MiniMax Music 2.6

MiniMax Music 2.6 · MiniMax — Text to audio · MP3/WAV/PCM. Call it through one queue API and pay for the options you pick.

modellane/minimax-music-2.6 · Text to audio · MiniMax

Text to audio model: MP3/WAV/PCM.

Vendor
MiniMax
Task
Text to audio
Output
Audio
Price
From $0.20 per run

Input parameters

  • Prompt prompt — required, at most 2000 characters Describe what you want produced as concretely as you can.
  • Lyrics lyrics — optional, at most 3500 characters Line breaks separate the lines. If you are writing lyrics, turn "Let the model write the lyrics" off.
  • Instrumental is_instrumental — optional, default: No When on, the track is produced without vocals and any lyrics are ignored.
  • File format format — optional, options: MP3, WAV, PCM The file format of the output.
  • Sample rate sample_rate — optional, default: 44100, options: 16000, 24000, 32000, 44100 The sample rate of the audio output; a higher value makes the file larger.
  • Bitrate bitrate — optional, default: 256000, options: 32000, 64000, 128000, 256000

Output and retention

The generated file and your input are kept for seven days and then deleted.

Queue API

Submit to the queue: POST /v1/queue/modellane/minimax-music-2.6

Status, result, cancellation and error codes work the same for every model; see the API docs.

Playground

Everything on this page is public; you need an account to run the model.