MoneyTools Transcripts

Transcribe audio to text + subtitles

speech_transcribe

Generate a value-added transcript with timestamped segments, SRT/VTT, language detection, word count and duration (optional summary). 0.002 USDC/started minute (min 0.003); 3 free/day. Pass url, upload_id (from speech_upload_url), or audioBase64 — WAV/MP3/M4A/MP4/WebM/OGG/FLAC you have the right to process. Platform pages refused. Max 10 min / 25 MB. Price = max(declared, parsed, 16 kbps floor).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "speech_transcribe"
  }
}

Input Schema

Name	Required	Description
`url`	No	HTTPS direct media file URL you have the right to process (audio/* or video/*; MP3/M4A/MP4/WebM/WAV/…). Not a YouTube/Instagram/TikTok/Facebook/X/Vimeo page.
`minutes`	No	Declared duration hint in minutes.
`summary`	No	If true, include a short 1–3 sentence summary.
`language`	No	Optional language hint (e.g. en, zh). If omitted we detect language.
`uploadId`	No	upload_id from speech_upload_url after a successful PUT (single-use).
`audioBase64`	No	Base64-encoded audio bytes (alternative to url/uploadId).
`durationSeconds`	No	Declared duration hint in seconds (cannot underprice; we parse the file).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Although annotations already flag openWorldHint=true and idempotentHint=false, the description adds real operating context: per-started-minute pricing, a 3 free/day allowance, a minimum charge, a price formula that cannot be gamed by understating duration, single-use upload IDs, and refusal of platform pages. That materially exceeds what the annotations convey.

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?

Front-loaded with the deliverable before pricing and constraints, and no sentence is filler. The pricing story is split awkwardly across two locations ('0.002 USDC/started minute (min 0.003)' and 'Price = max(declared, parsed, 16 kbps floor)'), which reads as slight compression rather than elegant structure.

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?

With no output schema, the description carries the return-value burden and does so by naming the transcript artifacts and optional summary. It covers inputs, billing, and limits for a paid, open-world job. Minor gaps remain around failure/partial-result behavior and how the subtitle artifacts are surfaced in the response.

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 all seven parameters; the baseline is 3. The description does add meaning about the mutual exclusivity of url/upload_id/audioBase64 and the fact that declared minutes act only as a hint subject to the max(declared, parsed, floor) rule. That is incremental value on top of an already-complete schema.

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?

The description opens with a concrete verb+resource ('Generate a value-added transcript') and enumerates the outputs: timestamped segments, SRT/VTT, language detection, word count, duration, optional summary. It also establishes the input linkage to speech_upload_url via upload_id. It stops short of differentiating itself from sibling speech_quote, which covers cost estimation.

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?

Usage is clear: pass url, upload_id, or audioBase64, with accepted formats and hard limits (10 min / 25 MB) spelled out. The exclusion of platform pages (YouTube/TikTok/etc.) is stated explicitly and reinforced by the schema. It does not say when to prefer speech_quote over calling this directly to price a job.

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

All MoneyTools Transcripts tools Inspect

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

Need Help?