---
title: "VoiceFixer"
emoji: 🩹
colorFrom: green
colorTo: indigo
sdk: gradio
sdk_version: 6.24.0
app_file: app.py
pinned: false
license: mit
short_description: Restores degraded speech of any kind
tags:
  - category:enhancement
  - subcategory:restoration
  - input:audio
  - output:audio
  - sample-rate:44100
  - channels:mono
  - speech
---

# VoiceFixer

VoiceFixer aims to restore human speech regardless how serious its degraded. It can handle noise, reverberation, low resolution (2kHz~44.1kHz) and clipping (0.1-1.0 threshold) effect within one model.

A HARP deployment. See https://github.com/TEAMuP-dev/HARP