MIDI-GPT for Live¶
A multitrack MIDI generation machine for Ableton Live. MIDI-GPT for Live is a free, open-source Max for Live device that writes MIDI into your clips with MIDI-GPT, a transformer for computer-assisted multitrack composition. It reads every MIDI clip in the selected scene as context, generates the bars you choose, and writes the result back as takes you can audition, revert or keep.
Beta
MIDI-GPT for Live is in beta. It works, but it hasn't been used on many machines or sets yet, and some combinations of settings still go wrong. Please report what you find, small things too.
- Fill in bars. Paint the bars to rewrite on any track. The rest of the scene stays as it is and is used as context.
- Continue or create tracks. Turn on AR to write a whole track, including one that has no clip yet.
- Steer the output. Polyphony, note length, density, scale, register, rhythm and remix per track; temperature, top-p, top-k and seed for the whole request.
- Takes. Generate up to 16 versions at once, switch between them while the music plays, go back to the original, or keep one.
- Runs on your computer. The model runs in a local server, with no GPU needed. Nothing leaves your machine unless you point the device at a server elsewhere.
Requirements¶
| Ableton Live | 11 or 12: Suite, or Standard with the Max for Live add-on |
| Max | the Max bundled with Live: 8.6 (Live 11 to 12.1) or 9 (Live 12.2 and later) |
| System | macOS, Windows or Linux (the Windows and Linux installers are untested) |
| Server | Python 3.10–3.14 (3.10–3.12 on Intel Macs) and midigpt 0.4.2, which the installer sets up |
| Disk | about 1 GB for the server, plus the model: 83 MB (yellow_small) or 350 MB (yellow_medium) |
Watch the full trailer¶
A 1:39 tour of every feature.
MIDI-GPT for Live is made by the Metacreation Lab for Creative AI at Simon Fraser University. Its companion is MIDI-GPT for REAPER.