Skip to main content
Glama

transcribe

Downloads YouTube audio and converts speech to text locally with Whisper when captions are unavailable, optionally limiting processing to a start/end time range.

Instructions

Download the audio and transcribe it locally with Whisper.

Slower than get_transcript but works when there are no captions and is usually more accurate. Pass start/end to download only that slice.

Args: url: YouTube URL or video ID. start: Optional start of the time slot, e.g. "12:30". end: Optional end of the time slot. model: Whisper model (tiny, base, small, medium, large-v3). Defaults to $WHISPER_MODEL or "small". language: Optional language code, e.g. "en", "fi". Auto-detect if empty.

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": {
      "url": "<url>"
    },
    "name": "transcribe"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
urlYes
modelNo
startNo
languageNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

With no annotations, the description carries the behavior burden and does well: it discloses local processing, the speed/accuracy tradeoff versus caption-based retrieval, and that start/end limits the downloaded slice. It stops short of stating runtime/cost expectations or whether audio files are persisted locally.

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?

Front-loaded with the action and the sibling comparison, then a compact Args list. No filler sentences; the tradeoff statement and the slice hint each carry distinct information.

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?

An output schema exists, so return values need not be described, and the description covers the inputs, defaults, and selection rationale. The remaining gap is operational context (expected duration, resource use, side effects like writing files) for a heavyweight local-inference call.

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 0%, so the description must supply all parameter meaning — and it does: url accepts a YouTube URL or bare video ID, start/end are optional time-slot bounds with a concrete example ("12:30"), model lists valid values and the $WHISPER_MODEL/"small" default, and language notes auto-detect when empty.

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 action pair — download the audio, then transcribe locally with Whisper — and explicitly contrasts itself with `get_transcript`. An agent can pick this tool over its sibling 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?

Gives an explicit when-to-use condition: use this when there are no captions, and it is usually more accurate but slower than `get_transcript`. It also scopes partial use via start/end, so the tradeoff against the alternative is fully defined.

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