web-search-and-content

Removes or normalizes unwanted characters and parameters from URLs.

Web search (Google results via Serper): top 10 organic results + answer box + knowledge graph. Query: ?q=&gl=&hl=

Audio transcription API: transcribe any public audio URL (mp3, wav, m4a, ogg — up to 25MB / ~20 min) to text with a neural speech-recognition engine running locally on our hardware. Multilingual (~99 languages), auto language detection. Use as a speech-to-text step for voicemail, podcasts, meetings, and voice agents. Audio is processed in a sandbox and deleted immediately; we keep nothing.

OpenGraph and meta tag extraction API: title, canonical URL, favicon, og:*, twitter:*, description, and author for any public page as clean JSON. For link previews, SEO audits, and content cataloging agents.

Content Signals lookup API: does this domain permit AI use of its content? Fetches robots.txt and parses Content-Signal / aipref declarations (search=, ai-input=, ai-train=) into structured JSON plus a plain-English interpretation, including related AI directives. The essential pre-crawl compliance check for scraping, RAG ingestion, and dataset agents as the web gates against bots (Cloudflare defaults change Sept 15, 2026). First mover — nobody else sells this check.

Use this tool to calculate a fast, lightweight AI discoverability score for a domain. Checks JSON-LD, crawlability, and essential AEO/GEO metrics without generating a detailed action plan.

Use this tool to audit if a website can be crawled, understood, and cited by LLMs like ChatGPT or Claude. Ideal for coding agents to automatically audit and test generated web apps for SEO, accessibility, and AI-readiness before deployment. Returns a JSON action plan prioritizing structured data, semantic HTML, and GEO requirements.

Vector embeddings API: converts up to 64 pieces of text per call into 768-dimensional numeric vectors suitable for similarity comparison, no separate provider account or key needed. Pay per call in USDC, and nothing submitted is retained afterward. Use it to build semantic search indexes, cluster related documents, or de-duplicate near-identical text at scale.

News Gurus Intel API — most recent cross-agent market intelligence ideas (institutional flow, options flow, on-chain, news catalysts) from a 40-source SharedBrain. Optional symbol filter, up to 25 ideas per call. Educational data, not financial advice.

Semantic search API for Telegram. Search across 1M channels, 150K chats, and 100K bots using hybrid search (embedding similarity + BM25 keyword matches).

Extract structured metadata from any web page: title, description, canonical URL, Open Graph and Twitter card tags, favicons, JSON-LD types, language and headings. Useful for link previews, content classification and SEO analysis.

Link preview data extraction: pulls the title, description, thumbnail image, and social-sharing tags from any public web page so you can render a rich preview card without loading the page yourself. Guarded against internal-network requests and capped at 512KB. For chat apps, bookmarking tools, and content aggregators building link previews.

Web content extraction: fetch any public web page and get its readable article content as clean markdown — boilerplate, nav, and ads stripped automatically. For "get me the readable text of this page" requests. Honors robots.txt and Content-Signal/aipref declarations (explicit disallow returns an unpaid 403). SSRF-guarded, 2MB cap.

Live YouTube scraping

Live Instagram scraping

Live Instagram scraping

Live Instagram scraping

Live YouTube scraping

Live YouTube scraping

Live Instagram scraping

Live Instagram scraping

Live YouTube scraping

Live Instagram scraping

Live YouTube scraping