Connect Torii Image Translator to Your AI Agent

Extract image text, translate and re-typeset it, or clean masked regions and typeset supplied text boxes. Ask your connected AI assistant to explain the results or carry out the specified operation.

5 tools API key

Connect Torii Image Translator Install OOMOL

Try a Torii Image Translator Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo Skill Torii Image Translator

Translate a Comic Image

Translate image text into a chosen language and receive a downloadable image.

/oo Torii Image Translator: Translate Torii image [public URL] into targetLanguage [language], using font [font] and context [context], then return the translated image.

Inspect Detected Text

Read OCR text, geometry, and confidence before editing.

/oo Torii Image Translator: Extract Torii text from [public image URL], then summarize returned text boxes and low-confidence regions.

Start Working with Torii Image Translator

Install OOMOL

Set up oo CLI and the oo Skill in your agent.
Install OOMOL →
Connect Torii Image Translator

Connect with a Torii Image Translator API key.
Connect Torii Image Translator →
Give Your Agent a Task

Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →

Choose Your Agent

Codex Claude Code Cursor Hermes

A Torii API key, available credits, and public image URLs.
Inputs use public image URLs. Translation modifies image text; OCR returns text and geometry without creating a translated image.

Torii Image Translator Tools

Torii Image Translator connects supported service operations to your AI assistant. Extract image text, translate and re-typeset it, or clean masked regions and typeset supplied text boxes.

Translation and OCR

Translate and re-typeset images or extract structured OCR records.

Image Editing

Remove masked content or typeset supplied boxes over a cleaned image.

5 tools

Translate Image

Translate text in a manga, comic, or other public image with Torii, remove the source text, re-typeset the translation, and return the downloadable translated image.

torii_image_translator.translate_image

Extract Text

Extract structured OCR text, geometry, orientation, colors, and confidence data from a public image with Torii.

torii_image_translator.extract_text

Inpaint Image

Remove masked text or objects from a public image with Torii inpainting and return the cleaned PNG through transit storage.

torii_image_translator.inpaint_image

Typeset Image

Render translated text boxes over a pre-cleaned public image with Torii and return the typeset PNG through transit storage.

torii_image_translator.typeset_image

Get Credits

Retrieve the credit balance remaining for the connected Torii API key.

torii_image_translator.get_credits

Frequently Asked Questions

What image input is accepted?

Provide a public imageUrl, and a public maskUrl for inpainting.

Can OCR return geometry?

extract_text returns text, geometry, orientation, colors, and confidence.

Can I typeset my own translation?

Use typeset_image with a pre-cleaned image and explicit textBoxes.