SAM Audio

Submitted by @azeem on December 20, 2025

SAM Audio is a unified model that separates any sound from any source. Use text ("dog barking"), visual clicks on video, or time spans to isolate specific audio. It unifies speech, music, and sound effect separation into one promptable model.

Screenshots

SAM Audio - Screenshot 1SAM Audio - Screenshot 2SAM Audio - Screenshot 3SAM Audio - Screenshot 4SAM Audio - Screenshot 5

Related resources

View all