dLazy AIdLazy AI
Model ReferenceVideo Models

videoretalk

Tongyi VideoRetalk lip sync / lip-sync (mouth sync, dubbing) video model — takes a talking-person video plus a voice audio track and regenerates the video so the speaker's mouth/lips match the new audio. Use this for lip syncing a person video to new speech. Optionally provide a reference face image to pick the target person when the video contains multiple faces.

Tongyi VideoRetalk lip sync / lip-sync (mouth sync, dubbing) video model — takes a talking-person video plus a voice audio track and regenerates the video so the speaker's mouth/lips match the new audio. Use this for lip syncing a person video to new speech. Optionally provide a reference face image to pick the target person when the video contains multiple faces.

Overview

FieldValue
Model IDbailian-videoretalk
CLIdlazy videoretalk
MCPvideoretalk (Claude Code surfaces this as mcp__dlazy__videoretalk)
Typevideo
ExecutionAsync task; the CLI polls until completion (--no-wait returns generateId immediately)
BatchSupports --batch <n> parallel fan-out

Parameters

ArgTypeRequiredNotes
video_urlurlYesVideo URL; video (accepts URL, local path, or data: URL)
audio_urlurlYesAudio URL; audio (accepts URL, local path, or data: URL)
ref_image_urlurlNoReference Face Image; image (accepts URL, local path, or data: URL)
video_extension"true" | "false"NoExtend Video to Audio Length; default "false"
query_face_thresholdstringNoFace Match Threshold; default 170; only when ref_image_url is non-empty

--input @file.json or --input '{...}' can supply all args at once; flags take precedence over --input keys.

CLI Examples

dlazy videoretalk --help
dlazy videoretalk --video_url "https://example.com/source.mp4" --audio_url "https://example.com/source.mp3"
dlazy videoretalk --video_url "./local-video.mp4" --audio_url "https://example.com/source.mp3"
dlazy videoretalk --video_url "https://example.com/source.mp4" --audio_url "https://example.com/source.mp3" --dry-run
dlazy videoretalk --video_url "https://example.com/source.mp4" --audio_url "https://example.com/source.mp3" --no-wait
dlazy videoretalk --video_url "https://example.com/source.mp4" --audio_url "https://example.com/source.mp3" --batch 4

Compose with a pipeline

dlazy seedance-2.0-fast --prompt "reference clip" \
  | dlazy videoretalk --video_url -

MCP

MCP is consumed by AI clients, not handwritten. Once dLazy is registered as an MCP server the tool appears in the client's tool list — Claude Code surfaces it as mcp__dlazy__videoretalk; generic clients (e.g. OpenClaw) call it as videoretalk.

See MCP setup for how to add the server.

Output

{
  "outputs": [
    { "type": "video", "id": "o_...", "url": "https://files.dlazy.com/result.mp4", "mimeType": "video/mp4" }
  ]
}

Media tools emit image / video / audio / file outputs. Use --output url to print only the URLs on stdout.

On this page