Skip to main content
Glama
Sign In

Doseedo: Film Scoring, AI Instruments, Sound Effects & Stems

by com.doseedo
OverviewDiscussionsAdmin

Generate sound effects (SFX & foley)

doseedo_generate_sound

SOUND EFFECTS (SFX) from words with Stable Audio Open — SOUND DESIGN and FOLEY for game audio, apps and video: impacts, whooshes, door slams, footsteps, UI blips, creature and sci-fi sounds, ambiences ("rain on a tin roof", "busy café"), risers, drum one-shots. A one-shot hit ("punchy house kick", "snare with a short room", "a riser into the drop"), a loop on the tempo grid ("glitchy percussion"), or a texture ("vinyl crackle", "rain"). kind picks which (hit | loop | texture); omitted, the server reads it off the words. Don't put a tempo in a hit's prompt — tempo words make it write a loop. Wrong tool for a part with notes (doseedo_render_midi) or a piece of music (you write it; doseedo_render_score plays it). Async: job_id → doseedo_wait_task (typically 15–40 s) → audio URLs (pre-signed: curl -OJ , no auth header, valid 24 h). Cancel: a render that has not reached the GPU yet is stopped and its credits refunded; one already rendering finishes on the GPU (its credits are spent), the job ends as canceled and the output is discarded.

Input Schema

NameRequiredDescriptionDefault
bpmNoTempo a loop is cut to (default 120).
kindNohit = one sound (0.5–10 s), loop = 1–4 bars tiled at bpm, texture = a bed. Default: read off the prompt.
nameNoOptional: a name for this job's files, e.g. "rainy-loop-3". Every file it returns downloads as <name>_<part>.<ext> (rainy-loop-3_Celesta.wav, rainy-loop-3_rough-mix.wav; one take: rainy-loop-3.wav), so the user can find them. Give each job its own name (a second take: "rainy-loop-3b"). Default: doseedo-<last 6 characters of the job id>.
seedNoOptional random seed for reproducibility.
promptYesWhat it sounds like, e.g. "punchy house kick drum, single hit" or "dusty vinyl crackle". ≤ 300 characters (a longer one is cut at a word boundary, with a warning).
time_signatureNoMeter a loop is cut to, e.g. "4/4" (default).
idempotency_keyNoOptional. Any unique string for THIS request (e.g. a UUID). Re-sending the same call with the same key after a timeout returns the same job instead of starting a second one.
duration_secondsNoLength in seconds. Default: 2 s for a hit, 4 bars at bpm for a loop, 8 s for a texture.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / prompt / description
      Previous value: -"What it sounds like, e.g. \"punchy house kick drum, single hit\" or \"dusty vinyl crackle\". ≤ 300 characters."New value: +"What it sounds like, e.g. \"punchy house kick drum, single hit\" or \"dusty vinyl crackle\". ≤ 300 characters (a longer one is cut at a word boundary, with a warning)."
    • addedInput schema / properties / prompt / maxLength
      Added value: +300
  2. Changed1 schema field changed
    • addedInput schema / properties / name
      Added value: +{
+  "description": "Optional: a name for this job's files, e.g. \"rainy-loop-3\". Every file it returns downloads as <name>_<part>.<ext> (rainy-loop-3_Celesta.wav, rainy-loop-3_rough-mix.wav; one take: rainy-loop-3.wav), so the user can find them. Give each job its own name (a second take: \"rainy-loop-3b\"). Default: doseedo-<last 6 characters of the job id>.",
+  "maxLength": 80,
+  "type": "string"
+}
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing the async contract (job_id → doseedo_wait_task, typically 15–40 s), the return form (pre-signed audio URLs, usable with curl -OJ and no auth header, valid 24 h), and precise cancellation economics — refunded if not yet on the GPU, credits spent and output discarded if already rendering. The idempotency_key parameter is consistent with idempotentHint=false: dedupe is opt-in, not a property of the tool.

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 purpose, then the kind rule, then the wrong-tool routing, then the async/cancel contract — a sensible order with no filler sentences. It is densely packed with parenthetical example lists, which is scannable but pushes toward the upper bound of useful length.

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 non-read-only, open-world, async generation tool with no output schema, the description supplies everything an agent needs: what gets produced, how long it takes, which follow-up tool completes the job, what the URLs look like and how long they live, and what cancel does to credits and output.

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 already 100%, so the schema carries most parameter meaning; the description still adds the non-obvious coupling between prompt wording and kind inference, plus the hit/loop/texture behavioral distinction that the enum description only sketches. It does not, however, add anything for bpm, time_signature, seed, or idempotency_key beyond what the schema says.

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 ("Generate sound effects (SFX) from words with Stable Audio Open") and enumerates concrete output families — impacts, whooshes, footsteps, UI blips, ambiences, risers, one-shots. It also draws a hard boundary against the nearest siblings by naming doseedo_render_midi for note parts and doseedo_render_score for scored music.

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 when-to-use (SFX/foley for games, apps, video), explicit when-not (parts with notes or composed music, each routed to a named alternative), and a practical selection rule for the kind parameter (hit vs loop vs texture, with the server inferring it if omitted). It even includes a concrete anti-pattern — don't put tempo words in a hit prompt or the model writes a loop.

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

All Doseedo: Film Scoring, AI Instruments, Sound Effects & Stems 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