MiniMax Music 3.0 API: AI Audio Generation

MiniMax Music 3.0 API Reference

Endpoint

POST https://api.muapi.ai/api/v1/minimax-music-3.0

Submit a job with your MuApi API key in the x-api-key header, then poll https://api.muapi.ai/api/v1/predictions/{request_id}/result until status is completed.

Parameters

Name	Type	Required	Description
prompt	string	Yes	Prompt for the music generation — style, mood, and instrumentation.
lyrics	string	Yes	10-3000 characters. A newline separates lyric lines, a double newline adds a pause, and ## marks a section to add instrumental accompaniment.
bitrate	integer	No	Audio bitrate.Options: 60000, 32000, 64000, 128000, 256000Default: 256000
sample_rate	integer	No	Audio sample rate.Options: 16000, 24000, 32000, 44100Default: 44100
is_instrumental	boolean	No	Whether to generate instrumental music with no vocals.Default: false

cURL example

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/minimax-music-3.0 \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"<prompt>","lyrics":"<lyrics>"}' | jq -r .request_id)

curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY"

Python example

import os, time, requests

API = "https://api.muapi.ai/api/v1"
headers = {"x-api-key": os.environ["MUAPI_API_KEY"]}

r = requests.post(f"{API}/minimax-music-3.0", headers=headers, json={"prompt":"<prompt>","lyrics":"<lyrics>"})
request_id = r.json()["request_id"]

while True:
    res = requests.get(f"{API}/predictions/{request_id}/result", headers=headers).json()
    if res["status"] == "completed":
        print(res["outputs"]); break
    if res["status"] == "failed":
        raise RuntimeError(res.get("error"))
    time.sleep(3)

Full docs and agent/MCP integration: llms.txt. Get an API key at muapi.ai/access-keys.