AetherWave Studio

Generate music (Suno)

aetherwave_generate_music

Generates AI music via Suno. Returns two tracks per submission. Default model is V6 (newest, best quality, the same default as the website). For instrumental output set instrumental: true. Music gen typically takes 30-90s - this tool polls with up to a 6-minute budget. A title is honoured with lyrics, and on an instrumental whose description fits the model style cap (200 chars on V3_5/V4, 1000 otherwise); a vocal song without lyrics is named by Suno. Transient GENERATE_AUDIO_FAILED errors are common; retry once before degrading the model version.

Returns within ~45 s. If the result has state "running" the job is still rendering: poll aetherwave_get_job with the returned taskId and kind every ~10 s. Pass wait:true ONLY if your MCP client permits tool calls longer than 60 s (most do not). Pass async:true to get the taskId back immediately without waiting.

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": {
      "prompt": "<prompt>"
    },
    "name": "aetherwave_generate_music"
  }
}

Input Schema

Name	Required	Description
`wait`	No	Block until the job finishes (up to the tool's full budget, 6-15 minutes). ONLY if your MCP client permits tool calls longer than 60 s; most abandon the call at 60 s and lose the taskId. Default false: return within ~45 s and hand back a taskId if still running.
`async`	No	Submit and return the taskId immediately without polling at all. Then poll aetherwave_get_job(taskId, kind).
`model`	No	Suno model version. Defaults to V6 (current best). All versions cost the same 20 credits.
`title`	No	Optional title for the generated tracks. Used with lyrics (defaults to the start of the description) and on instrumentals. A vocal song without lyrics gets a title from Suno instead.
`lyrics`	No	Custom lyrics. If omitted, Suno will generate lyrics from the prompt (unless instrumental=true).
`prompt`	Yes	Style/mood/topic description. E.g. 'Lo-fi ambient track, rain sounds, warm pads' or 'High-energy synthwave with driving bass'.
`audioWeight`	No	0 to 1. Weighting on the audio character of the generation. Only applies with lyrics.
`styleWeight`	No	0 to 1. How closely to follow the style description. Higher sticks to it, lower lets the model roam. Use when someone asks to stay closer to, or further from, a described sound. Only applies with lyrics or on a titled instrumental.
`vocalGender`	No	Vocal gender, 'm' or 'f'. Only applies when lyrics are supplied. Default 'm'.
`instrumental`	No	If true, no vocals. Default false.
`negativeTags`	No	Comma-separated things to AVOID, e.g. 'heavy metal, screaming, distorted guitar'. Use when someone says they do not want a particular sound. Only applies with lyrics or on a titled instrumental.
`weirdnessConstraint`	No	0 to 1. How experimental the result is. Higher is stranger and more unexpected, lower is safer and more conventional. Use when someone asks to make it weirder or more normal. Only applies with lyrics or on a titled instrumental.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 7, 2026

changedInput schema / properties / model / description

Previous value: -"Suno model version. Defaults to V5_5 (current best)."New value: +"Suno model version. Defaults to V6 (current best). All versions cost the same 20 credits."

changedInput schema / properties / model / enum

Previous value: -[
-  "V3_5",
-  "V4",
-  "V4_5",
-  "V5",
-  "V5_5"
-]New value: +[
+  "V3_5",
+  "V4",
+  "V4_5",
+  "V5",
+  "V5_5",
+  "V6"
+]

Changed4 schema fields changedNov 4, 2026

changedInput schema / properties / negativeTags / description

Previous value: -"Comma-separated things to AVOID, e.g. 'heavy metal, screaming, distorted guitar'. Use when someone says they do not want a particular sound. Only applies with lyrics."New value: +"Comma-separated things to AVOID, e.g. 'heavy metal, screaming, distorted guitar'. Use when someone says they do not want a particular sound. Only applies with lyrics or on a titled instrumental."

changedInput schema / properties / styleWeight / description

Previous value: -"0 to 1. How closely to follow the style description. Higher sticks to it, lower lets the model roam. Use when someone asks to stay closer to, or further from, a described sound. Only applies with lyrics."New value: +"0 to 1. How closely to follow the style description. Higher sticks to it, lower lets the model roam. Use when someone asks to stay closer to, or further from, a described sound. Only applies with lyrics or on a titled instrumental."

changedInput schema / properties / title / description

Previous value: -"Optional title for the generated tracks."New value: +"Optional title for the generated tracks. Used with lyrics (defaults to the start of the description) and on instrumentals. A vocal song without lyrics gets a title from Suno instead."

changedInput schema / properties / weirdnessConstraint / description

Previous value: -"0 to 1. How experimental the result is. Higher is stranger and more unexpected, lower is safer and more conventional. Use when someone asks to make it weirder or more normal. Only applies with lyrics."New value: +"0 to 1. How experimental the result is. Higher is stranger and more unexpected, lower is safer and more conventional. Use when someone asks to make it weirder or more normal. Only applies with lyrics or on a titled instrumental."

