MiniMax

MiniMax Music 2.6

minimax-music-2.6

A vocal-plus-instrumental model that generates complete songs from text, adding AI Cover-style adaptations and automatic lyric writing, with first output latency claimed to be under 20 seconds

minimax-music-2.6

Try minimax-music-2.6

Input

Lyrics

Instrumental

Showcases

View all showcases

Output

Fill in the parameters and run — results show up here.

Pricing

minimax-music-2.6 per song

Unit Price	$0.210

Overview

minimax-music-2.6 is MiniMax's text-to-song model, accessible through the unified HiAPI.ai interface. Enter a style prompt to generate a complete song with vocals and multi-layered instrumentation, or simply provide a prompt and let it write the lyrics automatically, or switch to instrumental-only mode to output vocal-free music. Lyrics support structural tags to control section arrangement, and the output format, bitrate, and sample rate can be specified as needed. It is suited for developers and content teams that need to produce original soundtracks, song demos, and style-adaptation material in batches.

Key Highlights

End-to-end complete song production — a single call returns a finished piece with vocals, instrumentation, and genre-styled mixing rather than fragmentary material, eliminating the need for multi-track assembly.
Lyrics can be generated automatically — a prompt alone drives the model to write lyrics and compose the song, so even without lyric-writing ability you can directly obtain a vocal work.
Structural tags control arrangement — use tags such as Intro, Verse, Chorus, and Bridge to divide sections and make deterministic arrangements for the song's progression.
Selectable output specifications — supports mp3, wav, and pcm formats, with bitrate and sample rate selectable among the tiers given in the schema, making it easy to integrate with downstream workflows.

Capabilities

Text-to-song: enter style, mood, and scene descriptions, and the model generates a complete song with vocals and multi-layered instrumentation that can be used directly as finished material or a demo.

Instrumental-only generation: after enabling instrumental mode, no lyrics are needed, and the output is a vocal-free accompaniment or instrumental piece, suitable for background music needs.

Automatic lyric writing: when the lyrics field is left empty, the model generates lyrics based on the prompt, lowering the barrier to writing from scratch; when precise control is needed, you can still provide your own lyrics.

Structured arrangement: section structure tags can be embedded in the lyrics to control the placement of intro, verse, chorus, and interlude, making the output structure better match expectations.

Controllable output parameters: audio format, bitrate, and sample rate can be specified, allowing you to choose suitable output specifications for downstream editing, distribution, or playback scenarios.

Use Cases

Short-video and podcast creators generate soundtracks — with style and mood descriptions as input, produce background music that can be laid directly into videos or podcasts, reducing reliance on external music libraries.
Songwriters validate song demos — submit style prompts and draft lyrics to quickly obtain a complete demo with vocals for validating melody and arrangement directions.
One-stop song production without lyric-writing ability — use a single scene description to drive automatic lyric writing and song generation, producing original tracks usable for events, advertising, or content distribution.
Batch production of instrumental accompaniment — enable instrumental mode to generate vocal-free accompaniment in batches, for scenarios such as voiceover, presentations, or games that need to leave room for vocals.

Limitations and Selection Advice

The lyrics field is capped at 3500 characters and the style prompt at 2000 characters; overly long content must be trimmed first. Generation results depend heavily on prompt quality, and automatically generated lyrics should be reviewed manually before use. If the need is to adapt the style of an existing song or to support interactions with extremely high real-time requirements, the current parameter capabilities do not cover such usage, and a model supporting the corresponding input form should be selected instead.

Create a generation task

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

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: minimax-music-2.6

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for minimax-music-2.6 and route default — see the parameter table below.

lyricsstringOptionalminLength 1maxLength 3500

Song lyrics, 1-3500 characters, with lines separated by \n; supports structural tags such as [Intro], [Verse], [Chorus] to control arrangement sections. If left empty, lyrics are automatically generated based on the prompt; not required when is_instrumental is true.

promptstringRequiredminLength 1maxLength 2000

Descriptive text for the music style, mood, and scene, for example "pop, melancholic, suitable for a rainy night", up to 2000 characters.

bitrateintegerOptionalDefault: 256000

Output audio bitrate, in bps, default 256000.

Options:3200064000128000256000

sample_rateintegerOptionalDefault: 44100

Output audio sample rate, in Hz, default 44100.

Options:16000240003200044100

audio_formatstringOptionalDefault: "mp3"

Output audio format, default mp3.

Options:mp3wavpcm

is_instrumentalbooleanOptionalDefault: false

Whether to generate instrumental music with no vocals; when true, lyrics are not required, default false.

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax-music-2.6",
  "input": {
    "prompt": "…",
    "bitrate": 256000,
    "sample_rate": 44100,
    "audio_format": "mp3",
    "is_instrumental": false
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "minimax-music-2.6",
    input: {
      "prompt": "…",
      "bitrate": 256000,
      "sample_rate": 44100,
      "audio_format": "mp3",
      "is_instrumental": false
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "minimax-music-2.6",
        "input": {
          "prompt": "…",
          "bitrate": 256000,
          "sample_rate": 44100,
          "audio_format": "mp3",
          "is_instrumental": False
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}