Seedream 5.0 Pro is LIVE | Try in Image Generator →

Music 01

minimax /

Minimax Music-01 Synthesizes Accompaniment And Vocals Simultaneously To Produce Complete Songs Across Diverse Styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-audio
Input

Idle

$0.35per run·~28 / $10

ExamplesView all

Related Models

README

MiniMax Music-01

MiniMax Music-01 is an advanced AI music generation model that creates complete songs with vocals and instrumentals. Provide lyrics with section tags, optionally upload reference audio for voice cloning or instrumental style, and generate professional-quality music tracks.

Why It Stands Out

  • Lyrics-based generation: Create songs from structured lyrics with section tags.
  • Voice cloning: Upload a voice reference to match vocal style and tone.
  • Instrumental reference: Guide the musical style with a reference instrumental.
  • Song reference: Use an existing song as inspiration for the generation.
  • Professional audio quality: Configurable bitrate and sample rate for studio-grade output.
  • Section tag support: Structure your song with [intro], [verse], [chorus], [bridge], and more.

Parameters

ParameterRequiredDescription
lyricsNoSong lyrics with section tags (e.g., [intro], [verse], [chorus]).
bitrateNoAudio bitrate in bps (default: 256000).
sample_rateNoAudio sample rate in Hz (default: 44100).
songNoReference song for style guidance (upload or public URL).
voiceNoVoice reference for vocal cloning (upload or public URL).
instrumentalNoInstrumental reference for musical style (upload or public URL).

Supported Section Tags

Use these tags to structure your lyrics:

TagPurpose
[intro]Opening instrumental or vocal intro
[verse]Main storytelling sections
[chorus]Repeated hook or refrain
[bridge]Transitional section
[outro]Closing section
[break]Instrumental break

How to Use

  1. Write your lyrics — use section tags like [intro], [verse], [chorus] to structure the song.
  2. Upload a reference song (optional) — provide a song for overall style guidance.
  3. Upload a voice reference (optional) — clone a specific vocal style.
  4. Upload an instrumental (optional) — guide the musical arrangement.
  5. Adjust audio settings (optional) — configure bitrate and sample rate.
  6. Click Run and wait for your song to generate.
  7. Preview and download the result.

Example Lyrics Format

[intro]

[verse]
The map is worn, the ink is thin
A journey waiting to begin
The compass spins, the stars align
I'm looking for a hidden sign

[chorus]
We're chasing horizons...

Best Use Cases

  • Original Songwriting — Generate complete songs from your lyrics.
  • Voice Cloning — Create songs in a specific vocal style.
  • Music Production — Produce demos with professional audio quality.
  • Cover Creation — Remix songs with new vocals or arrangements.
  • Content Creation — Generate unique music for videos and projects.

Pricing

OutputPrice
Per song$0.35

Pro Tips for Best Quality

  • Structure lyrics with clear section tags for better song organization.
  • Use high-quality voice references for better vocal cloning results.
  • Provide an instrumental reference that matches your desired genre and mood.
  • Keep lyrics concise — around 600 characters maximum works best.
  • Combine voice and instrumental references for maximum control over the output.

Notes

  • Ensure uploaded audio URLs are publicly accessible.
  • Processing time varies based on song length and current queue load.
  • Please ensure your content complies with usage guidelines.
Note:This website uses AI models provided by third parties.

Music 01 API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/music-01 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Music 01 below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "bitrate": 256000,
    "sample_rate": 44100
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/minimax/music-01" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/minimax/music-01";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "bitrate": 256000,
        "sample_rate": 44100
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "bitrate": 256000,
    "sample_rate": 44100
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/minimax/music-01", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Music 01 API — Frequently asked questions

What is the Music 01 API?

Music 01 is a MiniMax model for audio generation, exposed as a REST API on WaveSpeedAI. Minimax Music-01 Synthesizes Accompaniment And Vocals Simultaneously To Produce Complete Songs Across Diverse Styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Music 01 API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/minimax/minimax-music-01.

How much does Music 01 cost per run?

Music 01 starts at $0.35 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Music 01 accept?

Key inputs: `bitrate`, `instrumental`, `lyrics`, `sample_rate`, `song`, `voice`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/minimax/minimax-music-01.

How long does Music 01 take to generate?

Median end-to-end generation time on WaveSpeedAI is around 51 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Music 01 outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (MiniMax). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Music 01 | Realistic Voice & TTS API | WaveSpeedAI