{
    "@context": "https://schema.org",
    "@type": "Dataset",
    "name": "SozAI transcript library — index",
    "description": "Facets and counts over the YouTube transcripts published at sozai.app: how many there are, what they are about, what language they are in, and how to search them. The transcripts themselves are not in this file.",
    "source": "https://sozai.app/transcript/",
    "generated": "2026-09-21T09:51:21+00:00",
    "licence": {
        "name": "Creative Commons Attribution 4.0 International",
        "id": "CC-BY-4.0",
        "url": "https://creativecommons.org/licenses/by/4.0/",
        "attribution": "SozAI — https://sozai.app"
    },
    "licence_note": "The CC BY licence covers THIS FILE — the counts, the facets and the descriptions. It does not cover the transcripts themselves: those are the words of the people who made the videos, published here as a reference index, and the rights in them stay with their authors. Takedown route: https://sozai.app/dmca/",
    "transcript_count": 21669,
    "channel_count": 11502,
    "topic_count": 20,
    "topics": [
        {
            "slug": "science-education",
            "name": "Science & Education",
            "count": 2130,
            "url": "https://sozai.app/transcripts/topic/science-education/"
        },
        {
            "slug": "psychology",
            "name": "Psychology & Self-Development",
            "count": 1048,
            "url": "https://sozai.app/transcripts/topic/psychology/"
        },
        {
            "slug": "business",
            "name": "Business & Startups",
            "count": 894,
            "url": "https://sozai.app/transcripts/topic/business/"
        },
        {
            "slug": "news-politics",
            "name": "News & Politics",
            "count": 870,
            "url": "https://sozai.app/transcripts/topic/news-politics/"
        },
        {
            "slug": "music",
            "name": "Music",
            "count": 842,
            "url": "https://sozai.app/transcripts/topic/music/"
        },
        {
            "slug": "tech-ai",
            "name": "Tech & AI",
            "count": 841,
            "url": "https://sozai.app/transcripts/topic/tech-ai/"
        },
        {
            "slug": "religion",
            "name": "Religion & Spirituality",
            "count": 763,
            "url": "https://sozai.app/transcripts/topic/religion/"
        },
        {
            "slug": "software-howto",
            "name": "Software How-To",
            "count": 633,
            "url": "https://sozai.app/transcripts/topic/software-howto/"
        },
        {
            "slug": "film-tv",
            "name": "Film & TV",
            "count": 631,
            "url": "https://sozai.app/transcripts/topic/film-tv/"
        },
        {
            "slug": "health-fitness",
            "name": "Health & Fitness",
            "count": 596,
            "url": "https://sozai.app/transcripts/topic/health-fitness/"
        },
        {
            "slug": "money",
            "name": "Money & Investing",
            "count": 584,
            "url": "https://sozai.app/transcripts/topic/money/"
        },
        {
            "slug": "lifestyle",
            "name": "Lifestyle",
            "count": 461,
            "url": "https://sozai.app/transcripts/topic/lifestyle/"
        },
        {
            "slug": "society",
            "name": "Society & Culture",
            "count": 459,
            "url": "https://sozai.app/transcripts/topic/society/"
        },
        {
            "slug": "gaming",
            "name": "Gaming",
            "count": 449,
            "url": "https://sozai.app/transcripts/topic/gaming/"
        },
        {
            "slug": "language-learning",
            "name": "Language Learning",
            "count": 438,
            "url": "https://sozai.app/transcripts/topic/language-learning/"
        },
        {
            "slug": "stories",
            "name": "Stories & Audiobooks",
            "count": 388,
            "url": "https://sozai.app/transcripts/topic/stories/"
        },
        {
            "slug": "astrology",
            "name": "Astrology & Esoterica",
            "count": 355,
            "url": "https://sozai.app/transcripts/topic/astrology/"
        },
        {
            "slug": "career",
            "name": "Career & Job Search",
            "count": 328,
            "url": "https://sozai.app/transcripts/topic/career/"
        },
        {
            "slug": "sports",
            "name": "Sports",
            "count": 178,
            "url": "https://sozai.app/transcripts/topic/sports/"
        },
        {
            "slug": "food",
            "name": "Food & Cooking",
            "count": 122,
