Skip to main content
Glama
Sign In
SunoMCP

SunoMCP

by AceDataCloud
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

suno_extend_music

Extend an existing generated song from a chosen timestamp by adding new lyrics, letting you create extra verses, bridges, or outros and build longer tracks piece by piece.

Instructions

Extend an existing song from a specific timestamp with new lyrics.

This allows you to continue a previously generated song, adding new sections
like additional verses, a bridge, or an outro.

Use this when:
- A generated song is too short and you want to add more
- You want to add a bridge or outro to an existing song
- You're building a longer song piece by piece

After extending multiple times, use suno_concat_music to merge all segments.

Returns:
    Task ID and the extended 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>",
      "lyric": "<lyric>",
      "continue_at": "<continue_at>"
    },
    "name": "suno_extend_music"
  }
}

Input Schema

NameRequiredDescriptionDefault
lyricYesLyrics for the extended section. Use section markers like [Verse], [Chorus], [Bridge], [Outro]. The extension will continue from where the original song left off.
modelNoModel version to use for the extension.chirp-v5-5
styleNoMusic style for the extension. Leave empty to maintain the original style, or specify to change the style mid-song.
audio_idYesID of the audio to extend. This is the 'id' field from a previous generation result.
continue_atYesPositive continuation boundary in seconds; fractional seconds are preserved. Lyrics only affect new content after this boundary, not the source before it.
callback_urlNoWebhook callback URL for asynchronous notifications. When provided, the API will call this URL when the extension is complete.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.25
    • changedInput schema / properties / continue_at / description
      Previous value: -"Timestamp in seconds where to start the extension. For example, 120.5 means continue from 2 minutes and 0.5 seconds into the song."New value: +"Positive continuation boundary in seconds; fractional seconds are preserved. Lyrics only affect new content after this boundary, not the source before it."
    • addedInput schema / properties / continue_at / exclusiveMinimum
      Added value: +0
  2. Changed1 schema field changedv0.1.18
    • changedInput schema / properties / model / enum
      Previous value: -[
-  "chirp-v3-0",
-  "chirp-v3-5",
-  "chirp-v4",
-  "chirp-v4-5",
-  "chirp-v4-5-plus",
-  "chirp-v5",
-  "chirp-v5-5"
-]New value: +[
+  "chirp-v6",
+  "chirp-v6-wild",
+  "chirp-v6-mini",
+  "chirp-v3-0",
+  "chirp-v3-5",
+  "chirp-v4",
+  "chirp-v4-5",
+  "chirp-v4-5-plus",
+  "chirp-v5",
+  "chirp-v5-5"
+]
  3. Addedv0.1.5
  4. Removedv0.1.3
  5. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

No annotations exist, so the description carries the full behavioral burden. It signals an async task model ('Returns: Task ID') and describes the continuation semantics as adding new sections, but omits whether the source song is preserved or altered, whether credits are consumed per attempt, and how failures surface. The callback_url async behaviour lives only in the schema.

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 core action in the first line, then scoped by a short bullet list and a pointer to the follow-up tool. The trailing 'Returns' block is largely redundant given the output schema, which costs it a point.

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?

With an output schema present, return values need not be spelled out, and the description still covers purpose, trigger conditions, and the downstream merge step. The main remaining gap is any mention of prerequisites such as needing a previously generated unfinished or extendable audio_id.

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 the schema already documents lyric, model, style, audio_id, continue_at and callback_url in detail. The description restates the core idea of continuing from a timestamp but adds no format or constraint detail beyond the schema, so baseline 3 applies.

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?

Names a specific verb (extend) and resource (an existing song) plus the key scoping concept — a specific timestamp — and adds new lyrics. This is clearly distinguishable from sibling operations like suno_replace_section, suno_upload_extend, and suno_concat_music.

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?

The 'Use this when' block gives three explicit triggering scenarios (song too short, adding bridge/outro, building a longer song piece by piece) and routes the agent forward to suno_concat_music for merging. It doesn't state when NOT to use it — e.g. versus suno_replace_section for editing existing audio or suno_upload_extend for uploaded source audio — so a sibling-boundary gap remains.

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

Deploy Server

Other Tools