Image OCR for AI Agents: Text, Boxes and Markdown

Google Lens OCR API - Image to Text, Handwriting & Translation

s-r/google-lens-ocr

Turn image URLs into text with Google Lens OCR. Get the full text, paragraphs with lines, optional word bounding boxes and an optional translation for scans, screenshots, photos and handwriting. Built for developers, data teams and document workflows. Pay per image read.

Transcribe your audio and video files with Whisper: text, timestamped segments, optional word timings, language detection, translation to English, and SRT/VTT subtitle files. MP3, M4A, WAV, MP4, WebM and more from URLs or key-value stores. Priced per audio minute.

Google Lens OCR API - Image to Text & Coordinates

thodor/google-lens-ocr

Google Lens OCR API. Extract text from images with word, line and paragraph bounding boxes in pixels, plus object detection and translation.

Image OCR Scraper

seemuapps/image-ocr-scraper

Extract text from any image. Bulk OCR for screenshots, scanned documents, receipts, signs, and photos. Supports 109 languages and outputs clean Markdown or structured JSON with bounding boxes.

OCR Text Extractor - Images & Scanned PDFs to Text

scrapesage/ocr-text-extractor

Extract text from images (PNG, JPG, TIFF, WEBP, BMP, GIF) and scanned PDFs with Tesseract OCR in 28 languages. Per-page text, confidence scores, optional word boxes, automatic text-layer detection for born-digital PDFs. No API key, no browser. JSON, CSV, Excel.

AI Image Generator MCP Server

szoni/apify-image-mcp

Generate AI images from text via MCP — 29 models including FLUX, SDXL, Stable Diffusion, Imagen, Ideogram, Qwen and GPT Image. Pay per image, no provider account or API key needed. Ready for Claude, Cursor and other AI agents.

Receipt OCR API

happitap/receipt-ocr-api

Receipt OCR API - Multi-Model Text Extraction : Extract structured data from receipt images using advanced OCR technology with support for multiple AI models including Google Vision, OpenAI, Azure, AWS Textract, Gemini, Hugging Face, DeepSeek, and Native OCR.

Bulk OCR: Image & Scanned PDF to Text from CSV or Google Sheet

nerolabs/bulk-ocr-image-pdf-to-text

OCR every image and scanned PDF linked in an Apify dataset, CSV, Excel or Google Sheet, keeping your columns. Inputs: datasetId or fileUrl or fileUrls, urlField, languages. Adds text, confidence and page counts. Tesseract inside the run, no outside service. Charged per page. Agent-ready: x402, MCP.

Language Detector

zsoftware/language-detector

Detect the language of each line of text using machine learning. Paste multiple lines of text into the input, and this actor will identify the language of each one, returning results with confidence scores and alternative guesses based on a trained statistical model.

Send batches of HTTP requests and get agent-ready results: parsed JSON, clean Markdown from HTML, retries with Retry-After, redirect chain, timing, TLS expiry, SSRF protection and redacted secrets. URL health mode for link checks. Priced per response.