chattts

Papers using or citing this model 1

• Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers 1.5K citations · 2023 · IEEE Transactions on Audio, Speech, and Language Processing · arXiv

  We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called Vall-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard...