CutClip.one

shot.lipsync

Give a shot's take spoken dialogue with matching lips: ElevenLabs speaks the line in the speaker's voice (character.update voiceId), then a lip-sync model reworks the take's mouth to it. Works with any video model; best on close and medium shots with one visible face. The result is a new take with the line as its sound; it replaces the source take in the clip if that's still there (undoable). Costs credits (speech per character + lip-sync per second). Poll generation.list with shotId.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectId": "<projectId>",
      "shotId": "<shotId>"
    },
    "name": "shot.lipsync"
  }
}

Input Schema

Name	Required	Description
`text`	No	The words to speak. Defaults to the shot's dialogue without its speaker label
`model`	No	sync-lipsync-2 (default), sync-lipsync-2-pro (sharper, costlier) or kling-lipsync (2-10 s takes only, cheapest)
`dryRun`	No	Only preview the speaker, voice, line and cost; nothing is charged
`shotId`	Yes
`voiceId`	No	Override the speaker's voice (voice.list)
`projectId`	Yes
`speechModel`	No	eleven-multilingual-v2 (default), eleven-v3 or eleven-flash-v2.5
`takeAssetId`	No	The take to rework (a video from generation.list). Defaults to the take in the shot's clip

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does: it discloses the side effect (replaces the source take in the clip if still present), that it is undoable, the cost model (speech per character + lip-sync per second), and that it is asynchronous with polling via generation.list. That is exactly the behavioral context an agent needs before invoking a costly mutation.

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

Conciseness5/5

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

Six tight sentences, front-loaded with the core action and pipeline, then constraints, side effects, cost, and the polling instruction in that order. No filler and nothing repeated from structured fields verbatim.

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 an async, credit-consuming, take-replacing operation with 8 parameters and no output schema, the description covers what an agent cannot get elsewhere: quality preconditions, reversibility, billing, and how to track completion. Nothing essential to calling it correctly is missing.

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

Parameters4/5

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

Schema coverage is 75%, so the schema already documents most parameters; the description still adds meaning by tying the speaker's voice to character.update voiceId and explaining the override path, and by naming shotId as the polling key for generation.list. It does not deepen the model/speechModel trade-offs beyond what the schema text already says.

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?

States a specific verb and resource: give a shot's take spoken dialogue with matching lips, and spells out the two-stage pipeline (ElevenLabs TTS, then a lip-sync model reworks the mouth). An agent immediately knows this is an audio+video mutation on a take, not a plain voice change.

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

Usage Guidelines4/5

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

Gives real usage context — works with any video model, best on close/medium shots with one visible face — which tells the agent when this will produce good results. However it never names the obvious alternative (shot.revoice) or states when not to use this, so the agent must infer the choice between the two.

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

All CutClip.one 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.