A self‑hosted semantic audio search stack that indexes your sound library, auto‑tags files, and lets you find and preview audio with natural‑language queries.

Stack: FastAPI (Python) · CLAP embeddings · Qdrant vector DB · SQLite · Gradio UI · Docker

• Semantic search: Type things like “applause” or “bad feedback buzzer” and get the right sounds first.
• Auto‑metadata: Lightweight auto‑tagging powered by text–audio similarity. Optionally merges with your own tags/descriptions.
• Hybrid ranking: Combines vector similarity with keyword matches (filename, tags, description).
• Library sync: Reindex or incremental rescan to keep Qdrant and SQLite in sync with your library folder.
• Inline preview: Play audio directly in the UI and copy/download the file URL.
• Simple admin: Edit tags/description, delete tracks, bulk update via API.