Available now

Kling 2.6 Pro: text to video

By Kuaishou

Kling 2.6 Pro turns a written scene or a first frame into a 5 or 10 second clip with optional sound, and can copy a reference video's movement onto your character.

Model ID
Maker
Kuaishou

Input

Fields marked * are required. Review the price before generating.

Example prompt. Edit it or write your own.

The duration of the generated video in seconds

The aspect ratio of the generated video frame

Additional settings

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt.

Starting price$0.111 / second

You sign up first. Your settings are kept.

About this model

Overview

Kling 2.6 Pro makes 5 or 10 second clips in 16:9, 9:16 or 1:1. Sound is on by default: speech comes out in English or Chinese, and lines in other languages are translated to English.

Start from text, or from an image that becomes the first frame, with an optional end image. Motion control takes a photo of your character and a reference video, then has the character perform the same movement.

What you can build

  • Short scenes with dialogue and ambient sound from one prompt
  • A product photo that opens a moving shot and ends on a set frame
  • Your character repeating a dance or gesture from a filmed clip
  • Vertical clips for social feeds and square ones for ads

Prompting tips

  • Write spoken English lines in lowercase and keep capitals for acronyms and names, as the sound setting asks.
  • Turn the guidance scale up when the clip drifts from your prompt, down when motion looks stiff.
  • For motion control, use a photo where the whole body is clear and unblocked, and a video with one person in frame.
  • Pick video orientation for complex moves and image orientation when the camera move matters more.

What to check

Watch movement and listen to speech separately. Check pronunciation, lip timing and whether ambience overwhelms the voice.

Inputs

  • Prompt (required)
  • Duration (optional): The duration of the generated video in seconds. Options: 5, 10.
  • Aspect Ratio (optional): The aspect ratio of the generated video frame. Options: 16:9, 9:16, 1:1.
  • Negative Prompt (optional)
  • Cfg Scale (optional): The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. From 0 to 1.
  • Generate Audio (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.

Output and limits

  • Length: 5 seconds to 10 seconds.
  • Aspect ratios: 16:9, 9:16, 1:1.
  • Sound can be generated together with the video.
  • Readable text inside the video, especially small text, is unreliable.
  • Scenes with several interacting characters can lose consistency.
  • Longer clips can show more motion drift or scene changes.
  • Low-quality inputs cause glitches: heavy compression, collages, screenshots and text overlays.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • audio off: $0.111 / second
  • audio on: $0.2219 / second
  • The total for your settings is rounded up to the next cent.