            "url": "https://sozai.app/transcripts/topic/food/"
        }
    ],
    "languages": [
        {
            "slug": "english",
            "name": "English",
            "count": 7739
        },
        {
            "slug": "russian",
            "name": "Russian",
            "count": 4560
        },
        {
            "slug": "spanish",
            "name": "Spanish",
            "count": 1262
        },
        {
            "slug": "polish",
            "name": "Polish",
            "count": 1050
        },
        {
            "slug": "arabic",
            "name": "Arabic",
            "count": 828
        },
        {
            "slug": "hindi",
            "name": "Hindi",
            "count": 810
        },
        {
            "slug": "french",
            "name": "French",
            "count": 632
        },
        {
            "slug": "indonesian",
            "name": "Indonesian",
            "count": 589
        },
        {
            "slug": "portuguese",
            "name": "Portuguese",
            "count": 531
        },
        {
            "slug": "japanese",
            "name": "Japanese",
            "count": 444
        },
        {
            "slug": "korean",
            "name": "Korean",
            "count": 416
        },
        {
            "slug": "ukrainian",
            "name": "Ukrainian",
            "count": 359
        },
        {
            "slug": "german",
            "name": "German",
            "count": 351
        },
        {
            "slug": "italian",
            "name": "Italian",
            "count": 283
        },
        {
            "slug": "chinese",
            "name": "Chinese",
            "count": 274
        },
        {
            "slug": "tamil",
            "name": "Tamil",
            "count": 218
        },
        {
            "slug": "turkish",
            "name": "Turkish",
            "count": 150
        },
        {
            "slug": "bengali",
            "name": "Bengali",
            "count": 144
        },
        {
            "slug": "iw",
            "name": "Iw",
            "count": 111
        },
        {
            "slug": "vietnamese",
            "name": "Vietnamese",
            "count": 109
        },
        {
            "slug": "thai",
            "name": "Thai",
            "count": 108
        },
        {
            "slug": "ur",
            "name": "Ur",
            "count": 90
        },
        {
            "slug": "dutch",
            "name": "Dutch",
            "count": 86
        },
        {
            "slug": "swedish",
            "name": "Swedish",
            "count": 61
        },
        {
            "slug": "none",
            "name": "None",
            "count": 60
        },
        {
            "slug": "kazakh",
            "name": "Kazakh",
            "count": 40
        },
        {
            "slug": "fa",
            "name": "Fa",
            "count": 27
        },
        {
            "slug": "romanian",
            "name": "Romanian",
            "count": 24
        },
        {
            "slug": "fil",
            "name": "Fil",
            "count": 20
        },
        {
            "slug": "hebrew",
            "name": "Hebrew",
            "count": 20
        }
    ],
    "language_note": "The language of the video, detected from its captions, not the language of the interface. Facets with fewer than 20 transcripts are omitted.",
    "access": {
        "browse": "https://sozai.app/transcript/",
        "search": {
            "url_template": "https://sozai.app/transcript/?s={query}",
            "note": "Full-text search over the published transcripts."
        },
        "topic_hub": "https://sozai.app/transcripts/topic/{topic_slug}/",
        "per_transcript": {
            "html": "https://sozai.app/transcript/{slug}/",
            "markdown": "https://sozai.app/transcript/{slug}/index.md",
            "note": "Every transcript page carries the full text with timestamps, and — where enrichment has run — a summary, chapters and an FAQ. The markdown twin of any page is the same content at roughly a tenth the bytes."
        },
        "generate_new": {
            "url": "https://sozai.app/youtube-transcript/",
            "note": "Paste a YouTube link to fetch a transcript that is not in the library yet. Rate-limited to 10 an hour per IP."
        }
    },
    "caveats": [
        "Captions are what the library is built from. Where a video has only machine-generated captions, the transcript inherits their errors.",
        "A transcript page is not affiliated with, endorsed by or licensed from the channel that made the video.",
        "Topic hubs and language hubs are noindex by design and are navigation, not content."
    ]
}