Vocal Effects Generator

This is a demo of the paper DiffVox: A Differentiable Model for Capturing and Analysing Professional Effects Distributions, accepted at DAFx 2025. In this demo, you can upload a raw vocal audio file (in mono) and use our model to apply professional-quality vocal processing by tweaking generated effects settings to enhance your vocals!

The effects consist of series of EQ, compressor, delay, and reverb. The generator is a PCA model derived from 365 vocal effects presets fitted with the same effects chain. This interface allows you to control the principal components (PCs) of the generator, randomise them, and render the audio.

To give you some idea, we empirically found that the first PC controls the amount of reverb and the second PC controls the amount of brightness. Note that adding these PCs together does not necessarily mean that their effects are additive in the final audio. We found sometimes the effects of least important PCs are more perceptible. Try to play around with the sliders and buttons and see what you can come up with!

Note: To upload your own audio, click X on the top right corner of the input audio block.

-3 3
-3 3
-3 3
-3 3
PC > 4

Select which extra PC to adjust

-3 3
Select Preset (1-365)

Select a preset to load (this will override the current settings)

0 1

Parametric EQ

High Pass

16 5300
0.5 10

Low Shelf

30 200
-12 12

Peak filter 1

33 5400
-12 12
0.2 20

Peak filter 2

200 17500
-12 12
0.2 20

High Shelf

750 8300
-12 12

Low Pass

200 18000
0.5 10

Compressor and Expander

-60 0
1 20
-12 12
0.1 100
50 1000
0 1
-80 0
0 1

Ping-Pong Delay

100 1000
0 1
-80 0
-100 100
-100 100
200 16000
-80 0

FDN Reverb

Low Shelf

30 450
-12 12

Peak filter 1

200 2500
-12 12
0.1 3

Peak filter 2

600 7000
-12 12
0.1 3

High Shelf

1500 16000
-12 12
{
"Direct": {
"PK1": {
"Frequency (Hz)": 888.7962036132812 ,
"Gain (dB)": -3.1757237911224365 ,
"Q": 2.8977291584014893
} ,
"PK2": {
"Frequency (Hz)": 3888.570556640625 ,
"Gain (dB)": 1.4013111591339111 ,
"Q": 0.45586687326431274
} ,
"LS": {
"Frequency (Hz)": 153.35250854492188 ,
"Gain (dB)": 3.4354372024536133
} ,
"HS": {
"Frequency (Hz)": 3491.14990234375 ,
"Gain (dB)": 3.0743632316589355
} ,
"LP": {
"Frequency (Hz)": 17771.548828125 ,
"Q": 0.9646682739257812
} ,
"HP": {
"Frequency (Hz)": 108.44615173339844 ,
"Q": 0.9462385177612305
} ,
"DRC": {
"Attack (ms)": 2.839965581893921 ,
"Release (ms)": 200.01295471191406 ,
"Average Coefficient": 0.585992693901062 ,
"Compressor Ratio": 3.544210433959961 ,
"Expander Ratio": 0.9875312447547913 ,
"Compressor Threshold (dB)": -22.124746322631836 ,
"Expander Threshold (dB)": -51.284175872802734 ,
"Make Up (dB)": 2.408346652984619 ,
"Lookahead (ms)": 0.17572180926799774
} ,
"Panner": {
"Pan": -0.2528190612792969
}
} ,
"Sends": {
"DLY": {
"Delay (ms)": 332.0408020019531 ,
"Feedback (dB)": -8.096531867980957 ,
"Gain (dB)": -31.811790466308594 ,
"Odd delays": {
"Pan": -7.022196054458618
} ,
"Even delays": {
"Pan": -16.42267107963562
} ,
"LP": {
"Frequency (Hz)": 3546.636474609375 ,
"Q": 0.6616478562355042
}
} ,
"FDN": {
"T60 (s)": {
"0.00 Hz": 1.1763983964920044 ,
"459.38 Hz": 1.7094475030899048 ,
"918.75 Hz": 1.7677596807479858 ,
"1378.12 Hz": 1.8048088550567627 ,
"1837.50 Hz": 1.659761905670166 ,
"2296.88 Hz": 1.7533923387527466 ,
"2756.25 Hz": 1.6599433422088623 ,
"3215.62 Hz": 1.6662780046463013 ,
"3675.00 Hz": 1.606208324432373 ,
"4134.38 Hz": 1.3783307075500488 ,
"4593.75 Hz": 1.3532936573028564 ,
"5053.12 Hz": 1.3600809574127197 ,
"5512.50 Hz": 1.34394109249115 ,
"5971.88 Hz": 1.2608695030212402 ,
"6431.25 Hz": 1.2129786014556885 ,
"6890.62 Hz": 1.1818220615386963 ,
"7350.00 Hz": 1.1095601320266724 ,
"7809.38 Hz": 1.0889756679534912 ,
"8268.75 Hz": 1.0175886154174805 ,
"8728.12 Hz": 1.026969313621521 ,
"9187.50 Hz": 0.9993723630905151 ,
"9646.88 Hz": 1.0074224472045898 ,
"10106.25 Hz": 1.019188404083252 ,
"10565.62 Hz": 0.9941813945770264 ,
"11025.00 Hz": 0.9336742758750916 ,
"11484.38 Hz": 0.8342553973197937 ,
"11943.75 Hz": 0.8144983649253845 ,
"12403.12 Hz": 0.7439894080162048 ,
"12862.50 Hz": 0.6655712723731995 ,
"13321.88 Hz": 0.6132201552391052 ,
"13781.25 Hz": 0.5838556885719299 ,
"14240.62 Hz": 0.513392448425293 ,
"14700.00 Hz": 0.4559982120990753 ,
"15159.38 Hz": 0.38198843598365784 ,
"15618.75 Hz": 0.3218803405761719 ,
"16078.12 Hz": 0.2673649489879608 ,
"16537.50 Hz": 0.20177052915096283 ,
"16996.88 Hz": 0.16993345320224762 ,
"17456.25 Hz": 0.1523643285036087 ,
"17915.62 Hz": 0.1395587921142578 ,
"18375.00 Hz": 0.15545517206192017 ,
"18834.38 Hz": 0.3539257347583771 ,
"19293.75 Hz": 1.2214406728744507 ,
"19753.12 Hz": 2.1700596809387207 ,
"20212.50 Hz": 2.56219482421875 ,
"20671.88 Hz": 1.5161553621292114 ,
"21131.25 Hz": 0.5834694504737854 ,
"21590.62 Hz": 0.25141316652297974 ,
"22050.00 Hz": 0.24028468132019043
} ,
"Gain (dB, approx)": -34.898128509521484 ,
"Tone correction PEQ": {
"PK1": {
"Frequency (Hz)": 842.61181640625 ,
"Gain (dB)": 0.7727983593940735 ,
"Q": 1.8633146286010742
} ,
"PK2": {
"Frequency (Hz)": 4641.2265625 ,
"Gain (dB)": 1.5248521566390991 ,
"Q": 0.5597574710845947
} ,
"LS": {
"Frequency (Hz)": 333.4056396484375 ,
"Gain (dB)": 0.9715296626091003
} ,
"HS": {
"Frequency (Hz)": 5922.1455078125 ,
"Gain (dB)": -5.141826152801514
}
}
} ,
"Cross Send (dB)": -5.526805400848389
}
}