Skip to content
Docs menu

Video models

Volcengine Video-to-Video Lip Sync

On this page

Volcengine Video-to-Video Lip Sync — high-quality AI video generation.

modelIdvolcengine-video-to-video-lip-sync
Modalityvideo
PricingSee this model on the Pricing page for the current per-call price (with your markup).

Operations

OperationmodelIdEndpointRequired input
Defaultvolcengine-video-to-video-lip-syncPOST /api/v1/generatevideo_url, audio_url, mode
Poll taskGET /api/v1/task/{id}?model=volcengine-video-to-video-lip-sync

Input parameters

FieldTypeRequiredValues / example
video_urlstringYesVideo asset URL (image URL)
audio_urlstringYesTarget pure vocal audio URL; used to drive video lip movements. (image URL)
modestringYesService identifier (options: lite | basic) (default: lite)
separate_vocalbooleanNoEnable vocal separation to suppress background noise. (true/false) (default: false)
open_scenedetbooleanNoWhether to enable scene segmentation and speaker identification. Supported only in Basic mode. (true/false) (default: false)
align_audiobooleanNoSupported in lite mode. Whether to loop the video when the audio is longer than the video. (true/false) (default: true)
align_audio_reversebooleanNoSupported in lite mode. Loop the video in reverse. Requires Align Audio to be on — the call is refused otherwise. (true/false) (default: false)
templ_start_secondsnumberNoSupported in lite mode. Start time of the template video, in seconds. (default: 0)

Example request

bash
curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"volcengine-video-to-video-lip-sync","input":{"video_url":"https://example.com/input.mp4","audio_url":"https://example.com/input.mp3","mode":"lite","separate_vocal":false,"open_scenedet":false,"align_audio":true,"align_audio_reverse":false,"templ_start_seconds":0}}'