Kwaivgi Kling Video O3 Std Video Edit
Playground
Try it on WavespeedAI!Kling Omni Video O3 Video-Edit (Standard) enables natural-language video edits: remove or replace objects, swap backgrounds, restyle scenes, change weather/lighting, and apply localized 3-10s transformations with strong temporal consistency. Built for stable production use with a ready-to-use REST API, no cold starts, and predictable pricing.
Features
Kling Omni Video O3 (Standard) — Video Edit
Kling Omni Video O3 is Kuaishou’s advanced unified multi-modal video model. The Video-Edit mode revolutionizes video editing through natural language — simply describe what you want to change, and the AI performs pixel-level semantic reconstruction.
Key Capabilities
Conversational Editing
Edit videos with simple text commands:
- “Remove the pedestrians from the background”
- “Change daytime to dusk”
- “Replace the character’s clothing with a red dress”
- “Add snow falling in the scene”
Comprehensive Modification
The model supports editing:
- Content — Add, remove, or modify objects and people
- Angles & Perspectives — Adjust camera viewpoints
- Backgrounds — Replace or modify scene environments
- Local Elements — Edit specific parts of the frame
- Styles & Colors — Apply artistic transformations
- Weather & Lighting — Change atmospheric conditions
Semantic Understanding
The MVL system interprets your intent and performs:
- Pixel-level semantic reconstruction
- Context-aware modifications
- Coherent multi-frame changes
- Natural blending of edits
Core Features
- Natural Language Control — Describe edits in plain text
- Object Removal — Clean removal without artifacts
- Style Transfer — Apply artistic and visual styles
- Scene Modification — Change environments and settings
- Element Replacement — Swap objects, clothing, and more
Pricing
| Duration (s) | Total Price ($) |
|---|---|
| 3 | 0.378 |
| 4 | 0.504 |
| 5 | 0.630 |
| 6 | 0.756 |
| 7 | 0.882 |
| 8 | 1.008 |
| 9 | 1.134 |
| 10 | 1.260 |
How to Use
-
Upload Your Video Provide the source video you want to edit (max 10 seconds).
-
Upload images (Optional) Including reference images of the element, scene, style, etc. Max 4 images
-
Describe Your Edit Write a natural language command for the modification.
Example: “Remove all cars from the street and change the time to golden hour”
-
Set Parameters Choose whether to keep original sound.
-
Generate Receive your edited video with seamless modifications.
Pro Tips
- Be specific about what to change and how
- Use clear spatial terms (“left side,” “background,” “foreground”)
- Combine multiple edits in one prompt when related
- For complex edits, break them into sequential steps
Example Commands
| Command | Effect |
|---|---|
| ”Remove the logo” | Cleans branded elements |
| ”Make it night time” | Adjusts lighting and atmosphere |
| ”Add rain effects” | Inserts weather elements |
| ”Change hair color to blonde” | Modifies character appearance |
| ”Replace background with beach” | Swaps environment |
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-video-o3-std/video-edit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"keep_original_sound": true
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| video | string | Yes | - | The video URL. Video duration can not be longer than 10s. | |
| images | array | No | [] | - | Including reference images of the element, scene, style, etc. Max 4 |
| keep_original_sound | boolean | No | true | - | Whether to keep the original sound from the video. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | Array of URLs to the generated content (empty when status is not completed). |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |