Kling Lip-Sync

Retargets lip motion in an existing video to a new audio track. Use it when the video is already shot and you only need dubbing, localization, or speech replacement.

Cost

6 tokens/s

VideoProvider: Kling
Run generation
curl -X POST https://api.givon.ai/api/v1/generations \
  -H "Authorization: Bearer $GIVON_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"video","model":"kling-lip-sync","input":{"prompt":"cinematic drone shot over a city at night","duration":2,"speakerVideo":"asset://asset_...","speechAudio":"asset://asset_..."}}'

Input fields

* required
prompt*prompt

Scene / motion description.

Type
string
Default
Allowed
string
durationduration
Type
number
Default
2
Allowed
from 2 · up to 60 · step 1 seconds
Speaker video*speakerVideo

Asset input for the speakerVideo slot.

Type
string
Default
Allowed
video · asset, https, data
Speech audio*speechAudio

Asset input for the speechAudio slot.

Type
string
Default
Allowed
voiceover · asset, https, data

Cost

6 tokens/s

Capabilities

Modesvideo_to_video
Asset slotsspeakerVideo:video*speechAudio:voiceover*

Run Kling Lip-Sync

Get an API key and the same request shape will work across every model in the catalog.

Kling Lip-Sync API - video generation · Givon AI