Skip to main content
Glama

switch

by ai.switchapp

Lip Sync Video

lip_sync_video

Lip-sync audio onto one of your videos. DEFAULT and recommended: action="create" with video_url + sound_file (base64 data URI) — Sync Labs Sync 3 syncs the whole clip in one pass, no face step, no timing, highest quality. You do not need to pass engine at all. Kling flow, only when a line must land on an exact frame (manual timing control): (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
NameRequiredDescriptionDefault
actionYesWhich step to run.
engineNocreate: 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.
face_idNocreate: a face_id from identify-face (one face supported).
task_idNostatus: the task_id from create.
audio_idNocreate: alternative to sound_file — an existing audio id.
video_urlNoidentify-face: the source video (MP4/MOV, 2-60s, <=100MB, 720p/1080p). Use a SwitchApp/public URL.
session_idNocreate: from identify-face.
sound_fileNocreate: base64 data URI of the audio (e.g. data:audio/mpeg;base64,...).
speech_volumeNocreate: how loud the new speech is, as a percent 0-100 (default 100).
sound_end_timeNocreate: audio end, in MILLISECONDS.
sound_start_timeNocreate: audio start, in MILLISECONDS.
sound_insert_timeNocreate: where in the video to place the audio, in MILLISECONDS.
original_audio_volumeNocreate: how loud the clip's own sound stays, as a percent 0-100 (default 0).

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • 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."
  2. Changed4 schema fields changed
    • 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"
  3. Changed1 schema field changed
    • 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"
+}
  4. First observed

TDQS

A4.9/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint=false annotation, it discloses pricing (credits charged on create, refund on failure), the need for a public URL, format/constraint details (2-60s, <=100MB, 720p/1080p), and the final output (branded SwitchApp view_url). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but information-dense, with clear internal structure (default flow, Kling flow, status). No filler or repetition; every sentence adds value. Minor deduction for readability—the single block with parentheticals could be broken into clearer steps, but it remains efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 13-parameter tool with no output schema, the description covers all necessary ground: action steps, parameter dependencies, constraints, defaults, billing, and expected return. Nothing critical is missing for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds crucial context beyond schema: the default engine behavior, the fact that engine can be omitted, the MS unit requirement for timing parameters, volume ranges, and the distinction between sound_file and audio_id. This is rich semantic guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Lip-sync audio onto one of your videos') and clearly distinguishes two distinct flows (default Sync Labs vs. Kling timeline). It fully clarifies what the tool does and how it differs from other video/audio tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly recommends the default action and parameter set, then provides step-by-step instructions for the alternative Kling flow, including when to use it (manual timing control) and how to poll status. It also notes when not to pass the engine parameter, giving clear decision criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All switch toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.5/5.0
Disambiguation2/5

Several tools occupy nearly identical semantic ground: apply_iphone_realism and apply_ugc both describe casual phone-shot looks, upload_media and upload_reference_asset both accept uploads, and analyze_video overlaps heavily with analyze_video_report. The many apply_* style tools are essentially one tool parameterized by style, so agents can easily select the wrong one.

Naming Consistency4/5

Most tools follow a clear verb_noun snake_case pattern such as generate_image, list_my_videos, get_editor_run, and upscale_video. A few outliers like voice, talking_avatar_video, and video_to_prompt do not use the same verb-first convention, but they are still readable and do not create significant confusion.

Tool Count1/5

At 55 tools, the surface is far beyond what is appropriate for an MCP server; many of these be collapsed or parameterized, especially the 10 apply_* style wrappers and several overlapping upload/status helpers. Even for a broad media platform, this scale forces a huge context window and makes selecting the right tool impractical.

Completeness2/5

The surface covers generation, media display, video analysis, and Editor workflows well, but there are obvious gaps in library lifecycle management: move_asset and create_folder are referenced in tool descriptions without being exposed, and there is no clean way to delete or reorganize media assets. Agents following the descriptions will try to call tools that do not exist.

Resources