kwaivgi/kling-video/v2.6/pro/image-to-video

Name: Kling Video V2.6 Pro
Author: KwaiVGI

Kling Video V2.6 Pro is KwaiVGI's image-to-video AI model. Bring static images to life with fluid animation, consistent character motion, and professional-grade video output.

Input

Prompt(string)

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the image to be used for the video

This field is required.

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL of the image to be used for the end of the video

Duration(integer)

The duration of the generated video in seconds Allowed values: 5, 10.

Generate Audio(boolean)

Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase.

Voice Ids(array)

Optional Voice IDs for video generation. Reference voices in your prompt with <<<voice_1>>> and <<<voice_2>>> (maximum 2 voices per task). Get voice IDs from the kling video create-voice endpoint: https://fal.ai/models/fal-ai/kling-video/create-voice

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDkwaivgi/kling-video/v2.6/pro/image-to-video

Input Schema

6 parameters · 2 required · 4 optional

Parameter	Type	Required	Description
`image`	string	Required	URL of the image to be used for the video
`prompt`	string	Required	Max length: 2500
`duration`	integer	Optional	The duration of the generated video in seconds · Options: 5, 10 · Default: 5 510
`end_image`	string	Optional	URL of the image to be used for the end of the video
`voice_ids`	string[]	Optional	Optional Voice IDs for video generation. Reference voices in your prompt with <<<voice_1>>> and <<<voice_2>>> (maximum 2 voices per task). Get voice IDs from the kling video create-voice endpoint: https://fal.ai/models/fal-ai/kling-video/create-voice
`generate_audio`	boolean	Optional	Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. · Default: true

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "kwaivgi/kling-video/v2.6/pro/image-to-video",
  "image": "https://static.sandbase.ai/examples/mirrored/b08c180c4436-BSJXz9Ht-jgRgMf4IGxLU_upscaled.png",
  "prompt": "A king walks slowly and says \"My people, here I am! I am here to save you all\"",
  "duration": 5,
  "generate_audio": true
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Kling Video V2.6 Pro

API README

Kling Video V2.6 Pro Image-to-Video

Kling Video V2.6 Pro animates a supplied start image from a written direction. The image establishes the opening composition while the prompt describes motion, camera, and sound. An optional end image can guide the last frame.

The route produces either a 5- or 10-second video and returns a video URL. Native audio is enabled by default, and optional voice IDs can be referenced in the prompt. The request remains centered on the required image and prompt.

Highlights

Cinematic image animation. The exact V2.6 Pro route is documented for cinematic visuals. It applies that positioning to a supplied opening image.
Fluid motion. Fluid motion is explicitly named for this version, tier, and route. Motion is generated from the image and written action.
Improved visual quality. The exact API documentation identifies improved visual quality for V2.6 Pro image-to-video. This is a model result rather than a schema setting.
Improved motion consistency. The same exact documentation identifies improved motion consistency. It complements the route's fluid-motion positioning.

Pricing

Duration	Price
5 seconds	$0.70
10 seconds	$1.40

When to Use

✅ Good fit	❌ Consider alternatives
Animate a supplied still into a short action.	Generate without a starting image; use text-to-video.
Direct movement and camera behavior from the opening frame.	Require a duration other than 5 or 10 seconds.
Guide the final state with an optional end image.	Require a selectable aspect ratio independent of the image.
Generate speech and scene sound together with the motion.	Require more than two optional voice bindings.
Use this exact V2.6 Pro workflow.	Require controls that are not present in the local contract.

Prompt Guide

Describe motion relative to the supplied opening image. State the subject action, camera path, environmental movement, dialogue or sound, and any final-frame transition.

Subject action: [movement over time]
Camera: [framing and movement]
Environment: [light and background motion]
Timing: [pace and progression]
Dialogue and sound: [spoken lines, ambience, effects]
Final state: [arrival at the optional end image]

{
  "image": "<start-image-url>",
  "prompt": "A king walks slowly and says \"My people, here I am! I am here to save you all.\"",
  "duration": 5,
  "generate_audio": true
}

Technical Specs

Spec	Value
Required inputs	`image`, `prompt`
Prompt length	Up to 2,500 characters
Duration	5 or 10 seconds; default 5
Frame guidance	Required `image`; optional `end_image`
Native audio	Optional; default enabled
Voice IDs	Optional array; maximum two documented locally
Output	Video URL with optional file metadata

Kling Video V2.6 Pro Text-to-Video — Generate without a starting image.
Kling Video V2.5 Turbo Pro Image-to-Video — Use the earlier Turbo Pro image route.