Skip to main content
Glama

caption_video

Captions local video or audio files, exporting burned-in MP4, transparent MOV/WebM overlay, or SRT/VTT subtitles while rendering locally so media never uploads.

Instructions

Captions a local video or audio file with the Cuecaps studio's renderer in headless Chrome or Edge and writes .captions. next to it, never replacing a file: an MP4 with the captions burned in, a transparent MOV or WebM overlay, or SRT or VTT subtitles. Returns the file, its duration in seconds, the engine, the cloud minutes used and a studio link to fine-tune words and style. Needs a Creator or Pro key; 1440p and 4K need Pro. Transcription works as in transcribe, and the video never leaves this machine. Use transcribe when only the words are needed, and studio_link when the user wants to edit by hand or has no key.

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": {
      "path": "<path>"
    },
    "name": "caption_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
fpsNoFrames per second.
langNoThe spoken language. Give it for any video that isn't in English; auto lets cloud transcription detect it.
pathYesAbsolute path to the video or audio file: MP4, MOV, WebM, MP3, WAV, M4A or another format the studio opens.
linesNoLines per caption.
styleNoCaption style. list_styles shows how each one looks.
wordsNoWords per caption; 1 shows one word at a time.
aspectNoFrame shape: 9:16 for TikTok, Shorts and Reels, 1:1 or 4:5 for feed posts, 16:9 for YouTube.
engineNocloud: ElevenLabs Scribe on the plan's cloud minutes, strongest on music, accents and 90+ languages; the default when the minutes left cover the file. device: on-device Whisper, no minutes; the first run downloads the model (132 MB).
outputNomp4 with the captions burned in, mov or webm as a transparent captions-only overlay, or srt or vtt subtitles. Defaults to out_path's extension when out_path is given, else mp4.
keytermsNoNames and words for cloud transcription to spell your way.
out_pathNoAbsolute path to write to instead of <name>.captions.<ext> next to the input, ending in .mp4, .mov, .webm, .srt or .vtt; its extension sets output. An existing file is never replaced: -2, -3 and so on go before the extension.
positionNoWhere the captions sit in the frame.
resolutionNoShort side of the video. 1440p and 4k come with Pro.1080p

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare the mutation/scope profile; the description adds what an agent actually needs: the file is written next to the input, an existing file is never replaced, the video never leaves the machine, and the return payload includes the file, duration, engine, cloud minutes and a studio link. It also discloses the key-tier gating, which the annotations do not cover. Nothing contradicts the hints (destructiveHint=false is consistent with 'never replacing a file').

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?

It is a single dense paragraph, but it is front-loaded with purpose and output behavior before prerequisites and alternatives. A couple of clauses are near-redundant (engine/cloud-minutes detail is repeated in the returned-fields list), slightly hurting scannability for a 13-parameter tool.

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 13-parameter, multi-output rendering tool with no output schema, the description covers writes, collision handling, plan gating, privacy, return fields and sibling alternatives. An agent can invoke it correctly without further context.

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

Parameters3/5

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

Schema coverage is 100% and eight parameters carry enums, so the schema already documents nearly everything. The description reinforces a few semantics (burned-in vs transparent overlay vs subtitles, out_path extension deciding format) but adds little beyond the schema text, so the baseline of 3 applies.

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 opens with a specific verb and resource ('Captions a local video or audio file') and immediately names the renderer, the output formats, and the write location. It is clearly distinguishable from siblings: transcribe is named as the words-only path and studio_link as the manual-edit path.

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 states exactly when to use alternatives ('Use transcribe when only the words are needed, and studio_link when the user wants to edit by hand or has no key') and adds prerequisites (Creator or Pro key, Pro for 1440p/4K). An agent has no guesswork about routing.

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