Skip to main content
Glama

Agent Data Tools: Speech to text and text to speech

Voice agent: spoken question in, spoken answer out, with memory

voice_agent
Read-only

One turn of a voice assistant: send the user's voice note (or text), your instructions and the earlier turns; get back what was heard, a short reply, the reply spoken as MP3 (Aura-2, English or Spanish) and the updated history to send next time. Speech up to 2 minutes (MP3/WAV, or 1 MB of other formats); replies up to 600 characters. Use for voice bots in Telegram or WhatsApp, phone menus, kiosks and hands-free helpers. Example: text=What time do you open on Saturday?. Price $0.05/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

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": "voice_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoAbsolute http(s) URL of the user's spoken turn (MP3/WAV up to 2 minutes, other formats up to 1 MB); or POST the file; or send text instead
langNoReply language and voice: en or es (default en)
textNoThe user's turn as text (or send audio with url or a POSTed file)
voiceNoAura-2 voice for the reply (default luna for en, aquila for es)
historyNoEarlier turns as a JSON array of {role, content}, as returned in history by the last call
instructionsNoWho the assistant is and what it knows (up to 2,000 characters)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations: cost ($0.05/call via x402 USDC or card key), failed calls free, per-call charging making repeats non-free (consistent with idempotentHint=false), input limits (2 minutes, 1 MB, 600-character replies). It also restates the no-side-effect behavior, which agrees with readOnlyHint=true and destructiveHint=false.

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-loads the round-trip contract, then limits, then use cases, then pricing. The first sentence is long and packs several facts, but each clause carries operational information an agent needs; little is filler.

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?

With no output schema, the description takes on the return-value burden and does so: transcript, short reply, MP3 audio, updated history. Limits, language options, pricing and auth are all present, which is ample for a six-parameter, multi-modal tool.

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 the schema already documents url, lang, voice, text, history and instructions in comparable detail. The description reinforces the history chaining ('the updated history to send next time') and the text-or-audio choice, but adds little syntax or format meaning beyond the schema baseline.

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 concrete verb and resource: 'one turn of a voice assistant' that takes a voice note or text plus history and returns transcript, short reply, MP3 speech and updated history. The input/output round-trip is spelled out, so it is distinguishable from plain TTS or chat tools without opening the 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?

Gives explicit use contexts (voice bots on Telegram/WhatsApp, phone menus, kiosks, hands-free helpers) and a worked example (text=What time do you open on Saturday?). It does not name a sibling alternative or state when not to use it, so it falls short of full routing guidance.

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.