Skip to main content
Glama

Kubeez

generate_sound

PRE-FETCH (mandatory for the video models): resources/read kubeez://skills/media-upload AND kubeez://skills/billing-confirmation. Every model here bills PER SECOND and Kubeez has no refunds — quote with estimate before you fire.

Scope: generate:media. Sound effects and music, either from a sentence or written against a clip you already have. NOT for songs with vocals — that is generate_music (Suno).

PICK BY WHAT YOU HAVE: You have a sentence: sonilo-text-to-sfx one described sound effect. 1-180s, default 5s. 3s billing floor. sonilo-text-to-music an instrumental track. 5-360s, default 60s. 10s billing floor. You have a clip (video_url REQUIRED, https, up to 360s): sonilo-video-to-sfx effects matched to the picture, as a bare audio track sonilo-video-to-music a score written to the cut, as a bare audio track sonilo-video-to-sound both, mixed, as a bare audio track sonilo-video-to-video-sfx same as above but returns the CLIP with the sound in it sonilo-video-to-video-music same, muxed sonilo-video-to-video-sound same, muxed Prefer a -video-to-video-* id when the user wants a finished clip back; prefer the bare audio ids when they will mix it themselves in an editor.

PROMPTS: pass prompt and it is folded into the field that model reads. The two *-sound models write effects AND music, so they take music_prompt and sfx_prompt separately and reject a lone prompt. Max 2000 chars each. A video run with no prompt at all is valid — the model writes to what it sees.

BILLING: per second of the CLIP, not of the output, and each product carries the provider's OWN minimum billable length: 10s on anything that writes MUSIC (both mixed *-sound ids included), 3s on the effects-only ids. A 6s score bills 10s; a 2s effect bills 3s. estimate(model=..., reference_video_seconds=) applies it.

CLIP LENGTH: a video run bills the clip's length as the SERVER measures it, so the clip must be a Kubeez upload (get_upload_url) or one of your own Kubeez generations; any other URL is refused. duration_seconds does not change the bill on a video run.

LOCAL FILE: get_upload_url(model_id='sonilo-video-to-video-sfx') → upload → get_upload_session(token) → pass the returned URL as video_url. Its media[].duration_seconds is the measured length, for an exact estimate.

ASYNC: returns {generation_id, status:'pending'}. Poll get_status(generation_id). Sonilo has NO provider callback, so the poll is also what settles the run — keep polling until the status is completed or failed, or the credits stay reserved.

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": {
      "model": "<model>"
    },
    "name": "generate_sound"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYes
promptNo
duckingNo
video_urlNo
sfx_promptNo
music_promptNo
preserve_speechNo
duration_secondsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare non-readonly, open-world, non-idempotent; the description adds the material behavior: per-second billing with no refunds, provider minimum billable lengths (10s music / 3s effects), billing based on clip length as the server measures it, URL restrictions (must be a Kubeez upload or generation), and async polling that also settles credits. That last point — credits stay reserved if you stop polling — is exactly the kind of non-obvious trait an agent cannot get from structured fields.

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 prerequisites and a readable model table; nearly every sentence carries information. The billing rules are restated across BILLING and CLIP LENGTH sections, and the example billings could be tightened without losing meaning.

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 multi-model generation tool with async semantics, the description covers prerequisites, model selection, prompt handling, billing, input validation, upload workflow, and polling. Return shape is briefly noted and an output schema exists, so nothing essential is missing apart from the two boolean flags.

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 0% across 8 params, and the description compensates for most of them: prompt folding, the music_prompt/sfx_prompt split and its rejection of a lone prompt, 2000-char limit, video_url https/360s constraints, and the note that duration_seconds does not affect the bill on a video run. ducking and preserve_speech are left completely unexplained in both schema and description, which is why this is not a 5.

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 plus scope (generate:media) and explicitly excludes the sibling case: 'NOT for songs with vocals — that is generate_music (Suno).' The model routing table makes it unambiguous which operation an agent is invoking.

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?

Gives explicit selection criteria: 'PICK BY WHAT YOU HAVE' splits sentence-based vs clip-based models, and it adds a decision rule for bare-audio vs muxed output ('prefer a -video-to-video-* id when the user wants a finished clip back'). It also states mandatory pre-fetch steps and that estimate should be run before firing.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources