# High-fidelity audio

VoxPolska is an advanced model focused on Polish text-to-speech conversion, capable of generating natural, fluent, and expressive Polish speech.

InspireMusic is a unified toolkit focused on music generation, song generation, and audio generation, featuring high audio quality and long-form music generation capabilities.

An audio denoising and voice enhancement model based on Pytorch, which effectively removes audio noise and improves voice clarity

MusicGen is a text-to-music generation model that supports stereo and melody guidance, capable of producing high-quality music samples based on text descriptions or audio prompts.

Bark is a Transformer-based text-to-audio model created by Suno, capable of generating highly realistic multilingual speech, music, background noise, and simple sound effects.

A Transformer-based text-to-speech model built on fairseq S^2, supporting Simplified Chinese with a single female voice, trained on Common Voice v7 and CSS10 datasets.