Use Volcengine Video Lip Sync through Rivya Public API v1 with model id volcengine-video-lip-sync, supported inputs, parameters, Files API rules, credits, and response examples.

Available via APIReadinessVideo

API model id

volcengine-video-lip-sync

Inputs

file

Files API

Required for reference modes

Base credits

per_input_second · default=8 · ⌈total⌉

Capability

Video

Billing

METERED

Prompt limit

No documented prompt limit

Request contract

Send the model id at the top level. Model-specific controls belong in params.

Key	Type	Required	Default	Description
model	string	Yes	volcengine-video-lip-sync	Use the volcengine-video-lip-sync API model id.
prompt	string	No	-	Prompt text for models that support text input.
params	object	Yes	-	Model-specific parameter object. Use the rows below for allowed keys.
client_request_id	string	No	-	Optional client-side id for tracing requests in your system.

Model parameters

Key	Type	Required	Default	Range	Options	Description
mode	select	Yes	lite	-	lite, basic	Lite fits front-facing single-person footage; Basic supports more complex single-person scenes.
separate_vocal	select	No	false	-	false, true	Enable vocal separation when the target audio includes background sound that should be suppressed.
open_scenedet	select	No	false	-	false, true	Available only in Basic mode for scene segmentation and speaker identification.
align_audio	select	No	true	-	true, false	Available only in Lite mode. Loop the video when the audio is longer than the source footage.
align_audio_reverse	select	No	false	-	false, true	Available only in Lite mode and requires audio alignment to be on.
templ_start_seconds	number	No	0	min 0	-	Available only in Lite mode. Choose a non-negative start time in the source video.

Upload policy

Upload reference files first, then place the returned URL and duration token inside params.referenceMediaItems.

Reference rule

Source video and target audio: Upload exactly one MP4 or MOV video up to 95 MB and one MP3, M4A, WAV, AAC, or OGG vocal track up to 10 MB.

Max files

Accepted file kinds

video, audio

Duration token

Video and audio references should carry durationToken from /api/v1/files when duration verification is required.

kind	Max size	MIME types
video	95 MB	video/mp4, video/quicktime
audio	10 MB	audio/mpeg, audio/mp4, audio/wav, audio/x-wav, audio/aac, audio/ogg

Minimal request

{
  "model": "volcengine-video-lip-sync",
  "params": {
    "mode": "lite",
    "separate_vocal": "false",
    "open_scenedet": "false",
    "align_audio": "true",
    "align_audio_reverse": "false",
    "templ_start_seconds": 0
  }
}

Reference-file request

{
  "model": "volcengine-video-lip-sync",
  "params": {
    "mode": "lite",
    "separate_vocal": "false",
    "open_scenedet": "false",
    "align_audio": "true",
    "align_audio_reverse": "false",
    "templ_start_seconds": 0,
    "referenceMediaItems": [
      {
        "url": "https://cdn.example.com/reference-video.mp4",
        "kind": "video",
        "name": "reference-video.mp4",
        "mimeType": "video/mp4",
        "durationSeconds": 8,
        "durationToken": "video_duration_token_from_files_api",
        "width": 1280,
        "height": 720,
        "sizeBytes": 8388608,
        "framesPerSecond": 30,
        "videoBitrateMbps": 8,
        "videoMetadataToken": "video_metadata_token_from_original_files_api_upload_response"
      },
      {
        "url": "https://cdn.example.com/reference-audio.wav",
        "kind": "audio",
        "name": "reference-audio.wav",
        "mimeType": "audio/wav",
        "durationSeconds": 12,
        "durationToken": "audio_duration_token_from_files_api"
      }
    ]
  }
}

Create response

The create endpoint returns a public task id. Poll the status endpoint until the task succeeds or fails.

{
  "id": "task_volcengine_video_lip_sync_example",
  "status": "queued",
  "model": "volcengine-video-lip-sync",
  "reserved_credits": 8,
  "final_credits": 0,
  "settlement_status": "RESERVED",
  "created_at": "2026-05-11T00:00:00.000Z",
  "updated_at": "2026-05-11T00:00:00.000Z",
  "result": null,
  "error": null
}

Common errors

validation_failed, insufficient_credits, idempotency_conflict, rate_limited, not_found

Some modes require Files API reference uploads.

Volcengine Video Lip Sync API Integration