upload some audio (will be randomly trimmed to max of 100s)
Drop File Here
- or -
Click to Upload
or load example audio
input audio
manual controls
▼
periodic prompt
↺
0
13
onset mask width (multiplies with the periodic mask, 1 step ~= 10milliseconds) does not affect mask preview
↺
0
100
beat mask width (milliseconds) does not affect mask preview
↺
1
200
compression prompt
↺
1
14
mask dropout
↺
0
1
feedback steps (token telephone) -- turn it up for better timbre/rhythm transfer quality, but it's slower!
↺
1
8
preset
mask image
extras
▼
pitch shift amount (semitones)
↺
-12
12
time stretch factor
↺
0
8
sampling settings
▼
sample temperature
↺
0.1
10
top p (0.0 = off)
↺
0
1
typical filtering
typical mass (should probably stay between 0.1 and 0.5)
↺
0.01
0.99
typical min tokens (should probably stay between 1 and 256)
↺
1
256
sample cutoff
↺
0
0.9
sampling steps
↺
1
128
seed (0 for random)
model choice
generate (vamp)!!!
output audio 1
use as input (feedback)
output audio 2
use as input (feedback)
api vamp
Input Audio
Drop Audio Here
- or -
Click to Upload
Controls Data
View Controls
Output Audio
Output Labels
Process
Cancel