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

# MiniMax Lyrics

MiniMax AI lyrics generation model. It supports generating complete lyrics from a prompt or editing/continuing existing lyrics. The generated lyrics include structural tags and can be used directly for music generation.

## Request Headers

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

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

## Request Body

<ParamField body="mode" type="string" required={true}>
  Generation mode. write\_full\_song: write a complete song; edit: edit/continue lyrics

  Allowed values: `write_full_song`, `edit`
</ParamField>

<ParamField body="title" type="string">
  Song title. If provided, the output will keep this title unchanged.
</ParamField>

<ParamField body="lyrics" type="string">
  Existing lyrics content, effective only in edit mode. Can be used to continue or modify existing lyrics.

  Length limit: 0 - 3500
</ParamField>

<ParamField body="prompt" type="string">
  Prompt/instruction used to describe the song theme, style, or editing direction. If empty, it will be generated randomly.

  Length limit: 0 - 2000
</ParamField>

## Response Information

<ResponseField name="lyrics" type="string" required={false}>
  Generated lyrics, including structural tags, which can be used directly with the music generation API.
</ResponseField>

<ResponseField name="song_title" type="string" required={false}>
  Generated song title.
</ResponseField>

<ResponseField name="style_tags" type="string" required={false}>
  Style tags, comma-separated.
</ResponseField>