switch

Lip Sync Video

lip_sync_video

Lip-sync audio onto one of your videos. For action="create" without engine, session_id, or face_id, the default is Sync Labs Sync 3: video_url + sound_file (base64 data URI) processes the whole clip without a face-identification step or manual timing. engine="best" explicitly selects this lane. Kling provides manual timing control with engine="kling", or with session_id/face_id when engine is omitted: (1) action="identify-face" with video_url (MP4/MOV, 2-60s, <=100MB, 720p/1080p); (2) action="create" with session_id + face_id + audio + timing IN MILLISECONDS (sound_start_time, sound_end_time, sound_insert_time) + optional speech_volume/original_audio_volume (0-100); (3) action="status" with the task_id to poll — returns a branded SwitchApp view_url when done. Charges credits on create; failed jobs are refunded.

Input Schema

TableJSON Schema

Name	Required	Description
`action`	Yes	Which step to run.
`engine`	No	create: optional. "best" selects Sync Labs Sync 3 for whole-clip lip sync using video_url + sound_file. When engine is omitted, this lane is used unless session_id or face_id is supplied. "kling" selects the timeline flow with manual audio placement in milliseconds.
`face_id`	No	create: a face_id from identify-face (one face supported).
`task_id`	No	status: the task_id from create.
`audio_id`	No	create: alternative to sound_file — an existing audio id.
`video_url`	No	identify-face: the source video (MP4/MOV, 2-60s, <=100MB, 720p/1080p). Use a SwitchApp/public URL.
`session_id`	No	create: from identify-face.
`sound_file`	No	create: base64 data URI of the audio (e.g. data:audio/mpeg;base64,...).
`speech_volume`	No	create: how loud the new speech is, as a percent 0-100 (default 100).
`sound_end_time`	No	create: audio end, in MILLISECONDS.
`keep_background`	No	create, Sync 3 lane: keep the clip's own music and room under the new speech (default true); false gives the new speech alone.
`sound_start_time`	No	create: audio start, in MILLISECONDS.
`sound_insert_time`	No	create: where in the video to place the audio, in MILLISECONDS.
`original_audio_volume`	No	create: how loud the clip's own sound stays, as a percent 0-100 (default 100, the clip keeps its sound).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 8, 2026

changedInput schema / properties / engine / description

Previous value: -"create: OPTIONAL. Leave it out — the default is \"best\", Sync Labs Sync 3, whole-clip and highest quality, needing only video_url + sound_file. Pass \"kling\" only for the timeline flow where you place the audio yourself in milliseconds."New value: +"create: optional. \"best\" selects Sync Labs Sync 3 for whole-clip lip sync using video_url + sound_file. When engine is omitted, this lane is used unless session_id or face_id is supplied. \"kling\" selects the timeline flow with manual audio placement in milliseconds."

Changed2 schema fields changedSep 29, 2026

addedInput schema / properties / keep_background

Added value: +{
+  "description": "create, Sync 3 lane: keep the clip's own music and room under the new speech (default true); false gives the new speech alone.",
+  "type": "boolean"
+}

changedInput schema / properties / original_audio_volume / description

Previous value: -"create: how loud the clip's own sound stays, as a percent 0-100 (default 0)."New value: +"create: how loud the clip's own sound stays, as a percent 0-100 (default 100, the clip keeps its sound)."

Changed1 schema field changedSep 2, 2026

changedInput schema / properties / engine / description

Previous value: -"create: \"best\" = highest-quality whole-clip sync (needs only video_url + sound_file). Default \"kling\" (timeline flow)."New value: +"create: OPTIONAL. Leave it out — the default is \"best\", Sync Labs Sync 3, whole-clip and highest quality, needing only video_url + sound_file. Pass \"kling\" only for the timeline flow where you place the audio yourself in milliseconds."

Changed4 schema fields changedJul 4, 2026

changedInput schema / properties / original_audio_volume / description

Previous value: -"create: 0-100 (default 0)."New value: +"create: how loud the clip's own sound stays, as a percent 0-100 (default 0)."

changedInput schema / properties / original_audio_volume / type
```
Previous value: -"integer"New value: +"number"
```

changedInput schema / properties / speech_volume / description

Previous value: -"create: 0-100 (default 100)."New value: +"create: how loud the new speech is, as a percent 0-100 (default 100)."

changedInput schema / properties / speech_volume / type
```
Previous value: -"integer"New value: +"number"
```

Changed1 schema field changedJul 4, 2026

addedInput schema / properties / engine

Added value: +{
+  "description": "create: \"best\" = highest-quality whole-clip sync (needs only video_url + sound_file). Default \"kling\" (timeline flow).",
+  "enum": [
+    "best",
+    "kling"
+  ],
+  "type": "string"
+}

First observedJun 5, 2026

TDQS

Score is being calculated.

All switch tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?