Music 01 | Realistic Voice & TTS API

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

Parameter	Required	Description
lyrics	No	Song lyrics with section tags (e.g., [intro], [verse], [chorus]).
bitrate	No	Audio bitrate in bps (default: 256000).
sample_rate	No	Audio sample rate in Hz (default: 44100).
song	No	Reference song for style guidance (upload or public URL).
voice	No	Voice reference for vocal cloning (upload or public URL).
instrumental	No	Instrumental reference for musical style (upload or public URL).

Supported Section Tags

Use these tags to structure your lyrics:

Tag	Purpose
[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

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

Output	Price
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.

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; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Music 01 below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/minimax/music-01" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "bitrate": 256000,
    "sample_rate": 44100
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("minimax/music-01", {
        "bitrate": 256000,
        "sample_rate": 44100
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "minimax/music-01",
    {
    "bitrate": 256000,
    "sample_rate": 44100
}
)

print(output["outputs"][0])  # → URL of the generated output

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 prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. 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?

Average end-to-end generation time on WaveSpeedAI is around 49 seconds per request — measured across recent runs. Queue time scales 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.

ExamplesView all

Related Models

README