Back to Nodes
Kling Lip Sync

Kling Lip Sync

Official

Kling lip-sync for matching a video to supplied speech.

Nodespell AI
AI / Video / Kuaishou

Kling lip-sync for matching a video to supplied speech.

Kling Lip Sync is for replacing or adding spoken performance to an existing video. It accepts video and audio inputs, with text support depending on the graph setup.

Use it when the footage already exists and the main task is mouth synchronization. Use talking-avatar nodes when starting from a still image instead.

Inputs (2)

Video Url

String

The URL of the video to generate the lip sync for. Supports .mp4/.mov, ≤100MB, 2–10s, 720p/1080p only, width/height 720–1920px.

Min: 0Max: 100

Audio Url

String

The URL of the audio to generate the lip sync for. Minimum duration is 2s and maximum duration is 60s. Maximum file size is 5MB.

Min: 0Max: 100
Outputs (1)

Output

Inferred

Output

Nodespell Team

Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Video / Kuaishou

Input

VideoAudioText

Output

Video

Keywords

Video Edit
Use in Workflow