You're looking at a specific version of this model. Jump to the model overview.

malerlab /u-must-midi-to-audio:b642c172

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
midi
string
Piano MIDI file (.mid).
window_sec
number
18

Min: 8

Max: 20

Generation window length in seconds (the model was trained on 19-20 s slices).
overlap_sec
number
2

Max: 6

Overlap between windows; its generated audio primes the next window.
max_duration_sec
number
0
Only render the first N seconds of the MIDI; 0 = whole file.
seed
integer
0
Random seed.
reference
boolean
True
Also return the input MIDI rendered with a General MIDI soundfont, for comparison.

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'properties': {'audio': {'format': 'uri', 'title': 'Audio', 'type': 'string'},
                'duration_sec': {'title': 'Duration Sec', 'type': 'number'},
                'n_tokens': {'title': 'N Tokens', 'type': 'integer'},
                'notes': {'title': 'Notes', 'type': 'string'},
                'reference_audio': {'format': 'uri',
                                    'nullable': True,
                                    'title': 'Reference Audio',
                                    'type': 'string'}},
 'required': ['audio', 'duration_sec', 'n_tokens', 'notes'],
 'title': 'Output',
 'type': 'object'}