Skip to content

faxlab/LavaSR-Fast-Enhancer

Repository files navigation

LavaSR Fast Enhancer

LavaSR Fast Enhancer

Make your audio sound clearer, fuller, and more professional — in one click.

Latest Release Windows MIT License

Support on Ko-fi


App Screenshot


What It Does

Got audio that sounds thin, muffled, or low-quality? This app uses an AI model called LavaSR to restore missing detail and bring your audio back to life — then saves it as a clean 48 kHz WAV file, ready for professional use.

It's designed to be fast and simple. Drop your files in, click Enhance, and you're done.

LavaSR is an independent open-source project developed by ysharma3501. This GUI is a separate application that uses it as a backend — all credit for the model and core enhancement technology goes to the LavaSR authors.

LavaSR runs at ~5000× realtime on GPU and ~60× on CPU, fits in ~500 MB VRAM with a ~50 MB model, and outperforms larger diffusion-based models on audio quality benchmarks.


Perfect For

  • Voice recordings that sound narrow or dull
  • Old interviews, podcasts, or phone call recordings
  • Audio samples you want to polish before a mix
  • Batch-cleaning a folder of files before editing

Features

  • One-click enhancement — drop files, press Enhance, done
  • Batch processing — handle multiple files at once, even from different folders
  • Optional denoising — reduce background noise on top of enhancing
  • Drag output directly into your DAW or folder — no hunting through directories
  • Flexible output options — control the output folder, file suffix, and naming
  • Runs offline — no internet needed after the model downloads once

Download & Install

Option A — Installer (recommended)

  1. Go to Releases
  2. Download LavaSR-Fast-Enhancer-Setup-*.exe
  3. Run it and follow the prompts
  4. Open LavaSR Fast Enhancer from your Start Menu or desktop

Option B — Portable (no install needed)

  1. Download LavaSRFastEnhancer-Portable-*.zip from Releases
  2. Extract the ZIP anywhere
  3. Run LavaSRFastEnhancer.exe

First launch: The AI model (~200 MB) will download automatically. This only happens once.


How To Use

  1. Add your files — drag and drop audio files anywhere onto the app, or click Select Files
  2. Adjust settings (optional) — turn on denoising, change output folder, rename suffix
  3. Click Enhance — the app processes everything in the background
  4. Grab your results — drag finished files directly from the output list into your DAW, folder, or wherever you need them

Supported Formats

.wav .mp3 .flac .ogg .m4a .aac .wma .aiff

Keyboard Shortcuts

Shortcut Action
Ctrl + O Select files
Ctrl + Enter Enhance / Cancel
Delete Remove selected files from queue
Ctrl + L Clear the queue

Updates

The app can check for new versions automatically — this is off by default. You can also check manually at any time from the settings area.


Legal


If this tool saves you time, consider supporting development 💙

Support on Ko-fi

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors