Skip to main content
Glama
Sign In

VerifyLite

by io.github.SecondShotAI
OverviewDiscussionsAdmin

Transcribe audio or video

transcribe_audio
Read-only

Speech-to-text for one audio or video file by URL, using Whisper (turbo) on a GPU. Returns the full transcript, timed segments, ready-made SRT and WebVTT captions, and the detected language; optional translation to English. Files up to 25 MB (about 25 minutes of typical MP3). Useful for captioning videos, indexing podcasts, or reading meetings. Not charged if the file can't be fetched or transcribed. Paid via x402; see list_prices.

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_audio"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesAbsolute HTTP or HTTPS URL of an audio or video file, up to 25 MB.
languageNoOptional language code, e.g. 'en'. Detected if omitted.
translateNoAlso translate the speech to English.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the real behavioral load and delivers: cost semantics ('Not charged if the file can't be fetched or transcribed'), the paid x402 mechanism with a pointer to list_prices, a concrete 25 MB size ceiling, and the model/runtime (Whisper turbo on GPU). This is materially more than the structured fields provide.

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-loads the core capability, then outputs, then limits, then use cases, then pricing — a logical progression with no filler. Every clause carries information an agent would otherwise have to guess.

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?

There is no output schema, yet the description enumerates the return payload (full transcript, timed segments, SRT and WebVTT captions, detected language), covers the size limit, the URL requirement, and the billing outcome on failure. Nothing an agent needs to invoke or interpret the call is missing.

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 documents url, language (auto-detected when omitted), and translate. The description's mentions of 'detected language' and 'optional translation to English' largely restate those schema descriptions. Baseline 3 is correct — it does not add format or edge-case detail beyond the schema.

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 verb and resource ('Speech-to-text for one audio or video file by URL') and adds the mechanism (Whisper turbo on GPU) and the artifact produced (transcript, segments, SRT, WebVTT, detected language). An agent knows exactly what this does and that it operates on a single remote file. No sibling overlap exists, so no differentiation work is needed.

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?

Gives concrete use cases ('captioning videos, indexing podcasts, or reading meetings') and a hard precondition (files up to 25 MB, ~25 minutes of MP3) plus a pointer to list_prices for the x402 payment path. It stops short of explicit when-not guidance or naming an alternative tool, so it is clear context rather than full routing guidance.

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

All VerifyLite 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