Studio
All restoration models
NovaSR2026voice

Speech Enhancement - NovaSR Upscaler (NovaSR)

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

Try modelGitHub

Available in Studio. Uses standard processing minutes.

NovaSR Description

This upscaling model was trained on English speech. Use it to remove the walkie-talkie sound from your podcasts, voice-overs, or isolated vocal tracks.

NovaSR 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.