neural analog
All restoration models
AudioSR2023music

AudioSR Upscaler - AudioSR

Model card for the AudioSR restoration preset in Neural Analog (Audio SR, 2022)

Try modelarXiv paper

Available in Studio. Uses standard processing minutes.

AudioSR Description

Regenerates high frequencies above the selected cutoff while keeping lower frequencies from the original audio. Output sample rate: 48kHz. Recommended for: Low quality recordings, missing high frequencies, hissing noise around 12-13Khz (hihats, sibilance, brilliance). Low thresholds (eg: 3Khz) will change audio the most, while high threshold will mostly preserve what's already here. Not recommended for: Bass tracks, muddy low end. Use Neural Remix instead.

AudioSR Architecture

AudioSR architecture

AudioSR Parameters

KeyLabelOptionsDescription
frequency_cutoffFrequency Cutoff16Khz (16000), 13Khz (13000), 10Khz (10000), 8Khz (8000), 5Khz (5000), 4Khz (4000), 3Khz (3000)No additional help text.
stereo_modeChannelsMono (single_pass), Stereo (Mid/Sides) (mid_sides)No additional help text.