Lexical diversity analyzer

Open Lexical diversity analyzer on Happytails.ai. This view has the same page content and links, with explicit tool capabilities. Read the processing notes before using a tool.

Tool capabilities

{
  "id": "lexical-diversity-analyzer",
  "category": "text-tools",
  "built": true,
  "requirements": "Word tokens are Intl.Segmenter word-like segments containing a Unicode letter; pure numbers are excluded. TTR = distinct words / words; root TTR = distinct words / square root of words; corrected TTR = distinct words / square root of twice the words. Moving-average TTR uses only complete selected-size windows. These length-sensitive descriptive ratios do not measure proficiency or writing quality. Use up to 500000 text characters and 20000 word tokens. Reports allow up to 10000 matches or repeated phrase groups. JSON and CSV preserve the full report, with bounded exports up to 40 million characters and 500000 CSV records. Analysis runs locally with a 10-second timeout. Preview search and sort cover the first 200 rows; copy returns the summary. Download the full report for every row. Your text is not uploaded.",
  "implementation": {
    "fields": [
      {
        "key": "window",
        "label": "Words per moving window",
        "value": "50",
        "type": "text",
        "inputMode": "numeric",
        "maxLength": 8,
        "min": 2,
        "max": 1000,
        "step": 1,
        "help": "2–1000"
      },
      {
        "key": "caseMode",
        "label": "Case comparison",
        "value": "fold",
        "type": "select",
        "values": [
          "fold",
          "exact"
        ],
        "labels": {
          "fold": "Locale-aware lowercase",
          "exact": "Case-sensitive"
        }
      }
    ],
    "presentation": "metrics",
    "inputMaxLength": 500000,
    "inputErrorCode": "TEXT_DIAGNOSTICS_INPUT",
    "note": "Word tokens are Intl.Segmenter word-like segments containing a Unicode letter; pure numbers are excluded. TTR = distinct words / words; root TTR = distinct words / square root of words; corrected TTR = distinct words / square root of twice the words. Moving-average TTR uses only complete selected-size windows. These length-sensitive descriptive ratios do not measure proficiency or writing quality. Use up to 500000 text characters and 20000 word tokens. Reports allow up to 10000 matches or repeated phrase groups. JSON and CSV preserve the full report, with bounded exports up to 40 million characters and 500000 CSV records. Analysis runs locally with a 10-second timeout. Preview search and sort cover the first 200 rows; copy returns the summary. Download the full report for every row. Your text is not uploaded.",
    "experience": {
      "automatic": false,
      "single": false,
      "inputMaxLength": 500000,
      "inputMode": "text",
      "label": "Your text",
      "placeholder": "Type or paste your input…",
      "help": "Up to 500,000 characters. Review the settings before running.",
      "helpParts": [
        "Up to 500,000 characters.",
        "Review the settings before running."
      ],
      "action": null
    },
    "mode": "explicit",
    "interactive": false
  },
  "execution": "Browser interface",
  "api": null,
  "browser_agent": {
    "supported": true,
    "name": "run_current_tool",
    "discovery": "WebMCP on the human page in a supporting browser",
    "verification": "See audit/API-AUDIT.md; availability is not verification"
  }
}

Page guide