DiffSinger and DiffGAN-TTS
These are ecosystem siblings—both are PyTorch implementations of diffusion-based speech synthesis architectures (DiffSinger for singing and DiffGAN-TTS for general TTS) from the same author that share similar technical foundations but target different synthesis tasks.
About DiffSinger
keonlee9420/DiffSinger
PyTorch implementation of DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (focused on DiffSpeech)
This tool helps vocal synthesis artists and audio producers create realistic singing voices from text. You input written lyrics or phrases, and it generates high-quality audio of a synthesized voice singing those words. This is ideal for musicians, content creators, or voiceover artists looking to produce unique vocal tracks.
About DiffGAN-TTS
keonlee9420/DiffGAN-TTS
PyTorch Implementation of DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs
DiffGAN-TTS helps creators, educators, and content producers transform written text into high-quality, natural-sounding spoken audio. You input text, and it generates audio files of a single speaker or multiple speakers, with options to control elements like pitch and speaking rate. This is ideal for anyone who needs to quickly create voiceovers or spoken content from text.
Scores updated daily from GitHub, PyPI, and npm data. How scores work