Skip to main content
Glama
Sign In
Tapra MCP server

Tapra MCP server

Official
by tapra-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Who spoke when

diarize_audio

Identify who speaks when in an audio or video file and return each speaker turn with start and end times, without generating a transcript.

Instructions

Find speaker turns in an audio or video file (no transcript). Returns each turn with its speaker and times. Costs money per minute.

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": {
      "input_path": "<input_path>"
    },
    "name": "diarize_audio"
  }
}

Input Schema

NameRequiredDescriptionDefault
input_pathYesPath to the audio or video file.
output_pathNoSave the turns as JSON here.
max_cost_tndNoRefuse to run if the estimated cost is above this many TND. Defaults to TAPRA_MAX_COST_TND when set.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.2/5.0
Behavior4/5

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

Goes beyond the annotations by disclosing the per-minute monetary cost and the shape of the result (each turn with speaker and times) — neither is available from readOnlyHint/openWorldHint/idempotentHint. It does not describe what output_path does to an existing file, but destructiveHint=false already covers the safety profile.

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 short sentences, zero filler, with the core purpose first, the return shape second, and the cost warning last. Every sentence earns its place.

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 sentence about returning speaker turns and times carries the return-value burden well, and the cost note covers the main risk of an openWorld, non-idempotent operation. Minor gap: it doesn't mention that results can be persisted to output_path, which is a documented parameter.

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 all three parameters (input_path, output_path, max_cost_tnd, including the env-var default) are already documented in structured data. The description adds no parameter-level detail beyond restating that the input is an audio/video file, so the baseline 3 applies.

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 ('Find speaker turns') and resource ('audio or video file'), and the parenthetical '(no transcript)' immediately separates it from the transcribe/speech_to_text siblings. An agent can route to it without opening a schema.

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?

The '(no transcript)' qualifier implicitly tells the agent when this tool is the right choice versus transcription tools, and 'Costs money per minute' flags a decision-relevant precondition. However, no sibling is named explicitly and no when-not-to-use rule is given (e.g. 'use speech_to_text if you also need words').

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