MiniMax Music 3.0: AI Audio Generator

Generate full songs with vocals or instrumentals with MiniMax Music 3.0. Structured lyrics input, configurable audio quality. Try free — pay per song.

📝

Overview

About this model

MiniMax Music 3.0 is a text-to-music generation model that produces complete songs — vocals, instrumentation, and structure — from a short style prompt combined with lyrics you supply. It also supports an instrumental-only mode for background music, intros, and score work where vocals aren't wanted. Lyrics support verse/chorus formatting, pauses, and accompaniment markers, giving you fine control over song structure without needing a music production pipeline. For speech rather than song generation, see MiniMax Speech 2.6 HD.

1Content creation: Generate original background music and theme songs for videos, podcasts, and social content without licensing concerns.

2Game development: Produce instrumental tracks and stingers for game levels, menus, and cutscenes on demand.

3Marketing: Create custom jingles and vocal hooks for ad campaigns and product launches.

4Songwriting: Turn a lyric draft into a fully produced demo to test melody and arrangement ideas quickly.

5App integrations: Generate royalty-free background music programmatically for apps that need dynamic audio.

💰

Pricing & Value

Cost analysis

Provider	Cost	Notes
muapiapp	$0.20 per song	Flat rate per generation, pay-as-you-go, no subscription.
Fal.ai	Not available	MiniMax Music 3.0 is not currently listed on Fal.ai.
Replicate	Not available	MiniMax Music 3.0 is not currently listed on Replicate.

muapiapp$0.20 per song

Flat rate per generation, pay-as-you-go, no subscription.

Fal.aiNot available

MiniMax Music 3.0 is not currently listed on Fal.ai.

ReplicateNot available

MiniMax Music 3.0 is not currently listed on Replicate.

* Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Parameter	Type	Description	Default
Prompt	string	Prompt for the music generation — style, mood, and instrumentation.	`An upbeat synth-pop anthem with driving drums and a soaring chorus`
Lyrics	string	10-3000 characters. A newline separates lyric lines, a double newline adds a pause, and ## marks a section to add instrumental accompaniment.	`[Verse] Walking through the city lights ## [Chorus] We are shining, we are free`
Bitrate	Enum (5 options)	Audio bitrate.	`256000`
Sample Rate	Enum (4 options)	Audio sample rate.	`44100`
Instrumental Only	boolean	Whether to generate instrumental music with no vocals.	`false`

Promptstring

Prompt for the music generation — style, mood, and instrumentation.

Default ValueAn upbeat synth-pop anthem with driving drums and a soaring chorus

Lyricsstring

10-3000 characters. A newline separates lyric lines, a double newline adds a pause, and ## marks a section to add instrumental accompaniment.

Default Value

[Verse]
Walking through the city lights

##
[Chorus]
We are shining, we are free

BitrateEnum (5 options)

Audio bitrate.

Default Value256000

Sample RateEnum (4 options)

Audio sample rate.

Default Value44100

Instrumental Onlyboolean

Whether to generate instrumental music with no vocals.

Default Valuefalse

📖

Implementation Guide

Developer documentation

How to Use MiniMax Music 3.0

Write your prompt: Describe the musical style, mood, tempo, and instrumentation you want (e.g. "an upbeat synth-pop anthem with driving drums").
Write your lyrics: Supply 10-3000 characters of lyrics. Use a single newline to separate lines, a double newline to insert a pause, and ## to mark a section where instrumental accompaniment should be layered in.
Choose vocal or instrumental: Leave is_instrumental as false for a full vocal song, or set it to true for an instrumental-only version of the same arrangement.
Set audio quality: Optionally configure bitrate (60000-256000, default 256000) and sample_rate (16000-44100 Hz, default 44100) to match your delivery pipeline.
Submit and poll: POST to the endpoint and poll the returned request ID until status is completed, then download the audio output.

curl -X POST https://api.muapi.ai/api/v1/minimax-music-3.0 \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "an upbeat synth-pop anthem with driving drums and a soaring chorus",
    "lyrics": "[Verse]\nWalking through the city lights\n\n##\n[Chorus]\nWe are shining, we are free",
    "is_instrumental": false
  }'

❓

Common Questions

Frequently asked

What does MiniMax Music 3.0 do?

MiniMax Music 3.0 generates a complete song — vocals, instrumentation, and structure — from a text prompt describing style and mood, combined with lyrics you supply. It can also generate instrumental-only tracks.

How do I format lyrics for MiniMax Music 3.0?

Lyrics are plain text, 10-3000 characters. A single newline separates lyric lines, a double newline inserts a pause, and ## marks a section to add instrumental accompaniment.

Can I generate instrumental-only music?

Yes. Set is_instrumental to true and MiniMax Music 3.0 will generate a vocal-free instrumental version of the same arrangement, driven by the same prompt and lyric structure.

What audio quality settings are available?

You can set bitrate to 60000, 32000, 64000, 128000, or 256000 (default 256000), and sample_rate to 16000, 24000, 32000, or 44100 Hz (default 44100).

How much does MiniMax Music 3.0 cost on Muapi?

MiniMax Music 3.0 is priced at a flat $0.20 per generated song on Muapi, with no subscription required.

Is there a minimum or maximum lyrics length?

Lyrics must be between 10 and 3000 characters. Shorter or longer inputs will be rejected by the API.