Kling 3.0 Omni video

Animate a still image you supply into a 720p video with native audio using Kling 3.0 Omni: the picture is the first frame, the prompt says what happens next. Clips run 3 to 15 seconds. Returns the URL of the generated MP4. That URL is temporary: Goro holds a run’s results for 24 hours and nothing guarantees the file outlives that, so collect what you need within 24 hours.

Use when you have the exact frame the video must start from (a product shot, a character, a location) and want it brought to life with sound: an ad still that needs motion, a portrait that should turn and speak, a mockup that should be handled. Better at keeping the starting image intact than the cheaper models. To send a local or private image, upload it first (POST /v1/uploads, or create_upload over MCP, or goro run —image) and pass the handle as image_handle. Billed per second of video you ask for.

Price

$0.18 per second of video. An exact rate, not an estimate. The total is that rate times the seconds of video in your request, so you can work out what a call costs before you make it. No call costs less than

0.0020 or more than

2.70, the price of the largest request this endpoint takes, 15 seconds of video. discover and inspect quote your exact request before it runs.

Input

Field	Type	Required	Notes
`audio`	`true`		Fixed on. Native audio is part of what this endpoint quotes; a silent video would be a different price. Defaults to `true`.
`prompt`	`string`	yes	How the image should move. Describe the action, the camera move and any dialogue or sound; Kling generates matching audio.
`duration`	`integer`		Length of the generated video in seconds. This is what you are billed on, and it is the only field that changes the price. Defaults to `5`.
`image_urls`	`array`		One public http or https link to the starting image (JPEG, PNG or WEBP, up to 10 MB). Use this when the image is ALREADY published somewhere; the output URL of an image endpoint works directly. For a file that is not already public, send image_handle instead and it never has to be published anywhere. Exactly one of image_handle, image_urls and image_base64 is required.
`resolution`	`720p`		Fixed at 720p. Resolution changes the price per second, and this endpoint quotes one exact rate, so 1080p and 4k would get their own endpoints. Defaults to `"720p"`.
`image_base64`	`string`		Only for a SMALL image (under 3 MB) or a caller that cannot run a shell command. The image inline, as base64 of the file’s own bytes; a data:image/png;base64, prefix is accepted and its declared type ignored. Understand the cost before choosing it: this string is part of the request, and on an MCP call the request IS the tool arguments, which pass through the model’s context window. A 3 MB photograph is 4 MB of base64, on the order of a million tokens, and in practice it is truncated and the run fails looking like file corruption. Do not downscale an image to fit here: use image_handle, which takes up to 10 MB and keeps the file out of the conversation entirely. JPEG, PNG or WEBP. Exactly one of image_handle, image_urls and image_base64 is required.
`image_handle`	`string`		The RIGHT WAY to send a local or private image. Upload the file first with POST /v1/uploads (or the create_upload MCP tool, or the CLI’s —image flag, which does the whole thing for you) and put the short handle it returns here. The file goes straight from you to a private bucket: it never passes through a tool call, so it never passes through a model’s context window, and up to 10 MB is fine. Nothing is published. The handle is usable for 10 minutes after the upload lands and the file is deleted 30 minutes after that. JPEG, PNG or WEBP. Exactly one of image_handle, image_urls and image_base64 is required.

These are all the fields this endpoint accepts. Anything else is rejected as a validation_error rather than forwarded to the provider.

Example

curl -X POST https://api.usegoro.ai/v1/run \
  -H "Authorization: Bearer $GORO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"slug":"video.kling","input":{"prompt":"The woman turns to the window and smiles as the curtain lifts in a breeze."}}'

Response

The full response. Values are illustrative.

[
  "https://example.com/goro/generated-video-1.mp4"
]

Guide

CLI reference

API reference

Tools

Kling 3.0 Omni video

Price

Input

Example

Response

​Price

​Input

​Example

​Response

Price

Input

Example

Response