Billing note Both prompt and lyrics have hard length limits enforced before generation: prompt 10-300 characters, lyrics 10-600 characters (including section tags, line breaks and spaces). A request outside these ranges is rejected with HTTP 400 and nothing is charged — the text is not trimmed for you. Count characters before sending; long lyrics should be shortened or split into a separate generation.

MiniMaxMediumStandard

MiniMax Music 1.5

MiniMax Music 1.5 via Replicate. Full-length songs up to 4 minutes with natural vocals and rich instrumentation from a style prompt and structured lyrics. The previous generation to Music 2.5 / 2.6 at a fifth of the price.

70 credits

per song

Full songs up to 4 minutes with vocals

Structured lyrics with [intro] [verse] [chorus] [bridge] [outro] tags

MP3 or WAV output with sample rate and bitrate control

70 credits per song

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "minimax/music-1.5",
  "input": {
    "prompt": "Bright upbeat K-pop electro-pop company jingle, 128 BPM, energetic female vocals, catchy chant chorus, synth brass, punchy drums",
    "lyrics": "[verse]\n아침부터 AI, 커피보다 진해\n코딩하다 보니 벌써 새벽 두 시네!\n안 되는 건 없어, 일단 만들어 봐\n상상이 현실 되는 마법 같은 회사!\n[chorus]\n코어! 닷! 투데이!\n오늘의 상상이 내일의 기술로!\n코어! 닷! 투데이!\nAI도 놀라는 우리의 아이디어!\n[outro]\n뚝딱뚝딱 만들고, 반짝반짝 빛내고!\n기술을 넘어 경험으로!\n코어닷투데이, Hey!",
    "audio_format": "mp3"
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`prompt`	string	Yes	-	Style prompt (genre, mood, instruments). Must be 10-300 characters — shorter or longer is rejected with 400
`lyrics`	string	Yes	-	Lyrics, one line per newline, with [intro] [verse] [chorus] [bridge] [outro] tags. Must be 10-600 characters counting tags, line breaks and spaces — longer lyrics are rejected with 400, not trimmed
`audio_format`	string	No	mp3	Audio format of the output mp3wav
`sample_rate`	integer	No	44100	Sample rate for the generated music 16000240003200044100
`bitrate`	integer	No	256000	Bitrate for the generated music 3200064000128000256000

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

Core.Today company song

The same Korean company-song lyrics given to every music model — compare how each one sings them

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "minimax/music-1.5",
  "input": {
    "prompt": "Bright upbeat K-pop electro-pop company jingle, 128 BPM, energetic female vocals, catchy chant chorus, synth brass, punchy drums",
    "lyrics": "[verse]\n아침부터 AI, 커피보다 진해\n코딩하다 보니 벌써 새벽 두 시네!\n안 되는 건 없어, 일단 만들어 봐\n상상이 현실 되는 마법 같은 회사!\n[chorus]\n코어! 닷! 투데이!\n오늘의 상상이 내일의 기술로!\n코어! 닷! 투데이!\nAI도 놀라는 우리의 아이디어!\n[outro]\n뚝딱뚝딱 만들고, 반짝반짝 빛내고!\n기술을 넘어 경험으로!\n코어닷투데이, Hey!",
    "audio_format": "mp3"
  }
}'

Lazy jazz ballad

Short tagged lyrics with a jazz style prompt

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "minimax/music-1.5",
  "input": {
    "prompt": "Lazy late-night jazz, warm male vocals, brushed drums, upright bass, soft piano",
    "lyrics": "[verse]\nIn the hush of night we find our space,\nwrapped in moonlight's gentle embrace.\n[chorus]\nJust you and me in this lazy jazz,\nour souls entwined, nothing else we ask.",
    "audio_format": "mp3"
  }
}'