UniverSR2026music
UniverSR Upscaler - UniverSR
Model card for the UniverSR restoration preset in Neural Analog (UniverSR, 2026)
6x
Available in Studio. Consumes 6x the processing minutes.
UniverSR Description
Upscale music, voice, and sound effects. UniverSR is a 2026 model developed by the University of Seoul which performs audio super-resolution directly in the complex STFT domain using flow matching. Very similar to AudioSR, but with more coherent high ends. Recommended for: Low quality recordings, missing high frequencies, hissing noise around 10Khz (hihats, voice, suno hiss). Low thresholds (eg: 4Khz) will change audio the most, while high threshold will preserve what's already here. Not recommended for: muddy bass or muddy low end. Use Neural Remix instead.
UniverSR Architecture
UniverSR Parameters
| Key | Label | Options | Description |
|---|---|---|---|
| model_name | Model | Original (universr-audio), Fine-tune v1 (universr-audio-finetune-v1, 9x) | No additional help text. |
| frequency_cutoff | Strength | Subtle (12 kHz cutoff) (12000), Medium (8 kHz cutoff) (8000), Pronounced (6 kHz cutoff) (6000), Strong (4 kHz cutoff) (4000) | No additional help text. |
| stereo_mode | Channels | Stereo (Mid/Sides) (mid_sides), Stereo (L/R) (left_right), Mono (single_pass) | No additional help text. |
| reconstruction_method | Reconstruction | Seamless Reconstruction (original_signal), Original Reconstruction (original) | No additional help text. |