Quick start

From an empty device to your first take in five steps.

1. Start the server. Open Start MIDI-GPT Server (on the Desktop, or in the MIDI-GPT folder's Server folder; see Install); the first start downloads the model with your Hugging Face token. On the device's SETUP page, the light next to the address turns green when the server answers.
2. Add the device. In Live's browser, open User Library › MIDI-GPT and drag MIDI-GPT onto any track. Click the key on the device to open its window.
3. Tell it your instruments. Run SETUP › SETUP ALL once per set. MIDI-GPT guesses each track's instrument from its device and name, lets you confirm each guess, and saves it on the track. See Setup.
4. Choose what to write. Select a scene with some MIDI clips. In the roll at the top of the window, paint the bars to generate on a track, or turn on AR to write the whole track.
5. Generate. Press GENERATE. When it is done, the result is already playing in your clips: step through the takes, then press KEEP.

Where to go next

The interface guide explains every control, and Workflows shows the common ways to use them together.