Skip to main content
Glama
Sign In
Hermoso

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Generate voiceover

generate_voice

Convert a script into spoken audio using a chosen voice and return the MP3 URL for standalone voiceover or narration.

Instructions

RAW text-to-speech from the voice-model catalog: speak a script in a chosen voice and return the served MP3 URL. For a standalone voiceover / narration clip — NOT for adding audio to a video (render_ad and generate_video voice their own spots; change_voice re-voices a finished clip). engine picks the voice model (default 'seed-audio'; also 'eleven-v4' (Eleven v4; the retired id 'eleven-v3' still answers, on v4), 'minimax-speech', 'kokoro'); voice is a preset name from that engine (see hermoso_capabilities -> voice engines) — a name that engine does not have is REFUSED for free with its real list, and a few engines generate their own voice and take no preset at all (the reply says which voice actually spoke). Paid (priced by length: hermoso_capabilities lists each voice engine's credits per 1,000 characters; ≤900 characters).

Input Schema

NameRequiredDescriptionDefault
textYesthe script to speak (≤900 characters)
voiceNoa voice preset from the chosen engine (e.g. 'Aria'/'George' on eleven-v4, 'stokie_en' on seed-audio) — omit for the engine default
engineNovoice-engine id: 'seed-audio' (default), 'eleven-v4' (Eleven v4), 'minimax-speech', or 'kokoro' — listed in hermoso_capabilities

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.435
    • changedInput schema / properties / engine / description
      Previous value: -"voice-engine id: 'seed-audio' (default), 'eleven-v3', 'minimax-speech', or 'kokoro' — listed in hermoso_capabilities"New value: +"voice-engine id: 'seed-audio' (default), 'eleven-v4' (Eleven v4), 'minimax-speech', or 'kokoro' — listed in hermoso_capabilities"
    • changedInput schema / properties / voice / description
      Previous value: -"a voice preset from the chosen engine (e.g. 'Aria'/'George' on eleven-v3, 'stokie_en' on seed-audio) — omit for the engine default"New value: +"a voice preset from the chosen engine (e.g. 'Aria'/'George' on eleven-v4, 'stokie_en' on seed-audio) — omit for the engine default"
  2. Changed1 schema field changedv0.1.161
    • changedOutput schema / (root)
      Previous value: -{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "additionalProperties": false,
-  "properties": {
-    "audio": {
-      "description": "the served absolute URL of the MP3 voice clip",
-      "type": "string"
-    },
-    "creditsUsed": {
-      "description": "credits billed for this clip",
-      "type": "number"
-    },
-    "model": {
-      "description": "the voice engine label",
-      "type": "string"
-    },
-    "voice": {
-      "description": "the voice preset used",
-      "type": "string"
-    }
-  },
-  "type": "object"
-}New value: +null
  3. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare it is a write, non-idempotent, open-world call. The description supplies the genuinely costly facts: paid pricing by length, a ≤900-character cap, that an invalid voice name is REFUSED for free with the real list returned, that some engines synthesize their own voice and take no preset, and that the reply reports which voice actually spoke.

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?

The key distinction and the return value are front-loaded and every clause carries information, but the body is one dense block riven with nested parentheses, which makes the per-engine caveats harder to scan than they need to be.

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?

For a 3-parameter generation tool with no output schema, the description covers the return value (served MP3 URL), cost model, length limit, defaults, and error behavior — everything needed to call it correctly the first time.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description still adds semantics beyond the schema by naming 'seed-audio' as the default engine, explaining the failure mode for an unmatched voice preset, and noting engines that accept no preset.

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 ('RAW text-to-speech ... speak a script in a chosen voice and return the served MP3 URL') and immediately distinguishes itself from three siblings by name (render_ad, generate_video, change_voice) with the reason each differs.

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 when-to-use ('standalone voiceover / narration clip') and when-not ('NOT for adding audio to a video'), with the alternatives that cover the excluded case. The agent can route without opening any schema.

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

Deploy Server

Other Tools