MiniMax Music 1.5 API

POST /v1/tasks

All models are called through the Unified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model name	minimax-music-1.5
Type	Audio generation (text-to-music)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

MiniMax Music 1.5: full songs up to 4 minutes with natural vocals and rich instrumentation, English or Chinese lyrics, structure tags, billed per song.

Production guidance

For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Full song generation

Complete songs up to ~4 minutes in one pass — vocals, harmonies and arrangement, not just BGM loops.

promptlyrics

English & Chinese vocals

Sings naturally in both languages with clear diction — short-video soundtracks or brand jingles.

lyrics

Structured arrangement

[intro][verse][chorus][bridge][outro] tags shape the song structure with distinct verse/chorus dynamics.

lyrics

Per-song billing

Price is independent of duration — long or short, one flat rate per song.

prompt

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax-music-1.5",
  "input": {
    "prompt": "warm acoustic Chinese folk-pop ballad, gentle female vocals, fingerstyle guitar and soft strings, healing and nostalgic mood",
    "lyrics": "[verse]\n晨光洒进老街的窗\n豆浆的雾气慢慢上扬\n单车铃声穿过小巷\n载着昨天的梦去远方\n[chorus]\n慢一点走 别慌张\n日子会把答案酿成糖\n慢一点走 看夕阳\n把平凡过成诗的模样",
    "audio_format": "mp3"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "minimax-music-1.5",
  "input": {
    "prompt": "warm acoustic Chinese folk-pop ballad, gentle female vocals, fingerstyle guitar and soft strings, healing and nostalgic mood",
    "lyrics": "[verse]\n晨光洒进老街的窗\n豆浆的雾气慢慢上扬\n单车铃声穿过小巷\n载着昨天的梦去远方\n[chorus]\n慢一点走 别慌张\n日子会把答案酿成糖\n慢一点走 看夕阳\n把平凡过成诗的模样",
    "audio_format": "mp3"
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "minimax-music-1.5",
  "input": {
    "prompt": "warm acoustic Chinese folk-pop ballad, gentle female vocals, fingerstyle guitar and soft strings, healing and nostalgic mood",
    "lyrics": "[verse]\n晨光洒进老街的窗\n豆浆的雾气慢慢上扬\n单车铃声穿过小巷\n载着昨天的梦去远方\n[chorus]\n慢一点走 别慌张\n日子会把答案酿成糖\n慢一点走 看夕阳\n把平凡过成诗的模样",
    "audio_format": "mp3"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value minimax-music-1.5.

example minimax-music-1.5

input object required

Business parameters. Put MiniMax Music 1.5-specific configuration here.

prompt string required

Text prompt controlling the music style (genre, mood, instrumentation). 10-300 characters.

lyrics string required

Song lyrics, one line per phrase (use \n to separate). Supports structure tags [intro][verse][chorus][bridge][outro]. 10-600 characters.

audio_format enum optional

Output audio format.

default mp3 enum: mp3wavpcm

bitrate enum optional

Audio bitrate in bps.

default 256000 enum: 3200064000128000256000

sample_rate enum optional

Audio sample rate in Hz.

default 44100 enum: 16000240003200044100

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Old Street Morning (Chinese folk)

Healing female-vocal ballad, Chinese lyrics — verified run.

Request body

{
  "model": "minimax-music-1.5",
  "input": {
    "prompt": "warm acoustic Chinese folk-pop ballad, gentle female vocals, fingerstyle guitar and soft strings, healing and nostalgic mood",
    "lyrics": "[verse]\n晨光洒进老街的窗\n豆浆的雾气慢慢上扬\n单车铃声穿过小巷\n载着昨天的梦去远方\n[chorus]\n慢一点走 别慌张\n日子会把答案酿成糖\n慢一点走 看夕阳\n把平凡过成诗的模样",
    "audio_format": "mp3"
  }
}

Neon Wave (English synthwave)

Retro 80s synths with male vocals — style contrast test.

Request body

{
  "model": "minimax-music-1.5",
  "input": {
    "prompt": "upbeat synthwave pop with male vocals, punchy drums, retro 80s synths, neon night drive energy",
    "lyrics": "[verse]\nCity lights are calling out my name\nMidnight engines humming through the rain\n[chorus]\nWe ride the neon wave tonight\nChasing every flash of light\nNever gonna slow it down\nHeartbeat louder than this town",
    "audio_format": "mp3"
  }
}

Getting the result

The response returns a taskId immediately without waiting for generation to finish.
In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
When status=success, download the generated audio from output[].url.
When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

How long is a song? How is it billed?

Song length follows your lyrics, up to ~4 minutes (600 characters of lyrics is roughly 1 minute in our tests). Billing is per song, independent of duration. See the pricing page for live rates. View pricing

How should I write lyrics?

Separate lines with \n and sections with [verse]/[chorus] tags (10-600 characters). For the style prompt, name genre + vocal gender + instruments + mood. Longer lyrics produce longer songs.

What format is the output?

mp3 by default (256kbps/44.1kHz), with wav and pcm options; bitrate and sample_rate are adjustable.

How do I get the generated song?

The request returns a taskId immediately. When the task reaches a terminal state, download the audio from output[].url. In production, pass callback.url at the top level of the request body instead of polling.