> ## Documentation Index
> Fetch the complete documentation index at: https://novita.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# MiniMax Music

MiniMax AI music generation model, supporting creating AI music from text descriptions and lyrics across various styles, moods, and scenes

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Supports: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format, for example: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="model" type="string" required={true}>
  Model version. music-2.5+ is the latest recommended version supporting instrumental generation; music-2.5 is the standard version; music-2.0 is the base version

  Optional values: `music-2.5+`, `music-2.5`, `music-2.0`
</ParamField>

<ParamField body="lyrics" type="string">
  Song lyrics separated by \n. Supports structure tags: \[Intro], \[Verse], \[Pre Chorus], \[Chorus], \[Interlude], \[Bridge], \[Outro], \[Post Chorus], \[Transition], \[Break], \[Hook], \[Build Up], \[Inst], \[Solo]

  Length limit: 0 - 3500
</ParamField>

<ParamField body="prompt" type="string">
  Music description specifying style, mood, scene, etc. Required when is\_instrumental is true (music-2.5+ only)

  Length limit: 0 - 2000
</ParamField>

<ParamField body="audio_setting" type="object">
  Audio parameter settings

  <Expandable title="properties" defaultOpen={true}>
    <ParamField body="format" type="string">
      Audio encoding format

      Optional values: `mp3`, `wav`, `pcm`
    </ParamField>

    <ParamField body="bitrate" type="integer">
      Bitrate

      Optional values: `32000`, `64000`, `128000`, `256000`
    </ParamField>

    <ParamField body="sample_rate" type="integer">
      Sample rate

      Optional values: `16000`, `24000`, `32000`, `44100`
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="output_format" type="string" default="url">
  Output format, fixed to url, returns audio link

  Optional values: `url`
</ParamField>

<ParamField body="aigc_watermark" type="boolean" default={false}>
  Whether to add AIGC watermark at the end of audio
</ParamField>

<ParamField body="is_instrumental" type="boolean" default={false}>
  Generate instrumental music (no vocals). Only supported by music-2.5+, prompt is required when enabled
</ParamField>

<ParamField body="lyrics_optimizer" type="boolean" default={false}>
  When enabled and lyrics is empty, automatically generates lyrics from prompt. Only supported by music-2.5 and music-2.5+
</ParamField>

## Response

<ResponseField name="audios" type="string[]" required={false}>
  Generated audio list
</ResponseField>