Skip to main content
Glama

tts_generate

Synthesize speech from text into the media pool and optionally add it to the timeline at the playhead or a selected audio track using preset or custom voices.

Instructions

AI Speech Generator (Studio + downloaded extra): synthesize speech (max ~350 chars per call) into the media pool and optionally onto the timeline at at (default playhead) on audio_track (0 = new track). voice: 'Female 1', 'Male 1', … or 'Custom Voice' with custom_voice_file.

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": "tts_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
atNo
textYes
pitchNo
speedNo
voiceNoFemale 1
filenameNo
variationNo
audio_trackNo
add_to_timelineNo
custom_voice_fileNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

No annotations exist, so the description carries the full burden. It does disclose the ~350-character ceiling per call and the meaning of `at` and audio_track defaults, which is genuine behavioral context. It stops short of saying what happens on failure, how the media pool asset is named, or whether a re-run duplicates audio.

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?

Two dense sentences, front-loaded with the capability and prerequisite before the parameter glossary. The ellipsis in "'Male 1', …" is slightly loose but conveys the enum intent compactly. No filler sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter tool with zero schema descriptions, no annotations, and no output schema, the definition covers the highest-risk parameters and the environment prerequisite. The remaining gap is the five unexplained tuning/placement parameters, which an agent must supply blind.

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 0% across 10 parameters, so the description must compensate and only partially does: it explains `text` (350-char cap), `at`, `audio_track` (0 = new track), `voice`, and `custom_voice_file` pairing. Five parameters — pitch, speed, variation, filename, add_to_timeline — are left with only their defaults in the schema and no meaning in prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource: 'synthesize speech ... into the media pool and optionally onto the timeline'. That is a real distinction from the insertion-oriented siblings such as audio_insert, though the description never names an alternative explicitly. The parenthetical '(Studio + downloaded extra)' also identifies the product surface.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Requirements are implied ('Studio + downloaded extra'), and defaults indicate the no-timeline path via add_to_timeline, but the description never says when to pick this over audio_insert or clips_place for getting audio onto the timeline. Usage is inferable rather than stated.

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