Skip to main content
POST
/
vendors
/
minimax
/
v1
/
music-2.5
/
text-to-music
/
generation
Create Music Generation Task
curl --request POST \
  --url https://api.mulerouter.ai/vendors/minimax/v1/music-2.5/text-to-music/generation \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "Acoustic, indie folk, gentle and reflective mood",
  "lyrics_prompt": "[Intro]\n(Guitar strumming)\n\n[Verse]\nSitting by the window\nWatching the rain fall down\n\n[Chorus]\nBut I know tomorrow\nWill bring a brand new day"
}
'
{
  "task_info": {
    "id": "8e1e315e-b50d-4334-a231-be7d19a372f4",
    "status": "pending",
    "created_at": "2026-03-03T00:00:00Z",
    "updated_at": "2026-03-03T00:00:00Z"
  }
}

Documentation Index

Fetch the complete documentation index at: https://mulerouter.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Overview

Generate music from text descriptions and lyrics using the MiniMax Music 2.5 model. Music 2.5 is the latest version with improved quality:
  • Style description — specify music style, mood, and scenario via prompt
  • Lyrics support — provide song lyrics with lyrics_prompt
  • Structure tags — organize songs with [Intro], [Verse], [Chorus], [Bridge], [Outro] tags
  • Up to 5 minutes — generate songs up to 5 minutes long
  • Audio customization — configurable format (MP3/PCM/FLAC), sample rate, and bitrate
  • Improved quality — enhanced music generation compared to Music 2.0

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
prompt
string
required

A description of the music, specifying style, mood, and scenario. 10-2000 characters.

Required string length: 10 - 2000
lyrics_prompt
string
required

Lyrics of the song. Use \n to separate lines. You may add structure tags like [Intro], [Verse], [Chorus], [Bridge], [Outro] to enhance the arrangement. 10-3000 characters.

Required string length: 10 - 3000
audio_setting
object

Audio configuration settings.

Response

202 - application/json

Accepted - Task created successfully

task_info
object