Our New SAM Audio Model Transforms Audio Editing

SAM Audio is a new AI model from Meta that enables audio segmentation through text, visual, and time span prompts. Users can isolate specific sounds from complex audio mixtures by typing descriptions, clicking on video objects, or marking time segments. The unified model supports diverse use cases including music editing, podcast production, noise filtering, and accessibility applications. SAM Audio is available to try in the Segment Anything Playground and is downloadable for developers.