Audio
MiniMax Music 3
MiniMax Music 3 is a high-performance music generation model for creating complete songs up to five minutes long
- Text to audio
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for MiniMax Music 3. Review your own result before publishing.
A starting point.
Write the words or musical direction and upload a reference if this operation requires one.
Before you publish.
Listen to the complete audio and check pronunciation, lyrics, timing and sound quality.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Inputs and settings
Write the musical direction and lyrics in the fields supplied by this version. Where audio settings are available, choose sample rate, bitrate and format.
duration is an upper bound from 1–300 seconds; the model may stop earlier. Put each lyrics structure tag on its own line.
Supported inputs
These fields come from the current studio form for minimax/music-3. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
lyrics | Text | Required | — |
prompt | Text | Required | — |
duration | Number | Optional | ≥ 1 · ≤ 300 |
guidance_scale | Number | Optional | ≥ 0 · ≤ 20 |
num_inference_steps | Whole number | Optional | ≥ 1 · ≤ 100 |
seed | Whole number | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use MiniMax Music 3 through the API.
Start with this model ID for the endpoint featured on this page:
minimax/music-3
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.