All projects matching “text”

Read a public static HTTPS webpage as clean text with headings, links, timestamp and content hash. Use to ground an answer or ingest documentation. Respects robots.txt; no JavaScript or login.

Text completion using the model selected in the request body.

Extract clean, LLM-ready Markdown or plain text from up to 5 public webpage URLs. Removes page boilerplate and returns structured per-URL results for AI agents, RAG ingestion, research and summarization.

Search US federal product recalls (CPSC consumer products, FDA food/drug/device enforcement, NHTSA vehicle campaigns, and USDA FSIS meat/poultry recalls through 2026-10-22) by free-text query, firm name, date range, and source.

Whether a number is on WhatsApp and, if so: personal or business account, about text, country, linked devices and whether it runs on the Cloud API. Businesses add their public profile: name, description, categories, email, websites, address, coordinates, hours, join date and Facebook page. No photo; /v1/profile/full adds it. Query param: phone, with country code (e.g. +14155552671). Every answer i

Text Moderation pii: Detect personal data (email, phone, SSN, credit card with Luhn check, IP, IBAN, crypto address, name, address, date of birth, passport) with character offsets; optional redaction to [TYPE].

Reader Pro: fetch a public web page and return structured data, no LLM: OpenGraph/meta tags, parsed JSON-LD (schema.org), HTML tables as row objects, deduped internal/external links, emails/phones/social profiles, heading outline, images with alt text, plus optional CSS-selector fields.

Deterministic citation formatter — APA 7, MLA 9, Chicago 17 author-date, BibTeX. From structured fields, returns the reference entry (markdown/html/plain) + the in-text citation, reproducing published style-manual examples exactly. For full author lists use POST. Every answer signed. Free sample, no payment required: GET /play/cite

Find the cheapest suitable API or software service for an agent task (for example PDF text extraction, web scraping, search, weather, email validation). Returns one recommendation plus alternatives with real prices.

Scan source code or configuration text for hardcoded secrets: AWS access keys, GitHub/Slack/Google tokens, Stripe and OpenAI keys, PEM private-key blocks, JWTs and high-entropy secret assignments. Placeholder values are filtered out. Each finding gives the rule, a severity (critical/high/medium/low), line and column, entropy and a masked excerpt. Offline and deterministic.

Fetch a URL and extract clean main-content text with title, description, word count, and char count; boilerplate (nav/footer/sidebar/ads) is stripped.

Generate one image from a text prompt: app icon, brand logo, character mascot or illustration. POST JSON {description, type?, style?, aspect_ratio?}. type is icon, logo, mascot or illustration (default icon; only icon gets app-icon framing and mask safe margins). style is flat, metallic, 2d-game, clay, 3d, gradient or glassmorphism. aspect_ratio is 1:1, 4:3 or 16:9. Returns image_key and preview_u

Calculate kg/l unit prices for up to 50 rows of price_eur plus quantity text or EAN. Example: items [{price_eur:1.29,quantity:"500 g"}]. Errors are reported per row; kg and litre groups are not comparable. Empty batches with no usable line are not charged. No observed store offer.

Extract metadata and readable text from a public URL.

Find the right KBLI 2025 business classification code (5-digit, mandatory in Indonesia's OSS business licensing since 15 June 2026) from a free-text business activity in Indonesian or English. Returns official BPS titles, descriptions and hierarchy.

Compute the standard English readability formulas — Flesch Reading Ease, Flesch–Kincaid grade, Gunning fog, SMOG, Coleman–Liau and ARI — along with the underlying sentence/word/syllable statistics. Empty text is a clean 400.

Search Wikidata for entities matching a text query, returning candidate Q-ids with labels and descriptions.

Encode text into international (ITU) Morse code. Letters are separated by spaces and words by "/". Supports A-Z, 0-9 and common punctuation; unsupported characters are clean 400s.

Pay $0.01 USDC to make an outbound HTTP request through the proxy. Supports all standard HTTP methods, custom headers (including auth), and JSON or raw bodies. Responses are returned as text or base64-encoded binary. Max response size 10 MB, timeout 30s. Each request performs one upstream fetch and returns the final URL plus response metadata.

A styled QR code (module shapes, corner markers, a logo or a halftone photo) for any text, no account needed

Extract raw artifacts from images: OCR text and detected objects. No interpretation, just clean machine-readable data. Powered by GPT-4o Vision. Payment via USDC on base.

Give this API up to 10 domain names and it tells you whether each has a registration record at the official registry. It uses RDAP, the structured replacement for WHOIS, so there is no free-text parsing. Each domain comes back as 'registered', 'unregistered', or 'indeterminate' when the registry has no RDAP for that ending. 'Unregistered' means no record was found, which usually means available -

Generate ready-to-use 1200x630 Open Graph / social preview images from text for content, marketing, and publishing agents. Provide a title plus optional subtitle and category badge, pick a built-in theme (dark, light, midnight, forest, sunset), and receive a base64 PNG sized exactly for og:image and twitter:card. Pure server-side rendering with no external calls and no shell access.

Overwing guardrail: check text before you send, post, or act on it. Content moderation, PII detection, confidential leak detection, toxicity, self-harm and severity in ~150 ms. Returns a verdict plus one recommended_action (block / redact / review / allow) with calibrated confidence. Pass context (recipient, channel, owns_contact_info) with the outbound-message set. $0.002 USDC, no account.

Transkription bis 10 Min Audio, Whisper large-v3-turbo, Deutsch optimiert, verarbeitet in Deutschland. Speech-to-text for audio up to 10 min (mp3, m4a, ogg, wav, mp4), German-optimised, processed in Germany. JSON body with audio_url or audio_base64. Longer files are rejected before payment settles. Voraussetzung/required: accept_terms_hash, business_name (B2B) – /legal/terms.json

Clinical trial search — find ClinicalTrials.gov studies by free text, condition, intervention, sponsor, recruitment status and phase, and get each study's NCT id, titles, status, phases, conditions, interventions, sponsor, start and completion dates, enrollment and whether results are posted. Use for drug development, medical research and patient-recruitment questions.

Generate scannable QR codes from any text, URL, or structured payload (WiFi, vCard, SMS, email, geo, crypto). Returns PNG by default with JPG, WebP, and SVG output, plus optional error-correction, sizing, color, version, and encoding controls. Simple cURL POST: send qr_data, receive an image.

Search normalized clinical trials by registry, condition, intervention, sponsor, country, status, phase, study type, or free text.

Read the text out of a QR code or barcode in a PNG or JPEG image. Auto-detects QR, DataMatrix, PDF417, Aztec and 1D symbologies (Code128/39/93, EAN-13/8, UPC-A/E, ITF, Codabar). A valid image with no code returns { found: false }; a payload that is not a parseable image is a 400.

Give this API any text or binary data and it returns its fingerprint under whichever hash algorithms you choose - SHA-256, SHA-512, MD5, BLAKE2, CRC32 and more. It also signs data with a secret key (HMAC) and safely verifies whether an incoming signature matches, using a timing-safe comparison. Language models cannot hash: they emit a string of the right length and character set that is simply wro