Skip to main content
Glama

openFlow

by io.github.molkex
OverviewDiscussionsAdmin

generate_voice

Speak text aloud with a Gemini TTS voice and return a WAV (24 kHz, mono, 16-bit).

Takes ~15-25 seconds for up to 300 characters. Costs no image/video quota. Russian,
English and most other languages work; the voice name only sets the timbre.

text: what to say, up to 5000 characters. Google's TTS itself takes at most 500
  characters (about 30 seconds of speech) per request, so text longer than 300
  characters is split at sentence boundaries, spoken piece by piece and joined into
  ONE WAV — about 30 seconds of waiting per 1000 characters; the result then also has
  `chunks` and `media_ids`. A lone word or a fragment that reads like an instruction
  ("in a modern style.") may still be refused: give it a full sentence.
voice: one of list_voices() (default "Algieba").
style: optional delivery hint, e.g. "calm, slow" or "cheerful". Empty = neutral.
project_id: optional, a project from create_project; omit for the account's default.
include_preview: also return `wav_preview_b64`, the FIRST 8 KB of the file as base64.
  Off by default: it is only the first fraction of a second and costs context. To get the
  whole file open `download_url`, or call fetch_media(path=download_path, force_bytes=True).

Returns {audio_url, download_url, download_path, media_id, duration_sec_estimate,
size_bytes, voice} — `audio_url` is Google's signed link and EXPIRES, `download_url`
is ours. While still rendering, returns a job_id: call check_job.
idempotency_key: optional, any string unique to this logical request (e.g. a uuid).
  Repeating a call with the same key within 24h returns the SAME job instead of a
  new one — use it when you may retry after a timeout or a busy error.

Input Schema

NameRequiredDescriptionDefault
textYes
styleNo
voiceNoAlgieba
project_idNo
idempotency_keyNo
include_previewNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Idempotency Key"
+}
  2. Added

TDQS

A4.7/5.0
Behavior4/5

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

Annotations only declare the generic write/openWorld profile; the description adds substantial non-schema context: ~15-25s latency, no image/video quota cost, 500-char per-request engine limit causing chunked synthesis, possible refusal of fragments, and the fact that `audio_url` is an EXPIRING signed link while `download_url` is stable. Didn't reach 5 only because a few behaviors (failure modes beyond refusal, rate limits) are unstated.

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 the core action, then parameter-by-parameter — good structure. It is dense and long, but given 0% schema coverage and no output schema nearly every clause carries information; only the repeated warnings about char limits could be trimmed.

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 enumerates the return fields (audio_url, download_url, download_path, media_id, duration_sec_estimate, size_bytes, voice, plus chunks/media_ids for long text) and covers the async case by naming the job_id → check_job path. Nothing needed to call it correctly is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden and does: every one of the six parameters is explained with semantics the schema lacks — text's 5000-char cap plus 500/300-char splitting thresholds, voice default, style examples, project_id source, include_preview's 8 KB meaning and cost, and idempotency_key's 24h dedupe window.

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?

Opens with a specific verb+resource ('Speak `text` aloud with a Gemini TTS voice') and immediately states the exact output format (WAV, 24 kHz, mono, 16-bit). An agent can distinguish this from generate_video, music_generate, or chat_* siblings without opening any 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?

Explicitly routes to alternatives and conditions: 'call fetch_media(path=download_path, force_bytes=True)' for the whole file, 'call check_job' while rendering, 'list_voices()' for valid voice names. Also warns when *not* to rely on include_preview ('costs context').

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

All openFlow 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