neural analog
All restoration models
AERO2022music

AERO Upscaler - AERO

Model card for the AERO restoration preset in Neural Analog (AERO, 2022)

Try modelarXiv paper

Available in Studio. Uses standard processing minutes.

AERO Description

Spectral super-resolution model with selectable voice and music variants. Output sample rate depends on selected variant: Music (MUSDB)=44.1kHz, Voice 4-16=16kHz, Voice 8-16=16kHz, Voice 8-24=24kHz, Voice 12-48=48kHz. Not recommended for: Bass.

AERO Architecture

AERO architecture

AERO Parameters

KeyLabelOptionsDescription
stereo_modeChannelsStereo (Mid/Sides) (mid_sides), Stereo (L/R) (left_right), Mono (single_pass)No additional help text.
model_nameModel VariantMusic (MUSDB) (music_musedb), Voice 4-16 kHz (voice_4_16), Voice 8-16 kHz (voice_8_16), Voice 8-24 kHz (voice_8_24), Voice 12-48 kHz (voice_12_48)No additional help text.