Operated by Sourcelane✓ verified
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.
A bulk OCR connector that extracts text, tables, formulas, and charts from images (screenshots, scanned documents, receipts, signs, menus, business cards, photos) using the PaddleOCR engine. Produces clean, structured text in Markdown (preserving headings, lists, tables) or structured JSON containing text blocks with bounding-box coordinates; supports printed and handwritten text, mixed-language content across 109 languages, rotated text and low-quality scans, and generates one output record per processed image for multi-image batch processing with rapid per-image processing.
Verified Sep 28, 3:55 AM
$0.03
per image
Up to 33 per call. Only pay for results returned; failed calls are refunded.
Document digitization
Convert scanned PDFs, receipts, and invoices into searchable text
Data entry automation
Extract structured data from forms, business cards, and ID documents
Screenshot analysis
Capture text from app screenshots, error messages, or social media images
Translation pipelines
OCR foreign-language images for subsequent translation
Accessibility
Generate text alternatives for image-based content
Compliance & search
Enable full-text search across image-heavy archives
Images to OCR.
Upload image files directly.
Optional settings
| Window | Uptime | Success rate | p50 | p95 | Calls |
|---|---|---|---|---|---|
| 24h | — | — | — | — | 0 |
| 7d | — | — | — | — | 0 |
| 30d | — | — | — | — | 0 |
Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.
Call it via Sourcelane
curl -X POST https://api.usesourcelane.com/v1/call \
-H "Authorization: Bearer sl_live_your_agent_key" \
-H "Content-Type: application/json" \
-d '{"listing":"image-ocr-scraper","params":{"images":["https://dummyimage.com/600x100/fff/000.png&text=Hello+World+OCR+Test"]},"maxResults":10}'Request params
| Field | Type | Required | Description |
|---|---|---|---|
images | array | optional | Images to OCR. Each entry must be a publicly accessible http/https URL or a base64 data URI (data:image/jpeg;base64,...). |
imageFiles | array | optional | Upload image files directly. Combined with any URLs provided above. |
outputFormat | string | optional | Markdown gives clean human-readable text with structure preserved. JSON returns structured data with text positions and bounding boxes for downstream processing. |
Each result contains
| Field | Type | Description |
|---|---|---|
inputImageUrl | string | Input Image Url |
text | string | Text |
outputFormat | string | Output Format |
status | string | Status |
error | null | — |
Pick your tool and connect in under a minute. Then just ask — for example: “Transcribe this video and give me timestamps for every product mention: <url>”
Connect Claude
Web, desktop and mobile. One click, then confirm.
Adds the Sourcelane MCP server with your key as a header.
claude mcp add --transport http sourcelane https://api.usesourcelane.com/mcp \
--header "Authorization: Bearer sl_live_your_agent_key"Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.
{
"mcpServers": {
"sourcelane": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.usesourcelane.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer sl_live_your_agent_key"
}
}
}
}Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).
{
"mcpServers": {
"sourcelane": {
"url": "https://api.usesourcelane.com/mcp",
"headers": {
"Authorization": "Bearer sl_live_your_agent_key"
}
}
}
}Save as .vscode/mcp.json. VS Code prompts for your key once.
{
"servers": {
"sourcelane": {
"type": "http",
"url": "https://api.usesourcelane.com/mcp",
"headers": {
"Authorization": "Bearer ${input:sourcelane-key}"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "sourcelane-key",
"description": "Sourcelane agent key",
"password": true
}
]
}Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.
https://usesourcelane.com/openapi.jsonOne POST. Pass maxResults to cap cost.
curl -X POST https://api.usesourcelane.com/v1/call \
-H "Authorization: Bearer sl_live_your_agent_key" \
-H "Content-Type: application/json" \
-d '{"listing":"image-ocr-scraper","params":{"images":["https://dummyimage.com/600x100/fff/000.png&text=Hello+World+OCR+Test"]},"maxResults":10}'Wrap the REST call as a tool, or point an MCP client at the endpoint.
import requests
res = requests.post(
"https://api.usesourcelane.com/v1/call",
headers={"Authorization": "Bearer sl_live_your_agent_key"},
json={
"listing": "image-ocr-scraper",
"params": {"images":["https://dummyimage.com/600x100/fff/000.png&text=Hello+World+OCR+Test"]},
"maxResults": 10,
},
timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])—
0 reviews
Leave a review
Loading reviews…