Skip to main content
Glama

Align two audio files into sentence pairs

align_audio

Given two publicly reachable audio URLs (same content in two languages), transcribes both with Whisper and aligns them semantically into sentence pairs with timestamps and a similarity score. Use this when the user already has recordings rather than text. Free tier limits apply (2 runs / 20 min per day anonymous, ≤10 min combined per run).

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": {
      "audio_a_url": "<audio_a_url>",
      "audio_b_url": "<audio_b_url>"
    },
    "name": "align_audio"
  }
}

Input Schema

NameRequiredDescriptionDefault
lang_aNozh
lang_bNoen
audio_a_urlYesPublic https URL of the first audio file (mp3/m4a/wav, ≤50MB).
audio_b_urlYesPublic https URL of the second audio file.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations cover the safety profile (not read-only, open-world, non-destructive), and the description adds real context beyond that: audio must be publicly reachable, processing uses Whisper, and there are concrete rate limits (2 runs / 20 min per day anonymous, ≤10 min combined per run). The notable gap is execution behavior for a potentially long job — the agent is not told whether the call blocks, streams progress, or returns a job handle, which matters for multi-minute audio.

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 sentences, each doing distinct work: what it does and returns, when to choose it, and operating limits. The core verb-and-resource leads, and nothing is repeated from the schema or annotations.

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 correctly spells out the return shape — sentence pairs with timestamps and a similarity score. For a 4-parameter, open-world media-processing tool it is nearly sufficient; the missing pieces are the execution model for long audio and the undocumented second URL's constraints.

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 only 50%, so the description needs to carry weight. It adds the 'publicly reachable' access constraint and the same-content-in-two-languages framing that gives meaning to the lang_a/lang_b pair. However, it says nothing about lang_a and lang_b themselves — which one is the source, why the defaults are zh/en, or whether mismatched languages fail — and audio_b_url has no format/size constraint anywhere.

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 gives a specific pipeline: fetch two public audio URLs, transcribe both with Whisper, align them semantically into sentence pairs with timestamps and a similarity score. That is far more than a restatement of the name. It stops short of naming a sibling outright, distinguishing itself only implicitly via 'the user already has recordings rather than text' as opposed to text-based tools like translate_lines or create_bilingual_audio.

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 a clear selection condition: use this when the user already has recordings rather than text, which is the meaningful fork against the text-oriented siblings. It also surfaces quota context so the agent knows when not to promise a run. There is no explicit exclusion naming a specific alternative tool, which keeps it below a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources