ChatCut

submit_lipsync

Synchronize an existing video's visible speaker mouth with FINAL audio. Does not translate, clone voices, write dialogue, generate speech or create avatar performances. Changing dialogue does not authorize mouth changes: if the picture must stay unchanged, replace audio only. Load lipsync Skill. Reuse supplied final audio; otherwise generate or reuse final speech and resolve timing. Interactive Desktop asks for review of actual audio and treatment before paid rendering; external preauthorized callers must obtain approval first. Do not repeat identity/script questions for unchanged approved audio. For translation with automatic source-voice matching, default to video_translation: it includes lip-sync. A specified reusable voice or separately reviewable audio can use voice then this tool. Use one visible speaker in a suitable shot; the source video must keep its original speech audio. Align speech windows, pauses and picture meaning: equal total durations do not prove alignment. Resolve duration policy first. Multi-speaker assignment, severe occlusion and arbitrary duration mismatches are not guaranteed. Export a section as a separate asset to process only that section. Returns an asynchronous job, not a quality assessment. Track it and continue the requested edit with the resulting video. Natural mouth synchronization requires continuous audiovisual inspection, not static frames, metadata or timeline placement. On uncertain responses inspect the existing job before retrying. Fix wrong words or voice in the audio first; repeated lip-sync cannot fix them. At most 10 video generations run at once per account across video tools; extra submits are rejected, so wait for a running job to finish instead of retrying.

External MCP spend rule: this generates one video from supplied final audio and may spend credits. Confirm the source, final speech and duration policy; do not duplicate a translation's built-in lip-sync.

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": {
      "sourceVideoAssetId": "<sourceVideoAssetId>",
      "speechAudioAssetId": "<speechAudioAssetId>",
      "durationPolicy": "<durationPolicy>"
    },
    "name": "submit_lipsync"
  }
}

Input Schema

Name	Required	Description
`name`	No
`projectId`	No	Full project UUID. Required for external browser work; internal agents may omit. Execution/explicit-timeline calls never change later calls' target.
`requestId`	No	Omit normally: identical inputs reuse their existing job. Only for a user-requested fresh regeneration, create one new UUID and preserve it across retries. Never change it merely because a call timed out or failed; inspect the existing job first.
`timelineId`	No	Full timeline UUID, not a prefix. Required for browser work, even unplaced assets. Get it from read_project or manage_timelines action="list". Never switches visible timeline.
`durationPolicy`	Yes	preserve-video requires measured audio/video durations within 250 ms and disables dynamic duration; allow-adjustment uses ChatCut's conservative longer/shorter duration ratio <= 1.15 (not a verified provider formula). Adapt outside this range before submission; adjustment is not unlimited extension or authorization to discard footage. Never truncate dialogue.
`idempotencyKey`	No	Stable key for this browser execution. Reuse only with identical scope and parameters after a lost acknowledgement; applies only to this call.
`browserProfileId`	No	Optional browser profile override. Omit to select automatically; do not ask the user to choose.
`sourceVideoAssetId`	Yes	Existing project VIDEO with one visible speaker. The entire asset is processed; no spatial/speaker selector. A time crop does not isolate other people still visible. Not an avatar identity or portrait.
`speechAudioAssetId`	Yes	Final AUDIO whose exact words should be spoken. Not a voice-cloning reference sample. Reuse supplied audio; do not synthesize it again.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

First observedNov 5, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the annotations it discloses the important operating traits: the call returns an asynchronous job rather than a quality verdict, it spends credits, interactive runs pause for audio/treatment review while external callers need pre-approval, and a per-account cap of 10 concurrent video generations causes extra submits to be rejected. It also bounds the tool's competence (multi-speaker assignment, severe occlusion, arbitrary duration mismatch are not guaranteed) and warns that repeated lip-sync cannot fix wrong words or voice. The only friction is a mild tension with idempotentHint=false, since identical inputs reuse an existing job unless a fresh requestId is supplied — this is an escape-hatch nuance rather than a contradiction.

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

Conciseness3/5

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

The purpose is front-loaded and most sentences carry unique operational rules, but the body reads as a dense block of ~20 sentences with no grouping, making it hard for an agent to scan. There is some duplication, e.g. approval-before-render is stated both mid-paragraph and again in the trailing 'External MCP spend rule', and 'Fix wrong words or voice in the audio first' restates earlier exclusions.

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?

With no output schema, the description correctly takes on the return-value burden: 'Returns an asynchronous job, not a quality assessment. Track it and continue the requested edit with the resulting video', plus retry guidance ('On uncertain responses inspect the existing job before retrying'). Combined with credit spend, concurrency limits, approval gates and known limitations, an agent has everything needed to call this costly asynchronous mutation correctly.

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 89%, so most parameter meaning is already structured; the description still adds behavioral context the schema lacks, notably 'Align speech windows, pauses and picture meaning: equal total durations do not prove alignment' and 'Resolve duration policy first', which tells the agent how durationPolicy interacts with real audio. It reinforces, rather than repeats, the schema's constraints on sourceVideoAssetId ('one visible speaker', whole asset processed) and speechAudioAssetId ('reuse supplied audio; do not synthesize it again').

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 opening sentence gives a precise verb, resource and constraint: 'Synchronize an existing video's visible speaker mouth with FINAL audio.' The following negation list ('Does not translate, clone voices, write dialogue, generate speech or create avatar performances') explicitly separates it from video_translation, submit_voice, submit_avatar_video and submit_video, so an agent can route without opening any sibling schema.

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?

It names the alternative and the deciding condition: 'For translation with automatic source-voice matching, default to video_translation: it includes lip-sync', and 'A specified reusable voice or separately reviewable audio can use voice then this tool.' It also states when NOT to use it ('if the picture must stay unchanged, replace audio only'), requires resolving duration policy first, and covers the section-export path for partial processing.

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

All ChatCut 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.