Video

Kling 2.6 video

Kling 2.6 — text + image-to-video, optional end frame (forces sound off). 5s/10s.

Category: Create · kling-2-6

How to use & limits

Text-to-video and image-to-video (image_urls, max 1) with synchronized native audio.
sound is required; with end_image_url, sound is forced off.
prompt: up to 1,000 characters.
aspect_ratio (text-to-video only): 1:1, 16:9 or 9:16.
Duration: 5 or 10 seconds.
Optional negative_prompt.

Capabilities

What this model supports, straight from the schema — no pricing, no infrastructure detail.

Capability	Value
`end_frame` End frame	Yes
`video_edit` Video edit	—
`multi_shots` Multi-shot	—
`multi_prompt` Multi-prompt	—
`native_audio` Native audio	Yes
`text_to_video` Text-to-video	Yes
`image_to_video` Image-to-video	Yes
`max_prompt_length` Max prompt length	1000
`reference_to_video` Reference-to-video	—

Parameters

Fields accepted in params (or first-class, where applicable) for POST /generations.

Name	Label	Type	Required	Default	Options	Min / Max	Description
`prompt`	Prompt	textarea	Required	—	—	—	Scene description; up to 1,000 characters.
`image_urls`	Image references	multi_select	Optional	—	—	— – 1	Reference image for image-to-video (max 1).
`end_image_url`	End frame	url	Optional	—	—	—	Optional end frame; when set, sound must be false.
`sound`	Sound	boolean	Required	true	—	—	Enables native audio; required and incompatible with end_image_url.
`aspect_ratio`	Aspect ratio	select	Required	16:9	1:1 · 16:9 · 9:16	—	Aspect ratio (text-to-video only): 1:1, 16:9 or 9:16.
`duration`	Duration	select	Required	5	—	—	Duration: 5 or 10 seconds (default 5).
`negative_prompt`	Negative prompt	textarea	Optional	—	—	—	Terms to avoid in generation.

Example request

bash

curl -X POST https://caranguejo.art/api/v1/dev/generations \
  -H "Authorization: Bearer $CK" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling-2-6",
  "prompt": "Two friends chat in a busy cafe; rain can be heard outside.",
  "params": {
    "sound": true,
    "aspect_ratio": "16:9",
    "duration": 5
  }
}'

javascript

const res = await fetch("https://caranguejo.art/api/v1/dev/generations", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.CK,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "kling-2-6",
    "prompt": "Two friends chat in a busy cafe; rain can be heard outside.",
    "params": {
      "sound": true,
      "aspect_ratio": "16:9",
      "duration": 5
    }
  }),
});
const { data } = await res.json();

Example response

json

{
  "id": "9f0c1a7e-…",
  "object": "generation",
  "model": "kling-2-6",
  "type": "video",
  "status": "completed",
  "output": {
    "assets": [
      {
        "url": "https://media.caranguejo.art/outputs/example.mp4",
        "type": "video"
      }
    ]
  }
}

The job's real cost is returned as credits_charged on the completed response — check GET /balance for the account balance.

Common errors for this job type:

`insufficient_credits`	Account balance can't cover the job cost.
`content_policy_violation`	Prompt or media rejected by content policy.
`generation_timeout`	The job exceeded the maximum processing time.
`rate_limited`	Too many requests per minute.
`invalid_input`	A required parameter is missing or outside the model's schema.
`generation_failed`	Generic processing failure.