
MiniMax Music 2.6 API by MiniMax
MiniMax text-to-music (latest): generate a full vocal or instrumental song from a style prompt plus lyrics with [Verse]/[Chorus] structure tags. Synchronous single-call generation.
MiniMax Music 2.6 do MiniMax phát triển. Atlas Cloud (vận hành bởi Atlas Cloud AI LLC) cung cấp quyền truy cập vào mô hình này và không sở hữu mô hình. Mọi thương hiệu đều thuộc về chủ sở hữu tương ứng.
MiniMax Music
Generate a complete song — vocals or instrumental — from a short style prompt plus lyrics, in a single synchronous call.
Highlights
- Text-to-music: describe the genre/mood/instrumentation in
prompt, providelyricswith structure tags. - Structure tags in lyrics:
[Intro] [Verse] [Pre Chorus] [Chorus] [Bridge] [Outro] [Inst]. Separate lines with a newline; a blank line adds a pause. - Instrumental mode via
is_instrumental=true(lyrics optional). - Output is a downloadable audio file (mp3/wav/pcm), up to ~5 minutes.
Parameters
| field | required | notes |
|---|---|---|
prompt | yes | style / mood / genre / instrumentation, ≤2000 chars |
lyrics | for vocals | lyric text with structure tags, ≤3500 chars |
is_instrumental | no | instrumental-only, no vocals |
format | no | mp3 (default) / wav / pcm |
sample_rate | no | 16000 / 24000 / 32000 / 44100 (default) |
bitrate | no | 32000 / 64000 / 128000 / 256000 (default) |
Powered by MiniMax's music model via Atlas Cloud.
















