# CUDA-accelerated inference

BigVGAN is a high-performance neural vocoder that achieves high-quality audio generation through large-scale training, supporting multiple sample rates and frequency band configurations.

BigVGAN is a universal neural vocoder achieved through large-scale training, capable of providing high-quality audio output for tasks such as speech synthesis.

BigVGAN is a large-scale trained universal neural vocoder capable of high-quality mel-spectrogram to waveform conversion. The v2 version accelerates inference through custom CUDA kernels and expands training data diversity.

BigVGAN is a general-purpose neural vocoder trained at scale, capable of generating high-quality audio waveforms from mel spectrograms.

BigVGAN is a high-performance neural vocoder that achieves high-quality audio synthesis through large-scale training, supporting multiple sampling rates and frequency band configurations.