Skip to main content
Glama

Transcribe audio/video to subtitles

transcribe
Idempotent

Generate SRT, VTT, TXT, JSON, or ASS subtitles and text from local audio or video files on your own GPU, with language detection and optional English translation.

Instructions

Transcribe a local audio or video file into subtitles / text.

file_path: absolute path to the media file (mp4, mkv, mov, mp3, wav, m4a, ...). language: ISO code such as en, th, ja, es, hi — or "auto" to detect. accurate: slower, fewest errors (large-v3 with beam search, or the best fine-tune for Thai / Hindi). formats: comma list from srt, vtt, txt, json, ass (ass = karaoke word highlight). output_dir: folder for the output files; empty = next to the media file. vocabulary: names and terms to spell correctly, e.g. "Pitakpong, babelscribe" (whisper initial prompt); empty = none. translate: true = write the transcript translated to English (uses large-v3; slower than turbo). Returns the files written, detected language, device used, and the transcript text.

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

Input Schema

NameRequiredDescriptionDefault
formatsNosrt,txt
accurateNo
languageNoauto
file_pathYes
translateNo
output_dirNo
vocabularyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.4.0
    • addedInput schema / properties / translate
      Added value: +{
      +  "default": false,
      +  "title": "Translate",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / vocabulary
      Added value: +{
      +  "default": "",
      +  "title": "Vocabulary",
      +  "type": "string"
      +}
  2. First observedv0.3.2

TDQS

A4.2/5.0
Behavior4/5

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

Annotations declare non-read-only, non-destructive, idempotent, open-world, so the description's job is to add detail — and it does: it discloses that files are written to disk, where they go, that 'accurate' is slower (large-v3 with beam search), that 'translate' is slower than turbo, and what is returned (files, detected language, device, transcript). Remaining gaps are modest: no mention of overwrite behavior when output files already exist.

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?

The one-line purpose is front-loaded, followed by a parameter-keyed list, so scanning is fast and each line conveys distinct information. It is dense rather than padded, though the parenthetical asides (model names, whisper initial prompt) add minor length without changing how the tool is called.

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, but the description explicitly enumerates the return payload, and it explains the two most consequential behavioral choices (accuracy vs speed, translation). For a seven-parameter media tool it is nearly self-sufficient, with only edge cases like existing-file handling or supported device selection left implicit.

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 description coverage is 0% and there are no enums, so the description carries the entire burden — and it does so for all seven parameters, including the closed value set for 'formats' (srt, vtt, txt, json, ass with the ass karaoke meaning), acceptable language code style plus 'auto', and the empty-string conventions for output_dir and vocabulary.

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?

First sentence states a specific verb and resource: 'Transcribe a local audio or video file into subtitles / text.' It also scopes input to local media files and names the output artifacts, which cleanly separates it from siblings like find_media (locating files) and list_devices (hardware enumeration).

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 input description (you must already know the absolute path to a media file), and 'accurate' vs default gives a clear speed/quality tradeoff. However, there is no explicit guidance on alternatives — e.g., pointing at list_languages_and_models to discover supported languages or models, or list_devices to see which device will be used, which the description mentions only in the return value.

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