Volcengine video to video lip sync

video Volcengine price on request

Request

POST https://app.video-blade.com/api/v1/generations
X-API-Key: vb_…
Content-Type: application/json

{
  "callback_url": "https://your-app.example/callbacks/video-blade",
  "input": {
    "audio_url": "\u2026",
    "mode": "lite",
    "video_url": "\u2026"
  },
  "model": "volcengine-video-to-video-lip-sync"
}

Input parameters

Name	Type	Required	Description
`mode`	string	required	Service mode for lip-sync generation. - `lite`: For single-person frontal videos. Faster processing. - `basic`: For single-person complex scenes. Supports scene segmentation and speaker identification. Values: `lite`, `basic`
`video_url`	string	required	Video URL. Supported resolution: 360p–1080p. Videos above 1080p will be compressed to 1080p, while videos below 360p are not supported. Supported formats: MOV, MP4, HDR. Recommended codec: H.264. Other formats/codecs may be transcoded. Max file size: 500 MB. Bitrate: 1–30 Mbps. Frame rate: 24–60 fps.
`audio_url`	string	required	Target pure vocal audio URL; used to drive video lip movements. Accepted file types: audio/mpeg, audio/wav, audio/x-wav, audio/aac, audio/mp4, audio/ogg. Max file size: 10MB.
`separate_vocal`	boolean	optional	Enable vocal separation to suppress background noise. Default value: `false`. Default: `False`
`open_scenedet`	boolean	optional	Whether to enable scene segmentation and speaker identification. Supported only in Basic mode. Default value: `false`. Default: `False`
`align_audio`	boolean	optional	Supported in Lite mode. Whether to loop the video when the audio is longer than the video. Default value: `true`. Default: `True`
`align_audio_reverse`	boolean	optional	Supported in Lite mode. Whether to loop the video in reverse (backward). Requires `align_audio` to be set to `true`. Default value: `false`. Default: `False`
`templ_start_seconds`	number	optional	Supported in Lite mode. Start time of the template video, in seconds. Default value: `0`. Default: `0`

Pricing

Price on request; the charge is settled from actual consumption with the video coefficient ×2.0. See Pricing & tokens.