This repository contains the official implementation of "WavJourney: Compositional Audio Creation with Large Language Models".
Starting with a text prompt, WavJourney can create audio content with engaging storylines encompassing lifelike speech in context, emotionally resonant music compositions, and impactful sound effects that enhance the auditory experience.
Check the examples and demonstration video in the Demo Page!
We will be releasing the code & software very soon! Please stay tuned for further updates and more details!
If you find this work useful in your method, you can cite the paper below:
@article{liu2023wavjourney,
title = {WavJourney: Compositional Audio Creation with Large Language Models},
author = {Liu, Xubo and Zhu, Zhongkai and Liu, Haohe and Yuan, Yi and Huang, Qiushi and Liang, Jinhua and Cao, Yin and Kong, Qiuqiang and Plumbley, Mark D and Wang, Wenwu},
journal = {arXiv preprint arXiv:2307.14335},
year = {2023}
}