Descript

GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis

descriptinc

Official repository for the paper "Chunked Autoregressive GAN for Conditional Waveform Synthesis"

descriptinc

Official implementation of the paper WAV2CLIP: LEARNING ROBUST AUDIO REPRESENTATIONS FROM CLIP

descriptinc

Pure JS implementation of the Web Audio API

descriptinc

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

descriptinc

Object-oriented handling of audio data, with GPU-powered augmentations, and more.

descriptinc