AudioSR2023music
AudioSR Upscaler - AudioSR
Model card for the AudioSR restoration preset in Neural Analog (Audio SR, 2022)
Available in Studio. Uses standard processing minutes.
AudioSR Description
Regenerates high frequencies above the selected cutoff while keeping lower frequencies from the original audio. Recommended for: Low quality recordings, missing high frequencies, hissing noise around 10Khz (hihats, voice, suno hiss). 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 Parameters
| Key | Label | Options | Description |
|---|---|---|---|
| frequency_cutoff | Strength | Very Subtle (16 kHz cutoff) (16000), Subtle (13 kHz cutoff) (13000), Mild (10 kHz cutoff) (10000), Medium (8 kHz cutoff) (8000), Pronounced (5 kHz cutoff) (5000), Strong (4 kHz cutoff) (4000), Very Strong (3 kHz cutoff) (3000) | Sets where AudioSR starts regenerating high frequencies. Lower cutoffs regenerate more of the track for a stronger effect; higher cutoffs focus on the top end for a subtler, more nuanced result. |
| reconstruction_method | Reconstruction | Multiband Ensemble (multiband_ensemble), Seamless Reconstruction (original_signal) | No additional help text. |
| stereo_mode | Channels | Mono (single_pass), Stereo (Mid/Sides) (mid_sides) | No additional help text. |