{
  "id": 6451,
  "url": "https://arxiv.org/abs/2604.01929v3",
  "title": "Woosh: A Sound Effects Foundation Model",
  "summary": "The audio research community depends on open generative models as foundational tools for building novel approaches and establishing baselines. In this report, we present Woosh, Sony AI's publicly released sound effect foundation model, detailing its architecture, training process, and an evaluation against other popular open models. Being optimized for sound effects, we provide (1) a high-quality audio encoder/decoder model and (2) a text-audio alignment model for conditioning, together with (3)",
  "authors": "Gaëtan Hadjeres, Marc Ferras, Khaled Koutini, Benno Weck, Alexandre Bittar, Thomas Hummel et al.",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-02T11:49:00.000Z",
  "fetched_at": "2026-07-14T16:32:28.612Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6451",
  "original_url": "https://arxiv.org/abs/2604.01929v3",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}