Skip to content
HiAPI Docs
HiAPI
Playground Get API Key
English
English 中文

MiniMax Music 2.6 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-2.6
Type Audio generation (text-to-music)
Endpoint POST /v1/tasks
Pricing See HiAPI Pricing

MiniMax Music 2.6: complete songs with natural vocals and rich instrumentation; lyrics up to 3,500 characters, instrumental mode and auto-lyrics, English or Chinese, billed per song.

Production guidance

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

Style prompt plus your own or auto-generated lyrics produce a complete song with vocals and arrangement in one pass.

promptlyrics
Instrumental / BGM

Flip is_instrumental to get vocal-free music for film scores, podcasts and game background tracks.

is_instrumentalprompt
Fine-grained structure

14 structure tags including [Pre Chorus] [Hook] [Build Up] [Solo], with lyrics up to 3,500 characters.

lyrics
Auto-lyrics

Leave lyrics empty and the model writes them from your prompt — fastest way to a demo.

prompt

Request parameters

model string required

Fixed value minimax-music-2.6.

example minimax-music-2.6
input object required

Business parameters. Put MiniMax Music 2.6-specific configuration here.

prompt string required

A description of the music style, mood, and scenario. For example: 'Pop, melancholic, perfect for a rainy night'. Max 2000 characters.

lyrics string optional

Lyrics for the song. Use \n to separate lines. Supports structure tags like [Intro], [Verse], [Pre Chorus], [Chorus], [Interlude], [Bridge], [Outro], [Post Chorus], [Transition], [Break], [Hook], [Build Up], [Inst], [Solo] to control the arrangement. 1-3500 characters. Leave empty to auto-generate lyrics from the prompt; not needed when is_instrumental is true.

is_instrumental boolean optional

Generate instrumental music without vocals. When true, lyrics are not needed.

default false
sample_rate enum optional

Audio sample rate in Hz.

default 44100 enum: 16000240003200044100
bitrate enum optional

Audio bitrate in bps.

default 256000 enum: 3200064000128000256000
audio_format enum optional

Output audio format.

default mp3 enum: mp3wavpcm
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

Neon Night Drive (Mandarin city-pop)

Tested with custom Chinese lyrics and structure tags: city-pop, female vocals.

Request body
{
  "model": "minimax-music-2.6",
  "input": {
    "prompt": "Uplifting Mandarin city-pop with funky bass, bright brass stabs, shimmering synth pads and a confident female lead vocal; polished retro-modern production, driving groove for a neon night drive",
    "lyrics": "[Intro]\n[Verse]\n霓虹在后视镜里流成河\n城市的心跳踩着油门\n[Chorus]\n就让今晚的灯光都为我闪烁\n一路向前不回头\n[Outro]",
    "is_instrumental": false,
    "sample_rate": 44100,
    "bitrate": 256000,
    "audio_format": "mp3"
  }
}
Epic Overture (instrumental)

Tested instrumental mode via is_instrumental: film-score quality.

Request body
{
  "model": "minimax-music-2.6",
  "input": {
    "prompt": "Epic cinematic orchestral theme with soaring strings, powerful brass, thunderous percussion and a heroic adventurous mood, film-score quality",
    "is_instrumental": true
  }
}
Stadium Anthem (auto-lyrics)

Tested with lyrics left empty — the model writes lyrics from the prompt alone.

Request body
{
  "model": "minimax-music-2.6",
  "input": {
    "prompt": "Energetic Mandarin pop-rock anthem with driving electric guitars, punchy drums and a passionate female vocal, stadium-size chorus, triumphant mood"
  }
}

Getting the result

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

FAQ

How is it different from MiniMax Music 1.5?

Lyrics limit raised from 600 to 3,500 characters; adds instrumental mode (is_instrumental) and auto-lyrics; structure tags expanded from 5 to 14.

Can I skip writing lyrics?

Yes. Leave lyrics empty and the model writes them from your prompt; set is_instrumental to true for a vocal-free track.

How is it billed?

Per song, independent of duration. See the pricing page for the live rate.

Which languages can it sing?

It sings naturally in both English and Chinese; describe the style in the prompt and the model matches the language of your lyrics.

Next steps