OCR
Image OCR
Turn text trapped inside an image into machine-readable lines that can be searched, validated or passed to an agent without manual transcription.
/v1/ocr/json
What you get
Developer-ready output for Image OCR
Real workflows
Where teams use Image OCR
These examples map to the endpoint's current inputs and outputs—not hypothetical platform features.
Extract error text or labels from customer screenshots before routing a support ticket.
Convert image-based forms or document pages into text before validation and field extraction.
Run OCR over exported slides, posters or screenshots before adding them to an internal search index.
How it works
4 concrete steps from input to result
Send an image source
Try PaddleOCR first
Fall back to RapidOCR when needed
Return joined text and line metadata
API response
Fields developers usually wire first
Extract text from screenshots, scans and image files through a Paddle-first OCR chain with structured line output and a local fallback engine.
curl.exe -H "X-API-Key: YOUR_API_KEY" "http://127.0.0.1:8013/v1/ocr/json"
Developer FAQ
Common questions about Image OCR
What image inputs are supported?
Use multipart upload, image_url in the JSON payload, or image_base64 when the image already exists inside your application flow.
Why is Paddle first?
PaddleOCR is the primary engine in the chain because it generally handles mixed layout text well. When it is unavailable or fails, RapidOCR is used as the local open-source fallback.
Can I keep bounding boxes?
Yes. include_boxes keeps line coordinates in the response so you can draw overlays or map OCR text back onto the image.
What endpoint should I call for Image OCR?
Use POST /v1/ocr/json. Local development accepts the X-API-Key header with YOUR_API_KEY, and production clients can use the same shape with their own key.
Can I call it from CLI, SDK, MCP and no-code tools?
Yes. The same endpoint can be called with curl, the TypeScript SDK, Python SDK, MCP server, Zapier, Make, n8n, Google Sheets or Excel workflows where appropriate.
How does caching with maxAgeMs work?
When maxAgeMs is supported, a cached response can be reused if it is younger than the requested freshness window. Set maxAgeMs to 0 when you need a fresh scrape or extraction.
What happens when a page is blocked or requires login?
The API returns clear states such as blocked, verification_required, login_required, robots_disallowed or permission_required. It does not promise to bypass access controls.
Which response fields should I store?
Most integrations store text, lines[].text, lines[].confidence, meta.engine_used, plus source URL, status, confidence and timestamp fields when present. Keep source metadata so users can audit values later.
Can I batch this endpoint?
For local or small workflows, loop over a list of URLs or domains. For larger jobs, use crawl, batch workflow endpoints or a queue so failures and retries are tracked cleanly.
How should I handle errors in production?
Check success, HTTP status, error.type and retryable flags. Retry timeouts and temporary network failures, but do not retry robots, login or permission errors without changing input or authorization.
Does the API work with JavaScript-heavy sites?
The engine router starts with fast fetching and escalates when content quality is low. Browser-style rendering is used where available, while access-control barriers are reported explicitly.
Is this safe to use with customer data?
Send only domains, URLs or fields your workflow needs. Use retention controls for generated artifacts and avoid storing unnecessary raw HTML, screenshots or extracted personal data.
Related data APIs
Build the next step in the workflow
POST /v1/web/crawl
Scrape HTML
Fetch page HTML for DOM inspection, structured extraction, migration tooling and debugging, with rendering escalation when a static response is not enough.
GET /v1/web/scrape/html
Scrape Markdown
Convert webpages into clean, source-linked Markdown for AI agents, research notes and retrieval pipelines while keeping link and image controls explicit.
GET /v1/web/scrape/markdown
Meta Title and Description
Extract title, description, canonical, language, Open Graph and Twitter metadata for SEO QA, link previews and lightweight URL enrichment.
GET /v1/web/meta
Scrape Images
Discover page images across img, picture, lazy-loading, CSS backgrounds, inline SVG and video poster sources, then normalize them into usable media records.
GET /v1/web/scrape/images
Royalty-Free Image Finder
Search curated stock-image providers for reusable visual candidates, with provider and license context kept alongside every result.
POST /v1/royalty-free-images/search
YouTube Transcript
Retrieve timestamped YouTube transcript text through multiple local fallback methods for research, indexing and content analysis.
POST /v1/youtube/transcript
Scrape Sitemap
Discover site URLs from robots.txt, sitemap indexes and XML sitemaps with recursive parsing, filtering and link limits.
GET /v1/web/scrape/sitemap