{
  "$schema": "https://schema.org",
  "@context": "https://schema.org",
  "@type": "DataCatalog",
  "@id": "https://blomega.com/explore-ots-datasets#catalog",
  "name": "BLOMEGA Off-the-Shelf (OTS) Dataset Catalog",
  "url": "https://blomega.com/explore-ots-datasets",
  "description": "Off-the-shelf AI training datasets across video, audio/speech, text/NLP, images, documents, booking emails, and multilingual localization. Consent-verified and license-clear.",
  "publisher": { "@type": "Organization", "name": "BLOMEGA", "url": "https://blomega.com/", "email": "hello@blomega.com" },
  "dateModified": "2026-08-13",
  "measurementTechnique": "Consent-based collection with full chain of title; see https://blomega.com/data-provenance",
  "categories": [
    "Video",
    "Audio",
    "Emails",
    "Text & NLP",
    "Images",
    "Documents",
    "Localization",
    "Specialized formats",
    "Media"
  ],
  "highlights": {
    "multilingualConversationsHours": "976K+",
    "meetingRecordingsHours": "99.5K",
    "translationPairsMax": "22.5M (EN-FR)",
    "interviewAudioHours": "10K+ across 24+ accents",
    "bookingEmailCategories": 19,
    "localizationLanguagePairs": "20+"
  },
  "dataset": [
    { "@type": "Dataset", "name": "Multilingual Conversations", "category": "Audio", "size": "976K+ hours" },
    { "@type": "Dataset", "name": "Meeting Recordings", "category": "Video", "size": "99.5K hours", "inLanguage": "en", "description": "Video, audio, transcripts, action items, and recaps across industries." },
    { "@type": "Dataset", "name": "10K+ Hours Real Job Interview Audio (24+ Accents)", "category": "Audio", "size": "100 GB", "description": "Consented multi-accent interview audio for ASR/LLMs." },
    { "@type": "Dataset", "name": "English Animation Videos", "category": "Video", "size": "8.5K hours", "inLanguage": "en" },
    { "@type": "Dataset", "name": "Food Videos", "category": "Video", "size": "5K hours", "inLanguage": "en" },
    { "@type": "Dataset", "name": "Thai Media Content Videos", "category": "Video", "size": "3.1K hours", "inLanguage": "th" },
    { "@type": "Dataset", "name": "Multi-Person Social Interaction", "category": "Video", "size": "478K clips" },
    { "@type": "Dataset", "name": "Domestic Animal Behavior", "category": "Video", "size": "408K clips" },
    { "@type": "Dataset", "name": "Doctor Appointment Emails", "category": "Emails", "size": "7,470 emails", "description": "Confirmation, cancellation, and modification booking emails." },
    { "@type": "Dataset", "name": "English–French Translation Pairs", "category": "Localization", "size": "22.5M sentence pairs", "inLanguage": ["en", "fr"], "isAccessibleForFree": true, "source": "Kaggle" },
    { "@type": "Dataset", "name": "Europarl Parallel Corpus", "category": "Localization", "size": "2M pairs across 21 EU languages", "isAccessibleForFree": true },
    { "@type": "Dataset", "name": "Multilingual UN Parallel Corpus", "category": "Localization", "size": "11M pairs across 6 official languages", "isAccessibleForFree": true },
    { "@type": "Dataset", "name": "DICOM Medical Imaging Dataset with Clinical Reports", "category": "Images", "description": "Healthcare DICOM imaging paired with clinical reports." },
    { "@type": "Dataset", "name": "Industrial Electric Motor Thermography", "category": "Images", "size": "5.8K images", "description": "Thermographic inspection imagery for predictive maintenance." },
    { "@type": "Dataset", "name": "Multimodal Dataset for Household Robotics", "category": "Specialized formats", "description": "3D and Lidar multimodal household robotics data." }
  ],
  "note": "Representative selection. The full, filterable catalog (120+ datasets) is browsable at https://blomega.com/explore-ots-datasets. Contact hello@blomega.com for licensing and complete specifications."
}