Magnifying Glass with Paw

Audiobox

Background
Thumbnail

Description

Audiobox is Meta’s foundation research model for audio generation, allowing users to create voices and sound effects through voice inputs and natural language text prompts. This innovative tool empowers anyone to generate custom audio for various applications, from storytelling to sound design. The Audiobox family includes specialized models like Audiobox Speech and Audiobox Sound, all built on the shared self-supervised model, Audiobox SSL. Users can explore different capabilities through interactive demos and create original audio stories with Audiobox Maker.