Skip to main content
Glama

transcribe

Convert speech to text locally with word-level timestamps from a media file or active timeline, returning time-prefixed lines and a JSON path.

Instructions

Transcribe speech locally with whisper.cpp (word-level timestamps). Returns the transcript as lines prefixed with [mm:ss.s] start times, plus the path of the full word-level JSON. Cached per file+model. If path is omitted, uses the active timeline's source media.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "transcribe"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
modelNoWhisper model. "base" (default) is fast; "small"/"medium"/"large-v3-turbo" are more accurate but slower. Downloaded on first use.
languageNoISO language code such as "en" or "fr"; default auto-detect.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does reasonably well: it discloses that processing is local, that results are cached per file+model, and exactly what the return payload looks like (timestamped lines plus a JSON path). It omits practical traits such as expected runtime, model download cost on first use, and whether a stale cache can be bypassed — gaps that matter for a compute-heavy operation.

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?

Four short sentences, each carrying distinct information: capability, return format, caching, and default input. The most decision-relevant facts (local transcription, output shape) are front-loaded with no filler.

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

Completeness4/5

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 correctly spends words describing the return value, and it covers the caching and default-path behaviors an agent needs to call it correctly. It is only slightly short of complete, lacking any hint about runtime or failure modes for a model-driven transcription job.

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 67% and the schema already documents model and language thoroughly (including the enum tradeoffs and download behavior). The description adds one genuinely new piece of meaning — that an omitted path falls back to the active timeline's source media — which the schema does not state. Beyond that it adds nothing about parameter behavior, so baseline-plus-one is appropriate.

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

Purpose4/5

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

States a specific verb and resource: transcribe speech with whisper.cpp, with word-level timestamps. It also says what it emits (timestamped transcript lines plus a word-level JSON path), which lets an agent distinguish it from a captioning or planning tool. It stops short of naming a sibling such as make_captions, so the differentiation is implied rather than explicit.

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

Usage Guidelines3/5

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

Usage is implied by the purpose (call it when you need a transcript), and the note 'If path is omitted, uses the active timeline's source media' gives a useful default for the common case. There is no explicit when-to-use/when-not guidance and no mention of how this relates to alternatives like make_captions or render_caption_overlay.

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