TidyData APIsAll APIsPricing

Text Summarization API

Summarize any text or article URL in 50+ languages: picks the most important sentences (TextRank), with keywords and reading-time saved. No AI costs and no invented content.

Authentication & base URL

Subscribe through one of our marketplace listings; your marketplace API key and base URL are shown there. All endpoints return JSON over HTTPS, served from a global edge network (typically 20–150 ms).

Subscribe on RapidAPI

Endpoints

GET /v1/summarize

Summarize a text or URL

ParameterInDescriptionExample
textqueryText to summarize (up to 100,000 characters)
urlqueryOr an article URL to fetch and summarizehttps://en.wikipedia.org/wiki/Spell_checker
sentencesqueryNumber of sentences in the summary (default: about 20%, 3-5)3
ratioqueryOr a fraction of the sentences, 0.05-0.6
langqueryISO 639-1 language or auto (default)auto

POST /v1/summarize

Summarize long text (body: plain text or JSON {text, sentences, lang})

Request body: text/plain

ParameterInDescriptionExample
sentencesqueryNumber of sentences3
langqueryLanguage or autoauto

Example

GET /v1/summarize?url=https%3A%2F%2Fen.wikipedia.org%2Fwiki%2FSpell_checker&sentences=3

{
  "url": "https://en.wikipedia.org/wiki/Spell_checker",
  "title": "Spell checker - Wikipedia",
  "language": "en",
  "summary": "In software, a spell checker (or spelling checker or spell check) is a software feature that checks for misspellings in a text. Spell checkers can use approximate string matching algorithms such as Levenshtein distance to find correct spellings of misspelled words. An alternative type of spell checker uses solely statistical information, such as n-grams, to recognize errors instead of correctly-spelled words.",
  "sentences": [
    {
      "index": 0,
      "text": "In software, a spell checker (or spelling checker or spell check) is a software feature that checks for misspellings in a text.",
      "score": 1
    },
    {
      "index": 14,
      "text": "Spell checkers can use approximate string matching algorithms such as Levenshtein distance to find correct spellings of misspelled words.",
      "score": 0.851
    },
    {
      "index": 15,
      "text": "An alternative type of spell checker uses solely statistical information, such as n-grams, to recognize errors instead of correctly-spelled words.",
      "score": 0.794
    }
  ],
  "keywords": [
    "spell",
    "checkers",
    "spelling",
    "errors",
    "misspellings",
    "languages",
    "correct",
    "word",
    "program",
    "dictionaries"
  ],
  "stats": {
    "originalSentences": 80,
    "originalWords": 1619,
    "summarySentences": 3,
    "summaryWords": 61,
    "compression": 0.038,
    "readingTimeSavedSeconds": 393
  },
  "note": "Extractive summary (TextRank): the most representative sentences of the original text, in their original order. No AI and nothing invented."
}

Summarize any text or article URL in 50+ languages: picks the most important sentences (TextRank), with keywords and reading-time saved. No AI costs and no invented content.

Why extractive

Use cases

News digests and newsletters, "TL;DR" buttons, previews for search results and feeds, research and document triage, chat apps and Slack bots, SEO meta descriptions.

Pricing

Free plan 500 requests/month, Pro 25,000 for $4.99, Ultra 150,000 for $14.99.

Pricing

Free plan with 500 calls per month, then Pro (25,000 calls for $4.99/month) and Ultra (150,000 calls for $14.99/month). See all plans.