@AIatMeta
π Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. Weβre sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. π Learn more: https://t.co/FPnfv66UCP