Metadata-Version: 2.4
Name: tts_webui_extension.vocos
Version: 0.0.3
Summary: Vocos is a neural audio codec for high-quality audio compression and reconstruction
Home-page: https://github.com/rsxdalv/tts_webui_extension.vocos
Author: rsxdalv
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: vocos==0.1.0
Dynamic: author
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license-file
Dynamic: requires-dist
Dynamic: summary

# Extension adapter for Vocos

License - the source code within this repository is licensed under the MIT license.

This extension provides a neural audio codec for high-quality audio compression and reconstruction.

## Features

- Compress audio to various bitrates (1.5, 3.0, 6.0, or 12.0 kbps)
- Reconstruct high-quality audio from compressed representations
- Simple and intuitive interface
- Support for various audio file formats

## Usage

1. Upload an audio file (WAV, MP3, etc.)
2. Select the desired bandwidth (compression level) in kbps
3. Click "Reconstruct" to process the audio
4. Listen to or download the reconstructed audio

## About Vocos

Vocos is a neural audio codec developed by charactr that can compress audio to very low bitrates while maintaining high perceptual quality. It uses a neural network to encode and decode audio signals, providing better quality than traditional codecs at similar bitrates.

For more information, visit the [official Vocos repository](https://github.com/charactr-platform/vocos).
