with natural lip sync. Prefer the original track when editing? Keep the reference video’s sound instead.
Provide a multi-shot timeline of up to six shots, each with its own prompt and duration, and the Kling 3.0 Omni API returns an edited sequence from a single request. One call ships trailers, explainers, and social clips as a coherent multi shot narrative rather than a single take.
Choose Standard (720p), Pro (1080p), or native 4K per request to trade cost for fidelity. The Kling 3.0 Omni API renders high fidelity video with strong physics and cinematic camera movement, and per-second pricing keeps costs predictable across durations from 3 to 15 seconds.
Apiframe gives you API access to Kling 3.0 Omni behind one AI API and key, with no separate Kling AI account. The Kling 3.0 Omni API uses async jobs: send a request, get a task id, and poll or receive a webhook when the generated video is ready. The same AI API runs other Kling video models and dozens more.
A few outputs generated through the Kling 3.0 Omni API on Apiframe.
Reference to video: <<<image_1>>> gives a gentle head turn and blink in soft window light.
Image to video: animate <<<image_1>>> rotating on a pedestal, studio lighting, logo staying legible.
Multi shot timeline: a wide city street cutting to a close-up of a neon sign, continuous mood and clean cuts.
Text to video with native audio: a waterfall, flowing water and mist, birdsong ambience.
Send a single POST /v2/videos/generate request with your API key to
generate with Kling 3.0 Omni. The call returns a jobId you can poll or
receive via webhook.
curl -X POST https://api.apiframe.ai/v2/videos/generate \
-H "X-API-Key: afk_your_api_key_here" \
-H "Content-Type: application/json" \
-d '{
"prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
"model": "kling-3.0-omni",
"klingParams": {
"start_image": "https://example.com/input.jpg",
"mode": "pro",
"generate_audio": false,
"end_image": "https://example.com/input.jpg"
}
}'import requests
response = requests.post(
"https://api.apiframe.ai/v2/videos/generate",
headers={
"X-API-Key": "afk_your_api_key_here",
"Content-Type": "application/json",
},
json={
"prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
"model": "kling-3.0-omni",
"klingParams": {
"start_image": "https://example.com/input.jpg",
"mode": "pro",
"generate_audio": False,
"end_image": "https://example.com/input.jpg"
}
},
)
print(response.json()) # { "jobId": "...", "status": "QUEUED" }const response = await fetch("https://api.apiframe.ai/v2/videos/generate", {
method: "POST",
headers: {
"X-API-Key": "afk_your_api_key_here",
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
"model": "kling-3.0-omni",
"klingParams": {
"start_image": "https://example.com/input.jpg",
"mode": "pro",
"generate_audio": false,
"end_image": "https://example.com/input.jpg"
}
}),
});
const { jobId } = await response.json();
console.log(jobId);Generation is asynchronous. A successful submission returns 202 Accepted with a jobId. Poll GET /v2/jobs/{id} (or supply a webhook_url) until the status is COMPLETED; the result field then holds the output URL(s).
{
"jobId": "b2c3d4e5-f6a7-8901-bcde-f23456789012",
"status": "QUEUED"
}curl https://api.apiframe.ai/v2/jobs/JOB_ID \
-H "X-API-Key: afk_your_api_key_here"import requests, time
while True:
job = requests.get(
"https://api.apiframe.ai/v2/jobs/JOB_ID",
headers={"X-API-Key": "afk_your_api_key_here"},
).json()
if job["status"] in ("COMPLETED", "FAILED"):
break
time.sleep(2)
print(job["result"])let job;
do {
await new Promise((r) => setTimeout(r, 2000));
job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
headers: { "X-API-Key": "afk_your_api_key_here" },
}).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);Request parameters accepted by the Kling 3.0 Omni endpoint. Model-specific options are nested under the params object shown below.
| Parameter | Type | Required | Default | Allowed / range | Description |
|---|---|---|---|---|---|
| prompt | string | required | — | — | Text description of what to generate. |
| model | string | required | "kling-3.0-omni" | "kling-3.0-omni" | The model identifier for this endpoint. |
| klingParams.start_image | string (URL) | optional | — | — | Use a still as the first frame of the clip. |
| klingParams.mode | string | optional | "pro" | "standard", "pro", "4k" | Mode |
| klingParams.generate_audio | boolean | optional | false | — | Generate audio |
| klingParams.end_image | string (URL) | optional | — | — | Optional last frame to control the ending. |
| klingParams.reference_images | string[] (URLs) | optional | — | — | Up to 7 reference images (max 4 when a reference video is set). |
| klingParams.reference_video | string (URL) | optional | — | — | A 3–10s clip for style transfer or video editing. |
| klingParams.video_reference_type | string | optional | — | "feature", "base" | How the reference video is used. Required when a reference video is set. |
| klingParams.keep_original_sound | boolean | optional | false | — | Keep the reference video’s original audio track. |
| klingParams.negative_prompt | string | optional | — | — | Negative prompt |
Common questions about the Kling 3.0 Omni API.
Kling 3.0 Omni is Kuaishou's unified Kling video model. It handles text to video, image to video, reference to video, and video editing in one model, with native audio and multi shot storytelling. On Apiframe it runs behind one AI API and key, so you call it the way you call every other video generation model.
Kling 3.0 Omni is the unified variant: on top of Kling 3.0’s modes, audio, and multi-shot support, it adds reference images (up to seven), a reference video for style transfer or editing, and a keep-original-sound option. Pricing and the standard/pro/4K modes match Kling 3.0.
Pass up to seven image URLs in `reference_images` and refer to them in the prompt as `<<<image_1>>>`, `<<<image_2>>>`, and so on. The Kling 3.0 Omni API uses them to keep characters, products, and locations consistent in the generated video. When you also send a reference video, reference images are capped at four.
Yes. Send a reference video and set `video_reference_type` to `base` to edit or restyle that clip, or `feature` to transfer its style and camera language into a new generation. Audio generation is disabled when a reference video is present; use keep-original-sound to retain the source track.
Yes. Kling 3.0 Omni co-generates synchronized native audio — music, sound effects, and ambience — with natural lip sync, unless a reference video is supplied. Generate audio and reference video are mutually exclusive.
Duration runs from 3 to 15 seconds. Aspect ratios are 16:9, 9:16, and 1:1. Choose Standard (720p), Pro (1080p), or native 4K per request. Pricing is per second of output.
Pricing is per second and matches Kling 3.0: 29 credits/sec Standard, 39 Pro, and 72 at 4K, with audio adding to Standard (43) and Pro (58). The total is the per-second rate times the requested duration. See [Credit costs](/pricing).
Get an api key, store it in an environment variable, and send a POST request to the Kling 3.0 Omni API with `model: "kling-3.0-omni"`. The request returns a task id; poll it or set a webhook to fetch the video url when the job completes.
Still have questions?
Get your API key and integrate Kling 3.0 Omni in minutes — Pay-as-you-go.
Questions? Join our Discord or contact sales.
