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
| Field | Value |
|---|---|
| Model ID | bailian-videoretalk |
| CLI | dlazy videoretalk |
| MCP | videoretalk (Claude Code surfaces this as mcp__dlazy__videoretalk) |
| Type | video |
| Execution | Async task; the CLI polls until completion (--no-wait returns generateId immediately) |
| Batch | Supports --batch <n> parallel fan-out |
Parameters
| Arg | Type | Required | Notes |
|---|---|---|---|
video_url | url | Yes | Video URL; video (accepts URL, local path, or data: URL) |
audio_url | url | Yes | Audio URL; audio (accepts URL, local path, or data: URL) |
ref_image_url | url | No | Reference Face Image; image (accepts URL, local path, or data: URL) |
video_extension | "true" | "false" | No | Extend Video to Audio Length; default "false" |
query_face_threshold | string | No | Face Match Threshold; default 170; only when ref_image_url is non-empty |
--input @file.jsonor--input '{...}'can supply all args at once; flags take precedence over--inputkeys.
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 4Compose 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.
video-replicate
Video replicate tool: extracts the first frame and audio from the source video, runs video understanding for a prompt, and returns a Seedance 2.0 replicate bundle (first frame + audio + video).
videoseg
Video human segmentation tool: invokes Aliyun's async SegmentVideoBody and returns a same-length black/white mask video, suitable for downstream compositing or matting.