MiniMax Music 2.6

Use MiniMax Music 2.6 for audio; see supported inputs and option-based pricing on this page.

modellane/minimax-music-2-6-e12e3803 · Text to audio · MiniMax

MiniMax Music 2.6 supports text to audio. Its documented input fields are listed below; the request price is calculated from the selected options.

Vendor
MiniMax
Task
Text to audio
Output
Audio
Price
$0 · 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: false When on, the track is produced without vocals and any lyrics are ignored.
  • File format format — optional, options: mp3, wav, pcm
  • Sample rate sample_rate — optional, default: 44100, options: 16000, 24000, 32000, 44100
  • Bitrate bitrate — optional, default: 256000, options: 32000, 64000, 128000, 256000

Recommended use cases

    Where it is strong

      Limits

        Example prompt

        A short, calm instrumental piece with soft piano and strings.

        Example request

        POST /v1/queue/modellane/minimax-music-2-6-e12e3803

        Playground

        The identifier, price, parameters, and example requests on this page can be read without signing in. Running the model from the panel sends a real generation request and charges the project balance; the playground therefore requires an account.