Skip to main content
Glama

transcribe

Transcribe a local video or audio file to get every word with start and end times, plus SRT text and the engine used. Writes no file; use caption_video for captions or subtitles.

Instructions

Transcribes a local video or audio file and returns every word with its start and end time in seconds, plus the SRT text and the engine used. Writes no file: use caption_video when the user wants a captioned video, an overlay or a subtitle file. Needs a Creator or Pro key. engine "cloud" uses the plan's minutes and sends only compressed audio, deleted after transcription; "device" runs Whisper locally and uses none. Left unset, it picks cloud when the minutes left cover the file, else device.

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": "transcribe"
  }
}

Input Schema

NameRequiredDescriptionDefault
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.
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).
keytermsNoNames and words for cloud transcription to spell your way.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses that no file is written, that a Creator or Pro key is required, that cloud mode bills plan minutes and sends only compressed audio deleted after transcription, and that device mode downloads a 132 MB model on first run. These are auth, cost, and privacy facts the readOnlyHint/destructiveHint flags cannot express.

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?

Front-loaded with the outcome and return shape, then the exclusion, then the prerequisites and engine tradeoffs — every sentence earns its place. Minor redundancy: the cloud/device engine explanation partly repeats the engine schema description, and the sentences are dense enough that a reader must parse carefully.

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?

There is no output schema, so the description carries the return contract itself and does so (timestamped words, SRT text, engine). Auth requirement, cost model, file-writing behavior, and the alternative tool are all covered, leaving nothing an agent needs before calling it.

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 already 100%, but the description still adds value the schema lacks: the default resolution rule for engine ('picks cloud when the minutes left cover the file, else device') and the privacy/consumption consequences of cloud mode. This is behavior an agent would otherwise have to guess at call time.

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 ('Transcribes a local video or audio file') and immediately defines the return payload (words with start/end seconds, SRT text, engine used). It explicitly names the sibling it is not (caption_video) so an agent can route between them without opening either 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?

Explicitly excludes the captioning case: 'use caption_video when the user wants a captioned video, an overlay or a subtitle file.' It also gives selection guidance for the engine parameter, including the exact default heuristic when the parameter is unset, so the agent knows it can omit it.

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