Back to Nodes
Minimax Music 1.5

Minimax Music 1.5

Official

AI music generator for full-length songs with natural vocals and rich instrumentation.

Nodespell AI
AI / Audio / Minimax

AI music generator for full-length songs with natural vocals and rich instrumentation.

Model Overview

A powerful AI model that generates full-length songs (up to 4 minutes) complete with natural-sounding vocals and rich instrumentation. It can create music across various genres, making it a versatile tool for musicians and content creators.

Best At

  • Generating complete songs with both vocals and accompaniment.
  • Creating music in diverse genres like classical, pop, rock, and electronic.
  • Synthesizing music with improved musicality, instrument performance, and vocal expressiveness.
  • Producing music based on provided lyrics.

Limitations / Not Good At

  • Maximum output length is 240 seconds.
  • Limited to English and Chinese lyrics.
  • Requires reference music for style learning (though not strictly for basic generation).

Ideal Use Cases

  • Film and TV soundtrack creation
  • AI singer compositions
  • Musical reinterpretations and remixes
  • Background music for videos and podcasts
  • Interactive music applications
  • Quickly prototyping song ideas with lyrics

Input & Output Format

  • Input: Text prompts for musical style, lyrics for vocals, optional audio for style reference, and parameters like sample rate, bitrate, and audio format.
  • Output: Audio file (e.g., MP3) containing the generated song.

Performance Notes

  • Capable of producing up to 4 minutes of music.
  • Performance is optimized for generating cohesive musical pieces with vocals and accompaniment.

Model Examples (3)

Example Index01 / 03
Example 01

Coming-of-age montage song

Warm indie vocal song for a feature-film montage.

Open
Source Inputs02
Prompt

Indie pop-rock with warm guitars, live drums, intimate lead vocal, hopeful but slightly worn, suitable for the final-night summer montage in a coming-of-age film.

Lyrics

[Verse] We left the cinema through the service light Cheap coffee, morning blue, the buses white Your denim jacket smelled like rain and smoke We made a promise neither of us spoke [Chorus] Run with me past the closing signs We are not lost, we're just on time Small town fading in the rear-view glow Keep the camera rolling, let the headlights show

Parameters05
Prompt
Indie pop-rock with warm guitars, live drums, intimate lead vocal, hopeful but slightly worn, suitable for the final-night summer montage in a coming-of-age film.
Lyrics
[Verse]
We left the cinema through the service light
Cheap coffee, morning blue, the buses white
Your denim jacket smelled like rain and smoke
We made a promise neither of us spoke

[Chorus]
Run with me past the closing signs
We are not lost, we're just on time
Small town fading in the rear-view glow
Keep the camera rolling, let the headlights show
Audio Format
mp3
Bitrate
256000
Sample Rate
44100
musicsongmontage
Response
Inputs (2)

Lyrics

String

Lyrics. Use to separate lines. Supports [intro][verse][chorus][bridge][outro]. Valid input: 10-600 characters.

Multi InputMin: 0Max: 100

Prompt

String

Control music generation with a text prompt. Valid input: 10-300 characters.

Multi InputMin: 0Max: 100
Parameters (5)

Lyrics

String

Lyrics. Use to separate lines. Supports [intro][verse][chorus][bridge][outro]. Valid input: 10-600 characters.

Default:

Prompt

String

Control music generation with a text prompt. Valid input: 10-300 characters.

Default:

Bitrate

Number

Bitrate for the generated music

Default: 256000

Sample Rate

Number

Sample rate for the generated music

Default: 44100

Audio Format

String

Audio format

Default: mp3
Outputs (1)

Output

Inferred

Output

Nodespell

Nodespell

London

Building the future. Join us!

nodespell.comnodespell.appNodespellAI
Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Audio / Minimax

Input

TextAudio

Output

Audio

Keywords

Music GenerationLength Control
Use in Workflow