Skip to main content
Glama

generate_subtitles

Transcribe video audio into .srt subtitles using local whisper.cpp or the OpenAI API, then return the generated subtitle file path.

Instructions

Generate subtitles for a video using whisper. Mode 'local' uses bundled or supplied whisper.cpp; mode 'api' uses OpenAI. Returns the path of the generated .srt file.

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": {
      "video": "<video>"
    },
    "name": "generate_subtitles"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoTranscription mode (auto-detected from arguments if omitted)
modelNoPath to whisper model (local mode; auto-detects bundled if omitted)
videoYesPath to the video file
api_keyNoOpenAI API key (api mode)
whisperNoPath to whisper-cli (local mode; auto-detects bundled if omitted)
output_dirNoOutput directory for the .srt file

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 local mode relies on bundled or supplied whisper.cpp, that api mode calls OpenAI (implying network use and a credential), and that the result is a written .srt path. It omits operational traits that matter for a long-running transcription job — expected duration, overwrite behavior on an existing output file, and failure modes — which keeps it from a 5.

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?

Three tight sentences: action first, mode semantics second, return value last. Every sentence adds distinct information and nothing is repeated from the schema verbatim.

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, and the description compensates by stating the return value precisely ('the path of the generated .srt file'). Combined with full parameter coverage in the schema and mode/dependency disclosure, an agent has enough to invoke it correctly; only runtime, error, and overwrite behavior are unaddressed.

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 description coverage is 100%, so the baseline is 3. The description adds some meaning beyond the schema by explaining what 'local' and 'api' actually entail (bundled whisper.cpp vs OpenAI), but it says nothing extra about whisper, model, api_key, or output_dir beyond what the schema already documents.

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 ('Generate subtitles for a video') plus the underlying engine (whisper), which cleanly separates it from find_subtitles, get_subtitles, translate_subtitles, and download_subtitle. It never explicitly names those siblings or says how it differs from them, so it stops short of a 5.

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?

The description explains the two execution modes (local vs api) and that mode is auto-detected when omitted, which is genuine selection guidance at the parameter level. However, it gives no tool-level when-to-use framing — nothing says to use this only when no subtitle exists yet, or to prefer get_subtitles/find_subtitles for already-existing subtitles.

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

Deploy Server

Other Tools