Extract text from images using tesseract OCR, supporting local files, URLs, and base64 inputs for text-only AI models without vision capability.
image2text
Extract text from images without needing a vision-capable AI model.
Usage
python3 scripts/ocr.py <image path|URL|base64> [--lang <languages>] [--psm <mode>] [--raw]
Parameters
--lang: Language codes, comma-separated, defaultchi_sim+engchi_simSimplified Chinese |chi_traTraditional |engEnglish |jpnJapanese |korKorean | and 30+ more- Combine:
chi_sim+eng
--psm: Page segmentation mode, default63Fully automatic |6Block-level |4Single line |11Sparse text
--raw: Output plain text only, no markers
Auto-Detects Input Type
- Local path:
/Users/xxx/Downloads/xxx.png - Web URL:
https://example.com/image.png— OSS temp links work too - Base64: Pasted image data from clipboard — just paste directly
Workflow
- Receive image input → auto-detect type (local path / URL / base64)
- URL → curl downloads to temp file
- Base64 → decode to temp file
- Run tesseract OCR
- Output plain text
Examples
OCR a Chinese receipt:
python3 scripts/ocr.py ~/Downloads/receipt.png --lang chi_sim
English + Chinese mixed:
python3 scripts/ocr.py https://example.com/doc.jpg --lang chi_sim+eng
Plain text only (no markers):
python3 scripts/ocr.py /path/to/image.png --raw
Requirements
- tesseract must be installed:
brew install tesseract - Language packs auto-installed with tesseract
- On Mac: binary at
/opt/homebrew/bin/tesseract - Temp files auto-deleted after execution
- For best accuracy on receipts/screenshots: try
--psm 3
Related skills
- Downloads
- Security audit
- Review
- Last updated
- 6mo ago
- Current version
- v1.0.0
- License
- MIT-0
