Add translate-image skill — AI image translation, OCR, and text removal #5
Description
Agent Description
translate-image is an AI-powered image translation skill with 4 tools:
- Translate Image — Translate text in images across 130+ languages while preserving layout (manga, comics, street signs, menus, documents)
- Extract Text (OCR) — Extract text from images with bounding boxes, language detection, and confidence scores
- Remove Text — Remove text overlays using AI inpainting
- Image to Text (AI OCR) — Gemini-powered extraction with optional multi-language translation
Repository: https://github.com/translateimage/translate-image-skills
SKILL.md: skills/translate-image/SKILL.md
License: MIT
Requires: curl, python3, TRANSLATEIMAGE_API_KEY
API: https://translateimage.io
Use Case
- Translating manga, comics, and webtoons from Japanese/Korean/Chinese to English or other languages
- Reading foreign-language street signs, menus, product labels from photos
- Extracting text from document scans and screenshots via OCR
- Removing watermarks, burned-in subtitles, or text overlays from images
- Multi-language document processing with simultaneous translation to multiple target languages
Additional Context
No response