TextActive
OCR — Image to Text
Extract text from images using Tesseract OCR. Send image as image_base64 (PNG/JPEG/WebP/TIFF/BMP, max 10 MB decoded). Returns text and confidence (0-100, where 80+ is reliable). Set language to Tesseract code: 'eng' (default), 'deu' (German), 'fra' (French), 'chi_sim' (Chinese Simplified), 'jpn' (Japanese), 'ara' (Arabic). Use for invoices, receipts, scanned documents, or screenshots with text.
Input Schema
{
"type": "object",
"required": [
"image_base64"
],
"properties": {
"image_base64": {
"type": "string",
"description": "Base64-encoded image. Supported formats: PNG, JPEG, WebP, TIFF, BMP. Max 10 MB decoded. For best results use high-contrast images with clear text."
},
"language": {
"type": "string",
"default": "eng",
"description": "Tesseract language code. Default: 'eng' (English). Other supported: 'deu' (German), 'fra' (French), 'spa' (Spanish), 'ita' (Italian), 'por' (Portuguese), 'rus' (Russian), 'chi_sim' (Chinese Simplified), 'jpn' (Japanese), 'ara' (Arabic), 'kor' (Korean), 'nld' (Dutch), 'pol' (Polish). Use '+' to combine: 'eng+deu'."
},
"psm": {
"type": "integer",
"default": 3,
"description": "Page Segmentation Mode. 3 = fully automatic (default, best for most images). 6 = single uniform block of text. 7 = single text line. 11 = sparse text (find text anywhere). 13 = raw line (no line ordering). Use 6 or 7 for forms/labels."
}
}
}
Output Schema
{
"type": "object",
"required": [
"text",
"confidence",
"language",
"processed_at"
],
"properties": {
"text": {
"type": "string",
"description": "Full extracted text from the image, with line breaks preserved"
},
"confidence": {
"type": "number",
"description": "Overall OCR confidence score (0-100). Above 70 is considered reliable."
},
"language": {
"type": "string",
"description": "Language code used for recognition"
},
"word_count": {
"type": "integer",
"description": "Number of words extracted"
},
"char_count": {
"type": "integer",
"description": "Number of characters extracted (excluding whitespace)"
},
"processing_ms": {
"type": "integer",
"description": "Time taken for OCR processing in milliseconds"
},
"processed_at": {
"type": "string",
"format": "date-time",
"description": "ISO 8601 timestamp"
}
},
"example": {
"text": "Invoice #12345\nDate: April 10, 2026\n\nBill To:\nJohn Smith\n123 Main Street\n\nTotal Due: $1,250.00",
"confidence": 94,
"language": "eng",
"word_count": 18,
"char_count": 72,
"processing_ms": 1840,
"processed_at": "2026-04-10T14:00:00.000Z"
}
}