Minimax Music 02

Minimax Music 02

Playground

Minimax Music-02 is a compact, fast, cost-effective MoE music generator (230B params, 10B active) for high-quality music production. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

MiniMax Music 02

MiniMax Music 02 is an AI music generation model that turns a style prompt + lyrics into a complete song. Describe the mood, genre, and vocal style, paste your lyrics, and the model produces fully arranged audio with vocals and backing instruments.

What it can do

• Prompt-guided composition Generate songs from natural language prompts like “melancholic indie dream-pop with soft male vocals and light guitars.”

• Lyric-aware singing Paste structured lyrics (verses, chorus, bridge) and the model sings them, aligning melody and phrasing to your text.

• Full arrangement Produces a mixed track with vocals, backing instruments, and effects — ready for demos, temp tracks, or creative exploration.

• Configurable audio quality Supports multiple bitrates and sample rates (e.g., 256 kbps, 44.1 kHz) so you can balance quality and file size.

Inputs

• prompt (required) Musical description: genre, mood, instrumentation, vocal style, atmosphere.

• lyrics (required) The words to sing. You can structure them by sections (Verse, Chorus, Bridge) using plain text.

• bitrate Target audio bitrate, e.g. 256000 for 256 kbps.

• sample_rate Audio sample rate, e.g. 44100 Hz.

• Output: A single audio file (song) matching your prompt and lyrics.

Pricing

• Per run just needs $0.03!

How to use

1. Write a prompt describing style, mood, tempo, instruments, and vocal character.
2. Paste your lyrics, with simple section labels if helpful (Verse, Chorus, Bridge).
3. Choose bitrate and sample_rate according to your quality needs.
4. Click Run to generate the song, then listen in the preview panel and download the audio.

Tips for better songs

• Keep prompts concise but specific: mention genre, mood, and key instruments.
• Structure lyrics into short lines and clear sections to improve phrasing.
• For more “radio-ready” sound, use higher bitrate and standard 44.1 kHz sample rate.
• Iterate: tweak only one aspect of the prompt at a time (e.g., “more reverb”, “slower tempo”) to refine the sound.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/minimax/music-02" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "lyrics": "",
    "bitrate": 256000,
    "sample_rate": 44100
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"