JSON & RAG JSON

INDXR exports two kinds of JSON: standard JSON — the raw segments with a metadata wrapper, free — and RAG JSON — the transcript already cut into short passages (chunks) for RAG (retrieval-augmented generation, where an AI answers using text pulled from your own documents). Each chunk carries a token estimate (roughly how much of a model's input budget its text fills) and a deep link (a YouTube URL that jumps straight to that moment), ready to embed in a vector database — a store that finds passages by meaning rather than exact keywords.

Standard JSON (free)

A metadata wrapper around the transcript segments. Each segment has text, start_time and end_time (both in seconds; end_time is the next segment's start, or its own end for the last), plus a speaker when the transcript is diarised. The wrapper always carries video_id, title, duration_seconds and extracted_at, and adds channel, language, published_at and extraction_method when they are known (a video-file upload has no channel or publish date, so those are omitted). Take this when you want to handle the chunking and indexing yourself; it costs nothing on top of extraction.

{
  "metadata": {
    "video_id": "kBdfcR-8hEY",
    "title": "Justice: What's The Right Thing To Do? Episode 01 …",
    "duration_seconds": 3296,
    "extracted_at": "2026-08-07T15:18:48.032Z",
    "language": "en",
    "extraction_method": "youtube_captions"
  },
  "segments": [
    { "text": "Funding for this program is provided by:", "start_time": 4.2, "end_time": 8.24 },
    { "text": "Additional funding provided by", "start_time": 8.24, "end_time": 33.51 }
  ]
}

RAG JSON (chunked)

RAG JSON merges the segments into overlapping chunks and adds everything a retrieval pipeline needs. The top-level metadata.chunking_config records the chunk size, the overlap (about 15% of the chunk size), the overlap strategy, and the total chunk count.

Chunk fields

• chunk_index / chunk_id — position and a stable id (<video_id>_chunk_000)
• text — the chunk text (including the overlap carried from the previous chunk)
• start_time / end_time — the chunk's time range in seconds
• deep_link — https://youtu.be/<id>?t=N, jumps to the chunk's start
• token_count_estimate — words × 1.33
• metadata — video id, title, channel (null when the source has no channel, e.g. a video-file upload), language, chunk index, total chunks, time range

Overlap strategy

For AI transcription the overlap snaps to whole sentences (overlap_strategy: sentence_boundary); for auto-captions it snaps to whole segments (segment_boundary). The example below is auto-captions, so chunk 1 opens by repeating the tail of chunk 0 ("…they will all die let's assume you know that for sure") — that repeated run is the overlap.

Chunk size presets

You choose the target chunk length when you export — 30, 60, 90, 120 seconds. Sixty seconds is the default. Shorter chunks are tighter and better for pulling exact quotes; longer chunks keep more surrounding context per vector. Your preferred size is remembered in Settings.

{
  "metadata": {
    "video_id": "kBdfcR-8hEY",
    "title": "Justice: What's The Right Thing To Do? Episode 01 …",
    "duration_seconds": 3296,
    "extracted_at": "2026-08-07T15:18:48.032Z",
    "chunking_config": {
      "chunk_size_seconds": 60,
      "overlap_seconds": 9,
      "overlap_strategy": "segment_boundary",
      "total_chunks": 60
    },
    "language": "en",
    "extraction_method": "youtube_captions"
  },
  "chunks": [
    {
      "chunk_index": 0,
      "chunk_id": "kBdfcR-8hEY_chunk_000",
      "text": "Funding for this program is provided by: Additional funding provided by This is a course about Justice … they will all die let's assume you know that for sure",
      "start_time": 4.2,
      "end_time": 65.08,
      "deep_link": "https://youtu.be/kBdfcR-8hEY?t=4",
      "token_count_estimate": 128,
      "metadata": {
        "video_id": "kBdfcR-8hEY",
        "title": "Justice: What's The Right Thing To Do? Episode 01 …",
        "channel": null,
        "chunk_index": 0,
        "start_time": 4.2,
        "end_time": 65.08,
        "language": "en",
        "total_chunks": 60
      }
    },
    {
      "chunk_index": 1,
      "chunk_id": "kBdfcR-8hEY_chunk_001",
      "text": "that if you crash into these five workers they will all die let's assume you know that for sure and so you feel helpless … how many would turn the trolley car onto the side track?",
      "start_time": 56.78,
      "end_time": 118.18,
      "deep_link": "https://youtu.be/kBdfcR-8hEY?t=56",
      "token_count_estimate": 150,
      "metadata": { "…": "same shape as chunk 0" }
    }
  ]
}