MiniMax Music 2.6

MiniMax Music 2.6 — generate a full song from a style prompt. Wire `lyrics` with section tags ([Verse], [Chorus], [Bridge], …) to sing your exact words, or leave it empty and MiniMax writes its own lyrics from the prompt (\"Auto-write lyrics from prompt\" is ON by default). Turn on Instrumental for a vocal-free bed instead.

Try MiniMax Music 2.6 in the playground

Last updated View as MarkdownAgent setup

MiniMax Music 2.6

Badge: music
Node type: audio:minimax_music_v2_6
Category: audio

Description

MiniMax Music 2.6 makes a full song from a style prompt: describe the style, mood, genre and scenario in Style / Mood / Genre, for example "City Pop, 80s retro, groovy synth bass, warm female vocal, 104 BPM", and run the node. To have it sing your own words, wire Lyrics with section tags such as [Verse], [Chorus] and [Bridge]; wired lyrics are always sent word for word. Leave Lyrics empty and MiniMax writes its own from the prompt, or turn on Instrumental (no vocals) for a vocal-free bed. It costs about 30 credits per song. Agents can add it to a workflow and run it over the Wireflow MCP server. To see it sing lyrics that Claude Opus 5 wrote, in a full song workflow Claude builds from plain-English asks, watch Suno Alternative: Make Full AI Songs With Lyrics (MiniMax Music 2.6).

Pricing

  • Cost: ~30 credits per song

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
prompt Style / Mood / Genre TEXT (required) · multiline — A description of the music style, mood, genre and scenario — e.g. "City Pop, 80s retro, groovy synth bass, warm female vocal, 104 BPM".
lyrics Lyrics TEXT · multiline — The words to sing. Use section tags: [Intro] [Verse] [Pre Chorus] [Chorus] [Hook] [Bridge] [Outro]. Optional — leave empty and MiniMax writes its own lyrics from the style prompt ("Auto-write lyrics from prompt" is on by default). Wire this to sing your exact words instead.

These render as form fields in the right-side config panel when the node is selected.

ID Label Details
is_instrumental Instrumental (no vocals) BOOLEAN
lyrics_optimizer Auto-write lyrics from prompt BOOLEAN — On by default: with no Lyrics wired, MiniMax writes its own lyrics from the style prompt. Wired Lyrics are always sent verbatim; this switch is turned off automatically then, so your words are never rewritten.

Outputs

ID Label Type
audio Generated Audio AUDIO

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.