The Patchbay_

AI Music Generation

The fast-moving world of generating music with machine learning — from prompt-to-song web apps like Suno and Udio to open models like MusicGen and Stable Audio you run in code. This hub explains the landscape, compares the tools, and links hands-on setup guides.

Hands-on tutorials

Full walkthroughs for running each open model yourself — install, every generation parameter, troubleshooting and licensing.

Before you start

Two constraints decide which of these models you can actually use. Both are collected as reference tables.

GPU & VRAM RequirementsWhat every open model actually needs — documented figures separated from estimates.Model Licensing MatrixCode licence vs weights licence for every model, and what non-commercial really rules out.

The tools at a glance

ToolTypeAccessLicence / costVocalsBest for
SunoText → songWeb app + APISubscriptionYesFull songs with vocals from a prompt
UdioText → songWeb appSubscriptionYesHigh-fidelity songs with fine control
MusicGenText / melody → instrumentalLocal (Python)Open, non-commercial weightsNoSelf-hosted instrumental generation — tutorial
Stable Audio OpenText → audioLocal (Python)Open (community licence)NoLocal loops, textures and SFX — tutorial
Stable AudioText → audioWeb app + APISubscriptionNoCommercially-cleared audio and SFX
RiffusionText → musicLocal (Python)OpenRAIL-M weightsNoSpectrogram-based experiments (unmaintained)
YuE2Lyrics → score → songLocal (Python)Non-commercial weightsYesEditable compositions, best open song quality — tutorial
ACE-StepText → musicLocal (Python)Open (Apache-2.0)YesFast open generation for products — tutorial
MagentaSymbolic / MIDILocal (Python)Open (Apache-2.0)NoResearch and MIDI generation
RAVENeural synthesisLocal (Python)Open, non-commercialNoReal-time timbre transfer in a DAW

The main kinds of AI music tool

Background reading

How to choose

Licensing & ethics. Open code is not the same as open weights: several models (MusicGen, RAVE) release weights under non-commercial licences, so check before selling output. Web services set their own commercial terms per plan. And be transparent when a track is AI-generated — some platforms require it, and listeners increasingly expect it.

See the whole ML & generative category in the directory, or the wider tools directory.