Studio
All restoration models
RE-USE2026voice

Speech Enhancement - RE-USE Upscaler (RE-USE)

Model card for the RE-USE model behind the Speech Enhancement - RE-USE Upscaler preset in Neural Analog.

Try modelarXiv paper
6x

Available in Studio. Consumes 6x the processing minutes.

RE-USE Description

This model dramatically improves speech quality in multiple languages. It recovers high-frequency detail and reduces noise, reverb, and audio defects. For the most difficult restorations of podcasts, voice messages, or singing. Hallucinations are common: use UniverSR or blend with the original audio to improve the result.

RE-USE Parameters

KeyLabelOptionsDescription
stereo_modeChannelsStereo (Mid/Sides) (mid_sides), Sides only (sides_only), Mid only (mid_only), Stereo (L/R) (left_right), Mono (mono)No additional help text.