{"uid":"cap_aobEZCtSVJOK1NiDzJsEI","slug":"devx-voice-ocr-39a63205","name":"DevX Voice OCR","description":"OCR for agents: send an image URL or base64 (PNG, JPEG, WebP, GIF; up to 3 MB) and get the text it contains in reading order, as plain text or Markdown (tables, lists). Works on screenshots, receipts, invoices, signs and documents. $0.002 USDC per image on Base; images with no readable text are not charged. Gemma 4 vision. By DevX.","url":"https://voice.madebydevx.com/v1/ocr?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"format":{"enum":["text","markdown"],"type":"string","description":"Output format (default text)"},"image_url":{"type":"string","description":"Public http(s) URL of the image (max 3 MB)"},"requestKey":{"type":"string","pattern":"^[A-Za-z0-9][A-Za-z0-9._:-]{7,127}$","maxLength":128,"minLength":8,"description":"Optional idempotency key: the same payer + requestKey + input within 7 days returns the stored result without a second charge."},"image_base64":{"type":"string","description":"Base64 image; a data: URI prefix is allowed"},"language_hint":{"type":"string","maxLength":40,"description":"Optional expected language"}}},"responseSchema":{"type":"json","example":{"result":{"text":"INVOICE #4021\nTotal due: 12.50 USDC","image":{"mime":"image/png","bytes":7868},"lines":2,"model":"gemma-4-26b-a4b-it","format":"text","truncated":false,"characters":35},"status":"paid","payment":{"status":"paid","network":"eip155:8453","tx_hash":"0x0000000000000000000000000000000000000000000000000000000000000000","amount_raw":"2000"},"operation_id":"3c2b1a09-8f7e-4d6c-9b5a-4e3d2c1b0a99"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_3AymQKeYXF-CHiwU4ZpTN","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts text from images (screenshots, receipts, invoices, signs, documents) in plain text or Markdown format using Gemma 4 vision","exampleAgentPrompt":"Can you extract all the text from this receipt image at https://example.com/receipt.png and give it back to me in Markdown format so tables and lists are preserved?","exampleUseCases":[{"title":"Digitize invoice for accounting","prompt":"I have an invoice image at https://mybusiness.com/invoices/inv-2047.jpg — can you read all the text out of it, including line items and totals, and return it as Markdown?"},{"title":"Extract text from product label photo","prompt":"I took a photo of a nutrition label on a food package and uploaded it to https://cdn.myapp.com/label.png — can you extract all the text from it in plain text format?"},{"title":"Parse screenshot of error message","prompt":"Here's a base64-encoded PNG screenshot of an error dialog from my app — can you read the exact error message and any code or detail text shown in it?"}],"resultDescription":"A JSON object containing the extracted text (in plain text or Markdown), image metadata (MIME type, byte size), line and character counts, the model used, a truncation flag, an operation ID, payment confirmation details (tx hash, amount, network), and a status field indicating the charge was applied.","failureModes":["Image exceeds 3 MB limit — request rejected with size error","Unsupported image format (not PNG, JPEG, WebP, or GIF) — returns format error","Image URL is unreachable or requires authentication — fetch failure","Image contains no readable text — returned as empty text result, no charge applied","Base64 data malformed or invalid — parse error","Language hint not recognized — may fall back to auto-detection","Idempotency key reused with different input — conflict error returned"],"whenToPreferThis":"Choose this endpoint when you need to extract text from images programmatically in an agent workflow, especially for receipts, invoices, screenshots, or documents. It supports both URL-based and base64 image inputs, outputs structured Markdown (including tables and lists), and charges only when text is found. Prefer it over general-purpose vision LLM calls when you want a low-cost, pay-per-image OCR primitive with idempotency support on Base/USDC.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-28T06:37:34.034Z","isFirstParty":false,"canonicalSlug":"devx-voice-ocr-39a63205"}