10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 547 ms
modelrecord46,016 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
- 2GoldBeanfound in code, not yet checkedno passport yet
- baidu_qianfan_ocr
Custom template-based OCR using Baidu Qianfan platform — for structured field extraction from specific document types you have configured. Use when: you have a custom document template (invoices, receipts, customs forms) set up on Qianfan platform and need to extract predefined fields. Do NOT use fo
- baidu_qianfan_ocr
skillmr-shaper/opencode-skill-hybrid-ocrrecord
- ocr
OCR skill for extracting text from images and PDFs. Use when you need to read text from screenshots, photos, scanned documents, or any image file. Supports Chinese, English, and 100+ languages.
- ocr
MCP serverrecord
- qota_ocr_JAP_run_ocr
Read all text from a document image. Detects text lines with PP-OCRv6_small_det, then recognizes each line with Qota-OCR (Korean/English/Chinese/Japanese). If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio Fi
- qota_ocr_JAP_run_ocr
MCP serverrecord
- qota_ocr_run_ocr
Read all text from a document image. Detects text lines with PP-OCRv6_small_det, then recognizes each line with Qota-OCR (Korean/English/Chinese/Japanese). If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio Fi
- qota_ocr_run_ocr
skillclaude-office-skills/skillsrecord
- smart-ocr
>
- smart-ocr
- 7Umi-OCR MCP Serverfound in code, not yet checkedno passport yet
- ocr_batch
批量 OCR 多张本地图片，一次调用返回所有结果。
- ocr_directory
批量 OCR 目录下所有图片。
- ocr_batch
- 8mcp-ocrfound in code, not yet checkedno passport yet
MCP serversebkrummen/mcp-ocr
- ocr_image
Perform OCR on an image file using Qwen2-VL (MLX optimized).
- ocr_pdf
Perform OCR on a PDF file using Qwen2-VL (MLX optimized).
- ocr_image
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.