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| Field | Type | Default | Allowed |
|---|---|---|---|
prompt* promptScene / motion description. | string | — | string |
duration duration | number | 2 | from 2 · up to 60 · step 1 seconds |
Speaker video* speakerVideoAsset input for the speakerVideo slot. | string | — | video · asset, https, data |
Speech audio* speechAudioAsset input for the speechAudio slot. | string | — | voiceover · asset, https, data |
prompt*
promptScene / motion description.
- Type
- string
- Default
- —
- Allowed
- string
duration
duration- Type
- number
- Default
- 2
- Allowed
- from 2 · up to 60 · step 1 seconds
Speaker video*
speakerVideoAsset input for the speakerVideo slot.
- Type
- string
- Default
- —
- Allowed
- video · asset, https, data
Speech audio*
speechAudioAsset input for the speechAudio slot.
- Type
- string
- Default
- —
- Allowed
- voiceover · asset, https, data
Cost
6 tokens/sCapabilities
Modes
video_to_videoAsset slots
speakerVideo:video*speechAudio:voiceover*Run Kling Lip-Sync
Get an API key and the same request shape will work across every model in the catalog.