All projects matching “text”

Search contractor/trade licenses (TX TDLR electricians/A-C, FL DBPR construction) by free-text query, name, state, profession, or status.

Send a list of texts — website addresses, phone numbers, plain words, WiFi details, anything — and get back a ready-to-use QR code image for each one. Every QR code comes as a base64-encoded PNG you can drop straight into a webpage or save to disk. Great for marketing campaigns, event tickets, product labels, menus, or any situation where you need many QR codes in one go. Empty entries are quietly

Edit an image from a text instruction. SFW only.

Check a Romanian e-Factura (UBL 2.1, CIUS-RO 1.0.9) before uploading it to ANAF SPV, and get the exact fix for every error: plain-English explanation, the official Romanian rule text, the UBL path of the field and, for amount errors, the correct value computed from the invoice (chained, so following the report gives a consistent invoice). Also validates Peppol BIS Billing 3.0 and EN 16931. No acco

Send one SMS to a mobile number, paid per message in USDC with x402. Use it when an agent must notify a person by text. The 402 quotes the exact price for the destination and message length. No account and no API key: any wallet that pays sends in one call. An opt-out link is appended to the message, and numbers that opted out are refused. Returns an order; poll GET /v1/orders/{id} for delivery st

Embeds up to 32 texts on the local Ollama runtime. Returns explicit model and dimensions; no paid third-party API is called.

Convert text into a URL-safe slug: transliterate accents, apply a locale character map, and join with a separator.

Paid hosted deterministic explanation for EVM/RPC/wallet/UserOperation/x402 errors. Send raw pasted error JSON, text, or revert bytes.

Signed proof of what a web page said: give a URL, get its text, screenshot and TLS details with a timestamped cryptographic signature anyone can verify.

Use when you need a new image of a licensed character or brand: give a text prompt and a Story Protocol IP asset, and get a PNG generated with that asset as the reference image. Paid per image in USDC.

Short video clip: animate YOUR image (or your own text prompt) into a 1-6 s clip with audio, 9:16 or 16:9, returned as a temporary MP4 URL. Caller-owned media only. Flat $0.50 per clip.

Turn text into a numeric embedding vector for semantic search, RAG and similarity. Multilingual.

Clean a CSV ($0.005 USDC): give an https url or inline csv (max 1 MB / 20k rows). Trims whitespace, optional case rules, dates to ISO 8601, lowercases emails, normalizes phone digits, merges or flags exact + fuzzy duplicate rows on key_columns. Returns cleaned CSV text + JSON report (rows in/out, dupes, columns changed). Deterministic, no AI. As is, no warranty. Nothing stored.

Fetch a public https URL that returns text and compute byte/char/line/word counts plus SHA-256 ($0.005 USDC via x402). https only — http, file, data, localhost, and private IPs are rejected. Caps: 1 MB body, ~10s timeout, max 5 redirects. Rejects image/audio/video/octet-stream. Returns JSON { url, final_url, content_type, byte_length, char_count, line_count, word_count, sha256, warnings }.

Extract tables from a PDF ($0.01 USDC via x402). Pass pdf_base64 or a https pdf_url. Optional schema maps headers. Optional max_pages (1-10). Returns JSON { pages, tables: [{ page, headers, rows }], warnings }. Text PDFs are parsed in-worker; scans require HOSTED_PARSER_URL.

Financial statement quick risk scan / 财报快速风险扫描. Find up to five highest-priority accounting red flags, earnings-quality issues, cash-flow anomalies, debt/liquidity and governance risks in supplied 10-K, 10-Q or report text. Returns structured scores, evidence quotes and source links.

Fast text-to-image with Flux 1 Schnell (@cf/black-forest-labs/flux-1-schnell). POST prompt and optional dimensions; returns base64 image output. Hero: GET /heroes/flux-schnell. Per-generation x402 pricing per USDC per request (see npm run pricing:report).

Generate AI images or video from a text prompt with Midjourney-style --flags (--ar 16:9, --v, --flagship, ...). Async: returns a generation record; poll GET /api/gens/{uuid}/ or set callback_url for a webhook. Pay-to-play: without credits you get a 402 priced for this prompt; settle the exact USDC on Base via x402 and retry. No account needed: first settlement creates the account; subsequent reque

Searches Polymarket prediction markets by text and returns current outcome prices, volume, liquidity, end date and resolution status. Read-only market data, not financial advice.

Detect and redact PII in text or JSON. Recognizers are pure pattern/checksum matching (regex + Luhn/mod-97/SSN-area validation) — no LLM calls, no external services. Person names and dates of birth are matched only via nearby context (e.g. 'Mr. Smith', 'DOB: ...'), not general NER, to keep false positives low.

Generate 1-4 AI images from a text prompt using flux-schnell. $0.01 per image (price = $0.01 × num_outputs). Returns a job_id claim ticket; retrieve images free at /result/{job_id} (durable, no expiry).

Textus: structured content with editable baseline direction, characters and scenes for audio, games and media production. One purchase returns one selected text unit as JSON; no audio or provider execution. Find IDs, metadata, prices and availability: https://api.textus.dev/api/v1/resources.json

Count the LLM tokens in text for a given model or encoding — exact for OpenAI and open models (Llama, Mistral, Qwen, Gemma, DeepSeek, Command-R); labelled-approximate for Claude & Gemini.

create_text — $0.01 USDC

Generates one to four images from a text prompt with the chosen model, and returns the asset with the output URLs in results. AutoI picks a model automatically. Credits depend on the model tier and the quantity.

Findings brief for data and API sellers: how AI agents with funded wallets behave at a paywall. 1,416 purchases and refusals across six models and three agent frameworks on x402, with the install checklist. Full text, markdown, September 2026.

Usage info for the html-clean tool: pay this GET once to receive machine-readable instructions, then call POST /html-clean to turn raw HTML into clean structured content (title, meta, LLM-ready text, headings, links, images).

Prompt-injection scan for text your AI agent is about to read (web pages, emails, tool output, MCP tool descriptions): risk score 0-100, verdict, categories and exact spans. Detects instruction overrides, jailbreak personas, system-prompt extraction, fake chat delimiters, data-exfiltration URLs, tool hijacking, hidden Unicode and encoded payloads. Deterministic rules, no data stored.

A2A Indirect Prompt-Injection & Jailbreak Firewall (/v1/prompt-guard) — Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text. (https://prompt-guard.agentdiet.dev/v1/prompt-guard)

A2A Indirect Prompt-Injection & Jailbreak Firewall (/v1/prompt-guard) — Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text. (https://mcp-security.agentdiet.dev/v1/prompt-guard)