{"slug":"laion/clap-htsat-fused","title":"CLAP HTSAT Fused","description":"A contrastive language-audio pretraining model using HTSAT audio encoder, enabling zero-shot audio classification and retrieval.","provider":"laion","model_type":"multimodal","status":"active","context_window":null,"max_output_tokens":null,"pricing":null,"modalities":["audio","text"],"capabilities":[],"knowledge_cutoff":null,"release_date":"2023-03-01T00:00:00.000Z","deprecation_date":null,"retirement_date":null,"aliases":[],"homepage":"https://huggingface.co/laion/clap-htsat-fused","docs":"https://github.com/LAION-AI/CLAP","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"}