AudioSep is an AI audio source-separation application that extracts user-specified sounds from mixed recordings. It is presented as a browser-based Hugging Face Space for experimenting with text-guided audio separation.
In the Other audio editing space, AudioSep takes a focused approach. It focuses on separating specific sounds or voices from a mixed audio recording. AudioSep is a consumer product aimed at audio researchers and creators. AudioSep is free to use. AudioSep is available on the web, and it can be self-hosted.
It is developed by Audio-AGI. Among its 5 catalogued features are audio separation, text-guided separation, and sound isolation.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do