Skip to main content
Glama

Agent Data Tools: Speech to text and text to speech

Cheap text to speech: up to 2,000 characters in English as one MP3

text_to_speech_lite
Read-only

Low-cost text to speech for longer English text: up to 2,000 characters as one MP3 (base64) with Deepgram Aura-1, 12 voices. Half the price per character of text_to_speech, with a slightly less natural voice. Pick a voice by name or leave the default. Use for narration drafts, read-aloud of articles and summaries, notifications and accessibility at volume; for the most natural voices or Spanish use text_to_speech. Example: text=Your order has shipped and should reach you within three working days.. Price $0.04/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

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": {
      "text": "<text>"
    },
    "name": "text_to_speech_lite"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesText to speak, up to 2,000 characters
voiceNoVoice name: angus, asteria, arcas, orion, orpheus, athena, luna, zeus, perseus, helios, hera, stella. OpenAI voice names map to the nearest one. Default: luna

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and idempotentHint=false; the description adds value beyond them with per-call pricing ($0.04/call), the payment paths (x402 USDC or a card key via /credits), the fact that failed calls are free, and the warning that repeats are not free. It does not describe latency, error payloads, or how partial failures surface, but for a stateless conversion call the disclosure is strong.

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 cost, limit, format and engine, and every sentence carries either a constraint or a routing cue. Slight bloat from the pricing/payment sentence and the example (which ends with a stray double period), but nothing is genuinely wasted.

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 correctly tells the agent the return is base64 MP3, and it covers cost, billing key options, failure billing, and length limits. Combined with annotations that cover the safety profile, an agent has everything needed to call this correctly.

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%, with both `text` and `voice` documented including the twelve voice names and the luna default, so the structured field already carries the semantics. The description only adds 'pick a voice by name or leave the default' and the character ceiling, which is a small increment. Baseline 3 is appropriate.

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 and resource (low-cost text to speech), the exact output format (one MP3, base64), the engine (Deepgram Aura-1), the limit (2,000 characters), and the language (English). It also names the sibling it differs from (text_to_speech) and the trade-off (half the price, slightly less natural voice), so an agent can select it 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 Guidelines5/5

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

Explicit positive cases are given (narration drafts, read-aloud of articles and summaries, notifications, accessibility at volume) and an explicit exclusion routes the agent elsewhere: 'for the most natural voices or Spanish use text_to_speech'. Both the when and the when-not are present.

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.