suno-mcp

text_to_music

Generate music from text prompts or lyrics by creating Suno tasks, returning task IDs and output URLs for retrieval.

Instructions

Create a Suno task on RunAPI (text to music). Returns a task id, status, and output URLs.

Input Schema

TableJSON Schema

Name	Required	Description
`wait`	No	Poll until the task reaches a terminal status.
`model`	No	RunAPI model slug for this model line.
`style`	No	Music style.
`title`	No	Music title.
`lyrics`	No	Exact lyrics to sing.
`prompt`	No	Song brief for automatic lyrics.
`voice_id`	No	RunAPI Voice handle.
`persona_id`	No	Persona ID.
`timeout_ms`	No
`vocal_mode`	Yes	Vocal generation mode.
`continue_at`	No	Timestamp in seconds to continue from.
`audio_weight`	No	Audio weight (0-1).
`callback_url`	No	Webhook URL for async notifications.
`persona_type`	No	Persona type.
`style_weight`	No	Style adherence weight (0-1).
`vocal_gender`	No	Vocal gender.
`negative_tags`	No	Styles to avoid.
`duration_seconds`	No	Preferred duration in seconds; only available for Suno V5.5 custom requests.
`poll_interval_ms`	No
`weirdness_constraint`	No	Weirdness constraint (0-1).

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.3.6Sep 18, 2026

changedInput schema / properties / model / enum

Previous value: -[
-  "suno-v4",
-  "suno-v4.5",
-  "suno-v4.5-all",
-  "suno-v4.5-plus",
-  "suno-v5",
-  "suno-v5.5"
-]New value: +[
+  "suno-v4",
+  "suno-v4.5",
+  "suno-v4.5-all",
+  "suno-v4.5-plus",
+  "suno-v5",
+  "suno-v5.5",
+  "suno-v6",
+  "suno-v6-mini",
+  "suno-v6-wild"
+]

addedInput schema / properties / voice_id

Added value: +{
+  "description": "RunAPI Voice handle.",
+  "type": "string"
+}

Changed10 schema fields changedv0.3.5Sep 11, 2026
- addedInput schema / properties / audio_weight / maximum
```
Added value: +1
```
- addedInput schema / properties / audio_weight / minimum
```
Added value: +0
```
- addedInput schema / properties / lyrics / maxLength
```
Added value: +5000
```
- changedInput schema / properties / prompt / maxLength
```
Previous value: -3000New value: +5000
```
- addedInput schema / properties / style / maxLength
```
Added value: +1000
```
- addedInput schema / properties / style_weight / maximum
```
Added value: +1
```
- addedInput schema / properties / style_weight / minimum
```
Added value: +0
```
- addedInput schema / properties / title / maxLength
```
Added value: +80
```
- addedInput schema / properties / weirdness_constraint / maximum
```
Added value: +1
```
- addedInput schema / properties / weirdness_constraint / minimum
```
Added value: +0
```

Changed16 schema fields changedv0.3.2Aug 21, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

changedInput schema / properties / duration_seconds / description

Previous value: -"Duration in seconds."New value: +"Preferred duration in seconds; only available for Suno V5.5 custom requests."

addedInput schema / properties / duration_seconds / maximum
```
Added value: +360
```
addedInput schema / properties / duration_seconds / minimum
```
Added value: +10
```

addedInput schema / properties / persona_type / anyOf

Added value: +[
+  {
+    "const": "style",
+    "type": "string"
+  },
+  {
+    "const": "voice",
+    "type": "string"
+  }
+]

removedInput schema / properties / persona_type / enum
```
Removed value: -[
-  "style",
-  "voice"
-]
```
removedInput schema / properties / persona_type / type
```
Removed value: -"string"
```
addedInput schema / properties / poll_interval_ms / maximum
```
Added value: +9007199254740991
```
addedInput schema / properties / prompt / maxLength
```
Added value: +3000
```
addedInput schema / properties / timeout_ms / maximum
```
Added value: +9007199254740991
```

addedInput schema / properties / vocal_gender / anyOf

Added value: +[
+  {
+    "const": "male",
+    "type": "string"
+  },
+  {
+    "const": "female",
+    "type": "string"
+  }
+]

removedInput schema / properties / vocal_gender / enum
```
Removed value: -[
-  "male",
-  "female"
-]
```
removedInput schema / properties / vocal_gender / type
```
Removed value: -"string"
```

addedInput schema / properties / vocal_mode / anyOf

Added value: +[
+  {
+    "const": "auto_lyrics",
+    "type": "string"
+  },
+  {
+    "const": "exact_lyrics",
+    "type": "string"
+  },
+  {
+    "const": "instrumental",
+    "type": "string"
+  }
+]

removedInput schema / properties / vocal_mode / enum

Removed value: -[
-  "auto_lyrics",
-  "exact_lyrics",
-  "instrumental"
-]

removedInput schema / properties / vocal_mode / type
```
Removed value: -"string"
```

