SunoMCP

suno_extract_vocals

Isolate vocals from a generated song by specifying a time range under 30 seconds. Get an acapella track for remixing, mashups, or persona creation.

Instructions

Extract the vocal track from a generated song (stem separation).

Isolates the vocals from a song, removing instrumental background.
Useful for remixing, creating acapella versions, or persona creation.

Use this when:
- You want an isolated vocal track
- You need vocals for a remix or mashup
- You want to create a persona from specific vocal segments

Returns:
    Task ID and extracted vocal audio information.

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": {
      "audio_id": "<audio_id>",
      "vocal_start": "<vocal_start>",
      "vocal_end": "<vocal_end>"
    },
    "name": "suno_extract_vocals"
  }
}

Input Schema

Name	Required	Description
`audio_id`	Yes	The song ID to extract vocals from.
`vocal_end`	Yes	Required extraction end time in seconds. It must be greater than vocal_start, with a range shorter than 30 seconds.
`vocal_start`	Yes	Required extraction start time in seconds. The selected range must be shorter than 30 seconds.
`callback_url`	No	Webhook callback URL for asynchronous notifications.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedv0.1.11Aug 21, 2026

removedInput schema / properties / vocal_end / anyOf

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / vocal_end / default
```
Removed value: -null
```

changedInput schema / properties / vocal_end / description

Previous value: -"End time in seconds for the vocal extraction range."New value: +"Required extraction end time in seconds. It must be greater than vocal_start, with a range shorter than 30 seconds."

addedInput schema / properties / vocal_end / exclusiveMinimum
```
Added value: +0
```
addedInput schema / properties / vocal_end / type
```
Added value: +"number"
```

removedInput schema / properties / vocal_start / anyOf

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / vocal_start / default
```
Removed value: -null
```

changedInput schema / properties / vocal_start / description

Previous value: -"Start time in seconds for the vocal extraction range."New value: +"Required extraction start time in seconds. The selected range must be shorter than 30 seconds."

addedInput schema / properties / vocal_start / minimum
```
Added value: +0
```
addedInput schema / properties / vocal_start / type
```
Added value: +"number"
```

changedInput schema / required

Previous value: -[
-  "audio_id"
-]New value: +[
+  "audio_id",
+  "vocal_start",
+  "vocal_end"
+]

Addedv0.1.5May 31, 2026
Removedv0.1.3May 24, 2026
First observedv0.1.0Apr 4, 2026

TDQS

A3.8/5.0

Behavior3/5

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

No annotations are provided, so the description carries full burden. It discloses the core behavior (isolating vocals, removing instrumental background) and that it returns a Task ID and vocal info, but it does not explain the asynchronous nature, whether the original song is modified, or how the extracted audio is delivered.

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 well-structured with a clear opening, a 'Use this when' list, and a Returns section. It is concise enough but could be tightened by merging the first two sentences.

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

Completeness3/5

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

Given the output schema exists, the description need not detail return values, but it should mention that this is an asynchronous task (Task ID implies it) and that the audio must be Suno-generated. The description covers use cases and return info but misses operational nuances.

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 100%, so baseline is 3. The description does not add any parameter-specific meaning beyond the schema; it only implies time-based extraction without elaborating on the parameters.

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?

The description clearly states the tool extracts the vocal track from a song (stem separation), using specific verb 'Extract' and resource 'vocal track'. It distinguishes from siblings like suno_all_stems_music by specifying it isolates only vocals.

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

Usage Guidelines4/5

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

Provides explicit 'Use this when' bullet points covering isolated vocals, remix/mashup needs, and persona creation. However, it does not mention when not to use it or alternatives like suno_stems_music for full stem separation.

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

Deploy Server