Kling AI Commands & Prompt Reference
24 commands & parameters · 3 categories · Source: Kling AI API Documentation
Kling's video API is built around typed content items rather than a flat parameter list: a request carries a contents array where each item declares its type - prompt, first_frame, last_frame, element, or (for Motion Control) an appearance image and a motion reference video. Output shape lives in a settings object (resolution, multi-shot, native audio), and operational concerns like callbacks and watermarks live in options. This page maps that structure from the official API documentation.
The task lifecycle has its own small vocabulary worth knowing: external_task_id lets you attach your own unique ID at creation, and queries filter by status (submitted, processing, succeeded, failed) or product_type, paging with a cursor that overrides the time window.
All Commands
Generation Input Parameters (8)
| Command / Syntax | What it does | Notes |
|---|---|---|
| contents | Reference input collection: prompts, images, Elements | Array of typed inputs forming the generation request. |
| "type": "prompt" | Prompt input identifier inside contents | Carries the text field with positive and negative descriptions. |
| "type": "first_frame" | First-frame image input identifier | Anchors the opening frame of the generated video. |
| "type": "last_frame" | Last-frame image input identifier | Anchors the closing frame of the generated video. |
| "type": "element" | Element input identifier | References a reusable Element in the generation. |
| "type": "image" | Appearance reference image (Motion Control) | Generated characters follow the reference image; proportions should match the motion video. |
| "type": "video" | Motion reference video identifier (Motion Control) | Drives character motion from a reference clip. |
| text | Prompt text content, positive and negative descriptions | String field inside a prompt-type content item; can add elements and motion effects. |
Output Settings Parameters (4)
| Command / Syntax | What it does | Notes |
|---|---|---|
| settings | Output configuration object: resolution, duration, and related fields | Container for generation output parameters. |
| multi_shot | Whether to generate multi-shot video | Boolean; when false, multi-shot prompts will not produce multi-shot output. |
| audio | Audio generation switch for the video | Values: native (audio matching the visuals) or off (silent). |
| resolution | Resolution of the generated video | Set inside the settings object. |
Task & Query Parameters (12)
| Command / Syntax | What it does | Notes |
|---|---|---|
| options | General configuration: callback address, watermark, and similar | Container object alongside contents and settings. |
| callback_url | Callback URL for task result notifications | Server sends a notification on task status change; see the Callback Protocol. |
| external_task_id | Custom task ID, unique within the account | Does not overwrite the system task ID; usable for status queries. |
| watermark_info | Whether to also generate a watermarked result | Object with an enabled boolean. |
| task_ids | System task IDs to query, as a request path parameter | Choose either task_ids or external_task_ids per query, not both. |
| external_task_ids | Custom task IDs to query, as a request path parameter | Alternative to task_ids for status queries. |
| start_time | Start of the task-creation filter window | Unix timestamp in milliseconds; defaults to end_time minus 30 days. |
| end_time | End of the task-creation filter window | Unix timestamp in milliseconds; defaults to now. |
| cursor | Continuation cursor for paged task queries | Use next_cursor from the previous query; when set, start_time and end_time are ignored. |
| filters | Task query filter criteria | Key/value entries; key status or product_type. |
| "key": "status" | Filter tasks by status | Values: submitted, processing, succeeded, failed. |
| "key": "product_type" | Filter tasks by function type | Values: video, image, try_on. |
Frequently Asked Questions
How do I pass a prompt to Kling?
As a typed content item: add {type: prompt, text: ...} to the contents array. The text can carry both positive and negative descriptions.
How do I control audio in generated video?
Set audio in the settings object: native generates audio matching the visuals, off produces a silent video.
How do I check on a generation task?
Query by the system task_ids or your own external_task_ids (one method per query), filtering by status or product_type and paging with cursor.
Every entry on this page is a literal, typeable token taken from the official documentation linked above. Command sets in AI tools change quickly - the in-product command menu is always authoritative for your installed version.
Prompting Kling
Kling's strength is longer clips with coherent physics, and the parameters in the table control duration, mode (standard versus professional), aspect ratio, camera movement presets and negative prompts. Write the subject and action in plain language, name the camera move if you want one, and put unwanted elements — text, watermarks, extra limbs — in the negative prompt rather than the main one. Professional mode costs more credits and is worth it for the final render, not for exploration.
Image start and end frames
Providing a start frame anchors the first second and an end frame guides where the clip arrives, which is the tool for transitions and product turntables. Motion brush paints the regions that should move. Seeds and the same prompt reproduce a clip closely but not exactly; keep prompts and settings in a note so a good result can be revisited. The parameters here follow Kling's current web app and API documentation.