Changed2 schema fields changedOct 1, 2026

addedInput schema / properties / async

Added value: +{
+  "description": "Submit and return the taskId immediately without polling at all. Then poll aetherwave_get_job(taskId, kind).",
+  "type": "boolean"
+}

addedInput schema / properties / wait

Added value: +{
+  "description": "Block until the job finishes (up to the tool's full budget, 6-15 minutes). ONLY if your MCP client permits tool calls longer than 60 s; most abandon the call at 60 s and lose the taskId. Default false: return within ~45 s and hand back a taskId if still running.",
+  "type": "boolean"
+}

Changed4 schema fields changedAug 12, 2026

addedInput schema / properties / audioWeight

Added value: +{
+  "description": "0 to 1. Weighting on the audio character of the generation. Only applies with lyrics.",
+  "maximum": 1,
+  "minimum": 0,
+  "type": "number"
+}

addedInput schema / properties / negativeTags

Added value: +{
+  "description": "Comma-separated things to AVOID, e.g. 'heavy metal, screaming, distorted guitar'. Use when someone says they do not want a particular sound. Only applies with lyrics.",
+  "type": "string"
+}

addedInput schema / properties / styleWeight

Added value: +{
+  "description": "0 to 1. How closely to follow the style description. Higher sticks to it, lower lets the model roam. Use when someone asks to stay closer to, or further from, a described sound. Only applies with lyrics.",
+  "maximum": 1,
+  "minimum": 0,
+  "type": "number"
+}

addedInput schema / properties / weirdnessConstraint

Added value: +{
+  "description": "0 to 1. How experimental the result is. Higher is stranger and more unexpected, lower is safer and more conventional. Use when someone asks to make it weirder or more normal. Only applies with lyrics.",
+  "maximum": 1,
+  "minimum": 0,
+  "type": "number"
+}

Changed1 schema field changedAug 11, 2026

addedInput schema / properties / vocalGender

Added value: +{
+  "description": "Vocal gender, 'm' or 'f'. Only applies when lyrics are supplied. Default 'm'.",
+  "enum": [
+    "m",
+    "f"
+  ],
+  "type": "string"
+}

First observedJun 20, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations declare openWorldHint=true, non-idempotent, non-destructive; the description adds the operational traits annotations cannot express — 30–90 s generation time, ~45 s return window, a 6-minute polling budget, and common transient failures. It does not spell out that repeated submissions create separate jobs and spend credits each time, which matters for a non-idempotent 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 purpose and output count, then timing, then failure handling, then the wait/async contract. Slight redundancy with the schema's wait/async/instrumental descriptions and a dense middle sentence about title behavior, but nothing is wasted.

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 12-parameter async generation tool with no output schema, the description covers latency, polling target, failure recovery, defaults and the wait/async choice — enough to call it correctly. It stops short of describing the returned track objects or credit spend per submission, which would complete the picture.

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 the baseline is 3; the description still adds real meaning — default model and equal 20-credit pricing across versions, when a title is honored (lyrics, or instrumental within a 200/1000-char style cap) versus named by Suno, and how the style/title/lyrics combination gates other params.

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+resource ("Generates AI music via Suno") plus a concrete output expectation ("Returns two tracks per submission"), which clearly separates it from siblings like aetherwave_generate_speech, aetherwave_generate_image and aetherwave_master_audio. The default model note (V6, same as website) further pins down what the agent gets.

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 guidance on when to use wait vs async, when to poll aetherwave_get_job (and how often), and a concrete recovery path for GENERATE_AUDIO_FAILED (retry once, then degrade model). It also names the condition for setting instrumental and the client-side 60 s constraint that selects the default path.

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

All AetherWave Studio tools Inspect

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

Need Help?