{"slug":"facebook/audiobox-aesthetics","title":"AudioBox Aesthetics","description":"A model for predicting audio quality and aesthetic scores, part of the AudioBox family for audio generation evaluation.","provider":"facebook","model_type":"audio","status":"active","context_window":null,"max_output_tokens":null,"pricing":null,"modalities":["audio"],"capabilities":[],"knowledge_cutoff":null,"release_date":"2024-03-01T00:00:00.000Z","deprecation_date":null,"retirement_date":null,"aliases":[],"homepage":"https://huggingface.co/facebook/audiobox-aesthetics","docs":"https://github.com/facebookresearch/audiobox-aesthetics","categories":["ai-ml"],"tags":[],"last_verified":"2026-06-10T00:00:00.000Z","next_check":"2026-09-08T00:00:00.000Z","created_at":"2026-06-09T19:26:57.536Z","updated_at":"2026-06-09T19:26:57.536Z"}