Skip to main content
Glama

generate_audio

Generate voiceovers, background music, songs, or sound effects from text or prompts, then save the audio locally.

Instructions

Generate audio (voiceover, background music, a song or a sound effect) and save it locally.

text_or_prompt: for "voice" the text to speak; for "music"/"song"/"sfx" a description of the sound. model: "voice" (text to speech), "music" (instrumental background), "song" (sung, needs lyrics) or "sfx". aspect: the voice for "voice" (e.g. "Deep narrator", "Warm female"), the mood for "music" (e.g. "Cinematic", "Lo-fi"), the vocal for "song" ("Female vocal", "Male vocal", "Duet"); defaults to the first choice. See list_models(kind="audio"). option: length/duration, e.g. "300 chars" for voice, "30s" for music, "60s" for song, "5s" for sfx; defaults to the first. lyrics: song lyrics, required for "song".

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_or_prompt": "<text_or_prompt>"
    },
    "name": "generate_audio"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNovoice
aspectNo
lyricsNo
optionNo
text_or_promptYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.5

TDQS

A4/5.0
Behavior3/5

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

With no annotations, the description must carry behavior and does disclose real traits: output is saved locally, 'lyrics' is conditionally required for 'song', and several parameters default to the first available choice if omitted. It does not say where the file is written, whether generation is paid/slow (a get_balance and job_status sibling hint at cost and async behavior), or what happens on invalid model/aspect combinations.

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 purpose sentence followed by a per-parameter block that maps one-to-one onto the schema, so nothing is wasted structurally. The aspect line's example lists are slightly padded, but each line earns its place.

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 five-parameter generative tool with an output schema (so return format needn't be explained) and no annotations, the description covers modality selection, per-mode parameter meaning, defaults, and conditional requirements. The main residual gap is what 'save it locally' concretely means — path or filename — which an agent may need before invoking.

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%, yet the description defines all five parameters in prose: text_or_prompt's meaning per model, the four model values, aspect semantics plus examples and default, option formats per mode ('300 chars', '30s', '60s', '5s') plus default, and lyrics' conditional requirement. It effectively supplies the missing enum vocabulary that the schema lacks.

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 ('Generate audio') and enumerates the four modalities it covers (voiceover, background music, song, sound effect), plus the side effect of saving locally. The resource is unmistakably distinct from siblings generate_image and generate_video.

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?

Usage is implied rather than stated: the model values ('voice' for TTS, 'music' for instrumental background, 'song' for sung, 'sfx') implicitly tell an agent which mode fits an intent, and it points to list_models(kind="audio") for valid aspect values. There is no explicit when-not guidance or comparison against alternatives such as generate_image/generate_video beyond the obvious modality split.

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