Kling 2.6 Text To Video
Kling 2.6 text-to-video with native audio support.
Kling 2.6 text-to-video with native audio support.
Kling 2.6 Text To Video is the prompt-only Kling 2.6 node. It exposes duration, aspect ratio, generated audio, negative prompt, and CFG scale.
Use it when a prompt should define both motion and optional sound. Use image-to-video when a source frame should anchor the clip.
Prompt
StringPrompt
Prompt
StringProvide a detailed description of the subject, action, environment, and cinematic style to guide the video generation.
Duration
StringThe duration of the generated video in seconds
5Aspect Ratio
StringThe aspect ratio of the generated video frame
16:9Generate Audio
BooleanWhether 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.
trueNegative Prompt
StringDefines visual elements, styles, or artifacts to exclude from the generated video.
blur, distort, and low qualityCfg Scale
NumberThe CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt.
0.5Output
InferredOutput
Nodespell Team
Type
Node
Status
Official
Package
Nodespell AI
Category
AI / Video / KuaishouInput
Output