MiniMax Music
MiniMax Music is built for audio-conditioned generation: hum a melody or upload a reference, and the song is written around it.
Try it
You can fill this in now — signing in happens when you run it, and your inputs come with you.
How to use MiniMax Music
- Fill in Song description in the form on this page, and pick the task to run.
- Adjust anything in the parameter table below — the defaults are the platform's recommended values.
- Run it; signing in starts the charge, and the result (Text to music) appears above the form, ready to download.
Use it from the API
The same run, as a request. Send your API key as a bearer token; poll the returned request_uid until it is done.
curl -X POST https://api.melunox.com/v1/ai/async/tasks \
-H "Authorization: Bearer $WISAVEN_API_KEY" \
-H "X-App-Id: wisaven" -H "Content-Type: application/json" \
-d '{
"model": "minimax-music",
"task": "text-to-music",
"input": {
"prompt": "your prompt here",
"reference_audio_url": "https://…",
"instrumental": false
}
}'At a glance
- Developer
- MiniMax
- Can do
- Text to music, Audio to music, Humming to song
- Credits per run
- —
- Typical time
- ~90s
- Added
- 2026-08-11
Parameters
What the model takes. The form above is generated from exactly this list, and the API accepts the same field names.
| Parameter | Type | Default | Range / options |
|---|---|---|---|
promptSong description | Long text | — | — |
reference_audio_urlHumming / reference audio | Audio upload | — | — |
instrumentalInstrumental only | On / off | No | — |
What MiniMax Music costs
MiniMax Music costs usage-based pricing, charged at the platform's live rate, usually back in around 90 seconds. Credits are shared across every workspace, new accounts start with free ones, and a failed run is refunded.
MiniMax Music compared with other Music models
Same workspace, different trade-offs — credits, speed and what each one can be asked for.
| AI models | Can do | Credits per run | Typical time |
|---|---|---|---|
| MiniMax Music | Text to music, Audio to music, Humming to song | — | ~90s |
| ACE-Step | Text to music | — | ~90s |
| Stable Audio Open | Text to music | — | ~90s |
| Demucs HTDemucs | Stem separation | — | ~60s |
| Basic Pitch | Audio to MIDI | — | ~40s |
Questions
What can MiniMax Music do?
Text to music, Audio to music, Humming to song. Fill in the parameters on this page to try it.
How many credits does MiniMax Music cost?
Usage-based, charged at the platform's live price when you run it. One credit balance covers every workspace.
How long does it take?
Around 90 seconds; heavier settings or a queue take longer, and the page shows progress.
Do I need an account, and who owns the output?
Browsing and filling in the form need no account; running it does (new accounts start with free credits). What you generate is yours, personally or commercially, subject to the terms.
Other models like this
Where this model is used: Music·All models