https://www.solosoft.dev/tags/sam-audio/Recent content in SAM-Audio on SoloSoftHugoen-ushttps://www.solosoft.dev/post/audioghost-ai-audio-separation-2026/Mon, 01 Jan 0001 00:00:00 +0000https://www.solosoft.dev/post/audioghost-ai-audio-separation-2026/<p>For decades, isolating a single instrument from a mixed recording required either expensive multi-track access from the original studio session or painstaking spectral editing by an experienced audio engineer. <strong>AudioGhost AI</strong> rewrites this workflow by bringing Meta&rsquo;s state-of-the-art SAM-Audio model to the desktop with a straightforward graphical interface, letting anyone separate sounds with nothing more than a text prompt.</p> <p>Developed by the open-source contributor 0x0funky, AudioGhost AI is a purpose-built wrapper around Meta AI&rsquo;s SAM-Audio research model. SAM-Audio extends the &ldquo;Segment Anything&rdquo; philosophy — originally developed for image segmentation — into the audio domain. The original SAM model made it possible to click on any pixel in an image and isolate that object; SAM-Audio applies the same principle to sound. Describe the sound source you want (&ldquo;the lead vocal,&rdquo; &ldquo;the snare drum,&rdquo; &ldquo;the acoustic guitar,&rdquo;) and the model isolates it from the rest of the mix with impressive fidelity.</p>https://www.solosoft.dev/post/sam-audio-segmentation-2026/Mon, 01 Jan 0001 00:00:00 +0000https://www.solosoft.dev/post/sam-audio-segmentation-2026/<p>The Segment Anything Model (SAM) revolutionized computer vision by enabling prompt-based segmentation of any object in an image. <strong>SAM-Audio</strong> brings this same transformative capability to audio, allowing users to isolate specific sounds from a mixture using natural language descriptions. Instead of saying &ldquo;remove the vocals,&rdquo; you can say &ldquo;extract the acoustic guitar playing in the background.&rdquo;</p> <p>SAM-Audio is Meta&rsquo;s research project that extends the &ldquo;segment anything&rdquo; paradigm from the visual domain into the auditory domain. The model takes a mixed audio signal and a text prompt, then generates a time-frequency mask that isolates the described sound source. This is fundamentally different from traditional sound source separation, which operates on fixed categories like &ldquo;vocals&rdquo; or &ldquo;drums.&rdquo;</p>