MusicLM

MusicLM

MusicLM

Oct 12, 2023

MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes. Their experiments show that MusicLM outperforms previous systems in audio quality and adherence to the text description. Moreover, we demonstrate that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melodies according to the style described in a text caption. To support future research, we publicly release MusicCaps, a dataset composed of 5.5k music-text pairs, with rich text descriptions provided by human experts.

Tag:

audio editing

Pricing Model:

Free

Cost:

Contact for Pricing

Visit Page

Visit Page

Share this app

Share this app

Share this app

Share on X
Share on X
Share on Facebook
Share on Facebook
Share on LinkedIn
Share on LinkedIn

©ftools 2023

© 2023 ftools.info. All rights reserved