Skip to main content
Glama
Sign In

Patchwell

by io.patchwell
OverviewDiscussionsAdmin

transcribe

Destructive

Transcribe speech in an audio or video file. Use it when you need the words in a recording, quotes with their time, who said what, or subtitles. Returns text, sentence segments, each word with start/end seconds, confidence and speaker (spk: 1, 2, ... told apart by voice), turns (speaker, start, end, text), speakers with talk time (and a name with its supporting quote when the recording says who someone is: "My name is...", "the next question comes from..."), SRT and VTT with speaker labels, and flags listing any phrase the guards removed (Whisper's invented phrases over silence and repetition loops) with its original text and time. Files over about 100 seconds of processing return {"status": "running", "job_id"}: call get_job_result with it. Price: $0.14 per audio hour, minimum $0.02 a file; failed downloads are free.

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
urlYesDirect http(s) link to an audio or video file: mp3, wav, m4a, ogg, flac, mp4, mov, webm and most others. Up to 3 hours. YouTube page links don't work; pass the media file itself.
languageNoTwo-letter language code such as en, es or ja. Leave it out to detect the language from the audio.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations, the description discloses a lot the agent could not otherwise know: the ~100-second async threshold and the {"status": "running", "job_id"} contract, the per-hour price with minimum and free-failed-downloads policy, and the `flags` guard behavior for Whisper hallucinations. It does not explain why the tool carries destructiveHint=true or what state a call leaves behind, which is the remaining gap given the annotations already cover readOnly/openWorld/idempotency.

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?

Purpose and usage are front-loaded in the first two sentences, and the remaining length is spent on output shape, which is justified because there is no output schema. The single long run-on sentence enumerating fields is dense but each clause carries distinct information; a bulleted return-value structure would read better.

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 compensates fully by enumerating text, segments, per-word timings, confidence, `spk`, `turns`, `speakers` with talk time and evidence quotes, SRT/VTT, and `flags`. Combined with async handling and pricing, an agent has everything needed to call it and interpret the result.

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%, so the schema already fully documents `url` and `language`. The description adds no syntax, format, or constraint detail for either parameter, so baseline 3 applies; the media-format and 3-hour limits live in the schema, not the description.

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 first sentence gives a specific verb and resource ("Transcribe speech in an audio or video file") and the second narrows the use cases to words, timed quotes, speaker attribution, or subtitles. An agent can tell this apart from get_job_result (which is explicitly named as the polling follow-up) and from listen_clip without opening a schema.

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

Usage Guidelines4/5

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

It states clearly when to reach for it ("Use it when you need the words in a recording, quotes with their time, who said what, or subtitles") and routes the async case to get_job_result. There is no explicit when-not guidance (e.g. how it differs from listen_clip for short clips or from research), so it falls short of a 5.

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

All Patchwell toolsInspect
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.

Resources