MiniMax Music example output
NEW

MiniMax Music

Generate original music with vocals, lyrics, and style control.

MiniMax Music generates complete audio tracks from a style description and optional lyrics. Describe the mood, genre, and tempo. Add lyrics with structure tags like [Verse], [Chorus], [Bridge] to shape the arrangement. Leave lyrics empty for instrumental tracks. Stereo output at 44.1kHz, 256kbps MP3. From cinematic scores to lo-fi beats to full vocal tracks.

Try these prompts

How it works

01

Describe your vision

Type a detailed prompt or upload a reference sketch, photo, or mood board.

02

Choose your settings

Pick your resolution and aspect ratio. See the credit cost before you generate.

03

Generate in seconds

Your image is delivered in seconds. Download, iterate, or pipe into video.

Ready to create with MiniMax Music?

Jump into the Studio and start generating. Plans from £10/month.

Choose a Plan

Original music for your creative projects

Every video needs a soundtrack. Every presentation needs atmosphere. Every brand needs a sonic identity. But licensing music is expensive, production music sounds generic, and commissioning original tracks takes weeks. MiniMax Music generates complete, original audio tracks in under a minute.

Describe the style: cinematic orchestral, lo-fi chill hop, upbeat electronic, acoustic folk, dramatic trailer music. The model understands genre, mood, tempo, and instrumentation. Add lyrics with structure tags to create vocal tracks with verses, choruses, bridges, and outros. Leave the lyrics field empty for instrumentals.

The output is production-ready: stereo, 44.1kHz sample rate, 256kbps MP3. Use it as background music for architectural walkthroughs, product launch videos, social media content, motion graphics, or any project that needs original audio without the licensing headache.

Vocals and lyrics

Write your lyrics and add structure tags: [Intro], [Verse], [Chorus], [Bridge], [Outro]. MiniMax Music generates a vocal performance that follows the arrangement. The vocal style adapts to the genre description. Up to 3000 characters of lyrics.

Every genre, one model

Electronic, orchestral, jazz, hip-hop, ambient, rock, folk, cinematic. Describe the genre and mood in the style prompt (up to 300 characters) and the model handles instrumentation, arrangement, and production. No switching between specialised tools.

Pairs with your pipeline

Generate visuals with any Stensyl image or video model, add voiceover with ElevenLabs or OpenAI TTS, then layer original music on top. Complete creative projects without leaving the platform. Download as MP3 and drop into any editor.

Frequently asked

Questions about MiniMax Music.

MiniMax Music generates complete audio tracks from a style description and optional lyrics. Describe the mood, genre, and tempo. Add lyrics with structure tags like [Verse], [Chorus], [Bridge] to shape the arrangement. Leave lyrics empty for instrumental tracks. Stereo output at 44.1kHz, 256kbps MP3. From cinematic scores to lo-fi beats to full vocal tracks.
Built differently

Why Stensyl?

A small indie studio building creative tools the way they should be built. No VC theatre, no funnel games, no faceless support.