Skip to main content
Glama

SoapBox Faith

by io.github.alansafahi
OverviewDiscussionsAdmin

synthesize_speech

Idempotent

Generate spoken-audio (text-to-speech) for a verse, prayer, or devotional in 50+ languages, and get back a playable audio URL. Pass BCP-47 language (e.g. en-US, es-ES, sw-KE), optional voice/gender. Results are cached. Requires an API key (audio generation has real cost).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesThe text to synthesize into speech (a verse, prayer, or short devotional).
voiceNoOptional specific Google Cloud TTS voice name; overrides the default voice for the language.
formatNoAudio container/encoding of the returned URL.mp3
genderNoPreferred voice gender when a specific voice is not named.NEUTRAL
languageNoBCP-47 language tag for the voice.en-US

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed16 schema fields changed
    • addedInput schema / properties / format / default
      Added value: +"mp3"
    • changedInput schema / properties / format / description
      Previous value: -"mp3 (default) or ogg."New value: +"Audio container/encoding of the returned URL."
    • addedInput schema / properties / format / enum
      Added value: +[
+  "mp3",
+  "ogg"
+]
    • addedInput schema / properties / gender / default
      Added value: +"NEUTRAL"
    • changedInput schema / properties / gender / description
      Previous value: -"NEUTRAL | MALE | FEMALE (default NEUTRAL)."New value: +"Preferred voice gender when a specific voice is not named."
    • addedInput schema / properties / gender / enum
      Added value: +[
+  "NEUTRAL",
+  "MALE",
+  "FEMALE"
+]
    • addedInput schema / properties / language / default
      Added value: +"en-US"
    • changedInput schema / properties / language / description
      Previous value: -"BCP-47 language code, e.g. en-US, es-ES, sw-KE (default en-US)."New value: +"BCP-47 language tag for the voice."
    • addedInput schema / properties / language / examples
      Added value: +[
+  "en-US",
+  "es-ES",
+  "sw-KE"
+]
    • addedInput schema / properties / language / pattern
      Added value: +"^[a-z]{2}-[A-Z]{2}$"
    • changedInput schema / properties / text / description
      Previous value: -"Text to speak (max 2000 chars)."New value: +"The text to synthesize into speech (a verse, prayer, or short devotional)."
    • addedInput schema / properties / text / examples
      Added value: +[
+  "For God so loved the world..."
+]
    • addedInput schema / properties / text / maxLength
      Added value: +2000
    • addedInput schema / properties / text / minLength
      Added value: +1
    • changedInput schema / properties / voice / description
      Previous value: -"Optional specific Google voice name."New value: +"Optional specific Google Cloud TTS voice name; overrides the default voice for the language."
    • addedInput schema / properties / voice / examples
      Added value: +[
+  "en-US-Neural2-D"
+]
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations, the description discloses important behavioral traits: results are cached (consistent with idempotentHint), requires an API key, and notes that audio generation has real cost. This adds valuable context that annotations alone do not convey and aligns with the non-read-only, non-destructive hints. No contradiction found.

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?

Four sentences, each with a clear purpose: the first states the core function and output, the second covers the primary input parameters, the third notes caching behavior, and the fourth explains the API key requirement and cost. No filler or redundancy; front-loaded with the main purpose.

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?

Despite having no output schema, the description tells you exactly what to expect ('playable audio URL'), covers the required input (text), key optional parameters, caching, auth, and cost. All five parameters are well-specified in the schema, and the description provides the missing operational context (cost, key) needed for a complete usage picture.

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 all five parameters in detail. The description adds only a small framing benefit (e.g., '50+ languages', 'optional voice/gender') but does not provide new semantic details beyond the schema's own parameter descriptions. This matches the baseline for complete schema coverage.

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?

The description uses a specific verb ('Generate') and resource ('spoken-audio / text-to-speech') and clearly states the output ('playable audio URL'). It also scopes the content domain ('verse, prayer, or devotional'), distinguishing it clearly from sibling tools like get_verse or search_sermons, which are text-based.

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 provides clear context on how to use the tool by mentioning the BCP-47 language tag and optional voice/gender parameters. The cost and API key requirement give practical usage guidance, though it does not explicitly name alternatives or state when not to use this tool (no TTS alternatives exist among siblings anyway).

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

All SoapBox Faith toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources