Nebius Token Factory
Mini toolsSAM Audio
Model family: SAM
SAM Audio is a state-of-the-art audio separation model in Meta’s Segment Anything collection. It can isolate sources like vocals, instruments or barking dogs from real-world recordings, guided by text prompts, clicks on the sounding object in video, or marked time spans. This unified promptable model makes professional-grade sound isolation, noise filtering and cleanup far more accessible for music, podcast, film and accessibility workflows.
New
Audio
Gen 4
Overview
SAM Audio is Meta’s Segment Anything audio model, a unified system that segments sounds from complex mixes using text, visual and time-span prompts, enabling one-click isolation, noise removal and creative audio editing.
About Meta Platforms
We're connecting people to what they care about, powering new, meaningful experiences, and advancing the state-of-the-art through open research and accessible tooling.
Industry:
Technology, Information and Internet
Company Size:
78.000-79.000
Location:
Menlo Park, California, US
Website:
ai.meta.com
Tools using SAM Audio
No tools found for this model yet.
Last updated: February 3, 2026
