Skip to main content
Glama

ninerouter_transcribe_audio

Convert base64-encoded audio into text by uploading it through 9Router with a multipart request, supporting language hints, prompts, and custom response formats.

Instructions

Transcribe inline base64 audio through 9Router using a multipart upload.

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": {
      "model": "<model>",
      "file_base64": "<file_base64>"
    },
    "name": "ninerouter_transcribe_audio"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYes
promptNo
optionsNo
filenameNoaudio.wav
languageNoLanguage hint for models that support it. Omit for cx/transcribe.
mime_typeNoaudio/wav
file_base64Yes
response_formatNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.6/5.0
Behavior2/5

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

Annotations already declare the mutation-safe profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), so the bar is lower, but the description adds little beyond restating the transport. It never says what comes back (transcript text versus a structured object), whether long audio is truncated or times out, what error behavior looks like on oversized payloads, or that requesting a transcription is billed/rate-limited.

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?

A single front-loaded sentence with no filler and no redundancy. It is efficient, though its brevity borders on under-specification for a tool with eight parameters and a nested object.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and only 13% schema coverage on eight parameters, the description must carry nearly everything and instead covers only the encoding and transport. An agent cannot tell what the response looks like, what `response_format` does, or how `options` is consumed, making this inadequate for the tool's actual complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 13% across 8 parameters, including a nested free-form `options` object, so the description carries heavy burden and mostly fails it. "Inline base64 audio" maps loosely to the required `file_base64`, but nothing is said about `model`, `prompt`, `language` (whose own schema note about cx/transcribe is the only real hint), `response_format`, `mime_type`, or the key/value semantics of `options`.

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?

"Transcribe inline base64 audio" gives a specific verb and resource, and the phrase "inline base64" plus "multipart upload" distinguishes it from a URL-based or file-handle transcription path. It does not name a sibling such as ninerouter_text_to_speech as the inverse operation, but the purpose itself is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to choose this tool over alternatives, no prerequisites, and no mention of practical constraints such as base64 payload size limits or which of the sibling model-listing tools to consult first. The agent must infer all usage context from the schema.

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