Changed16 schema fields changedv0.2.4Jul 29, 2026
- addedInput schema / properties / audio_weight / description
```
Added value: +"Audio weight (0-1)."
```
- addedInput schema / properties / callback_url / description
```
Added value: +"Webhook URL for async notifications."
```
- addedInput schema / properties / continue_at / description
```
Added value: +"Timestamp in seconds to continue from."
```
- addedInput schema / properties / duration_seconds / description
```
Added value: +"Duration in seconds."
```
- removedInput schema / properties / endpoint
```
Removed value: -{
-  "type": "string"
-}
```
- addedInput schema / properties / lyrics / description
```
Added value: +"Exact lyrics to sing."
```
- addedInput schema / properties / negative_tags / description
```
Added value: +"Styles to avoid."
```
- addedInput schema / properties / persona_id / description
```
Added value: +"Persona ID."
```
- addedInput schema / properties / persona_type / description
```
Added value: +"Persona type."
```
- addedInput schema / properties / prompt / description
```
Added value: +"Song brief for automatic lyrics."
```
- addedInput schema / properties / style / description
```
Added value: +"Music style."
```
- addedInput schema / properties / style_weight / description
```
Added value: +"Style adherence weight (0-1)."
```
- addedInput schema / properties / title / description
```
Added value: +"Music title."
```
- addedInput schema / properties / vocal_gender / description
```
Added value: +"Vocal gender."
```
- addedInput schema / properties / vocal_mode / description
```
Added value: +"Vocal generation mode."
```
- addedInput schema / properties / weirdness_constraint / description
```
Added value: +"Weirdness constraint (0-1)."
```
Changed1 schema field changedv0.1.9Jul 13, 2026
- addedInput schema / properties / endpoint
```
Added value: +{
+  "type": "string"
+}
```
Changed7 schema fields changedv0.1.2Jun 23, 2026
- addedInput schema / properties / callback_url / type
```
Added value: +"string"
```
- addedInput schema / properties / lyrics / type
```
Added value: +"string"
```
- addedInput schema / properties / negative_tags / type
```
Added value: +"string"
```
- addedInput schema / properties / persona_id / type
```
Added value: +"string"
```
- addedInput schema / properties / prompt / type
```
Added value: +"string"
```
- addedInput schema / properties / style / type
```
Added value: +"string"
```
- addedInput schema / properties / title / type
```
Added value: +"string"
```
First observedv0.1.0Jun 23, 2026

TDQS

C2.9/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions returning a task id, status, and output URLs, implying an asynchronous task-based flow, but it does not disclose any side effects (e.g., cost, rate limits), how to poll or retrieve results beyond that, or any prerequisites. For a mutation tool, this is minimal disclosure.

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?

The description is concise at two sentences with no fluff. The core purpose is front-loaded, and the return information is stated briefly. It is efficient and to the point, though it could add a bit more context without becoming verbose.

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

Completeness2/5

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

Despite having 20 parameters and no output schema, the description is extremely sparse. It does not explain the task lifecycle (e.g., how the wait parameter works, how to use callback_url, or how to interpret statuses), nor does it mention the range of vocal modes or other key options. The agent is left to rely solely on the schema, which is not sufficient for a tool of this complexity.

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 description coverage is 90%, so the schema already documents most parameters. The description adds no parameter-specific meaning beyond what the schema provides; it does not explain how parameters relate to the text-to-music process. Baseline 3 is appropriate given high schema coverage.

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?

The description clearly states the action ('Create a Suno task') and the resource ('text to music on RunAPI'), and mentions the return values. It distinguishes from siblings like text_to_sound by specifying 'music' rather than 'sound', but does not explicitly name alternatives. A clear purpose with minor differentiation gap.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives like cover_audio, text_to_sound, or extend_music. The description only states what it does, not the conditions or contexts where it is the preferred choice. This leaves the agent to infer usage from the name and siblings.

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

text_to_music

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools