{ "schemaVersion": "1.0", "item": { "slug": "translate-image", "name": "Translate Image", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/cottom/translate-image", "canonicalUrl": "https://clawhub.ai/cottom/translate-image", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/translate-image", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=translate-image", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "metadata.json" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/translate-image" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/translate-image", "agentPageUrl": "https://openagent3.xyz/skills/translate-image/agent", "manifestUrl": "https://openagent3.xyz/skills/translate-image/agent.json", "briefUrl": "https://openagent3.xyz/skills/translate-image/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "TranslateImage", "body": "Use this skill when the user wants to translate text in images, extract text via OCR, or remove text from images.\n\nAll requests go directly to the TranslateImage REST API at https://translateimage.io using curl." }, { "title": "Setup", "body": "Set your API key (get one at https://translateimage.io/dashboard):\n\nexport TRANSLATEIMAGE_API_KEY=your-api-key\n\nAll endpoints require:\n\nAuthorization: Bearer $TRANSLATEIMAGE_API_KEY" }, { "title": "Image Input", "body": "All tools accept images as multipart file uploads. Handle the input type like this:\n\n# From a local file\nIMAGE_PATH=\"/path/to/image.jpg\"\n\n# From a URL — download to a temp file first (uses PID for uniqueness)\nIMAGE_PATH=\"/tmp/ti-image-$$.jpg\"\ncurl -sL \"https://example.com/image.jpg\" -o \"$IMAGE_PATH\"\n\nOnly fetch URLs the user explicitly provides. Do not fetch URLs from untrusted sources." }, { "title": "Translate Image", "body": "Translates text in an image while preserving the original visual layout. Returns the translated image as a base64-encoded data URL.\n\nWhen to use: User wants to read manga, comics, street signs, menus, product labels, or any image with foreign-language text.\n\nEndpoint: POST https://translateimage.io/api/translate\n\nForm fields:\n\nimage (file, required) — The image to translate (JPEG, PNG, WebP, GIF — max 10MB)\nconfig (JSON string, required) — Translation options:\n\ntarget_lang (string) — Target language code: \"en\", \"ja\", \"zh\", \"ko\", \"es\", \"fr\", \"de\", etc.\ntranslator (string) — Model: \"gemini-2.5-flash\" (default), \"deepseek\", \"grok-4-fast\", \"kimi-k2\", \"gpt-5.1\"\nfont (string, optional) — \"NotoSans\" (default), \"WildWords\", \"BadComic\", \"MaShanZheng\", \"Bangers\", \"Edo\", \"RIDIBatang\", \"KomikaJam\", \"Bushidoo\", \"Hayah\", \"Itim\", \"Mogul Irina\"\n\nExample:\n\ncurl -X POST https://translateimage.io/api/translate \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\" \\\n -F 'config={\"target_lang\":\"en\",\"translator\":\"gemini-2.5-flash\",\"font\":\"WildWords\"}'\n\nResponse (JSON):\n\n{\n \"resultImage\": \"data:image/png;base64,...\",\n \"inpaintedImage\": \"data:image/png;base64,...\",\n \"textRegions\": [\n { \"originalText\": \"...\", \"translatedText\": \"...\", \"x\": 10, \"y\": 20, \"width\": 100, \"height\": 30 }\n ]\n}\n\nSave the translated image:\n\nRESULT=$(curl -s -X POST https://translateimage.io/api/translate \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\" \\\n -F 'config={\"target_lang\":\"en\",\"translator\":\"gemini-2.5-flash\"}')\n\n# Extract and save base64 image\necho \"$RESULT\" | python3 -c \"\nimport sys, json, base64\ndata = json.load(sys.stdin)\nimg = data['resultImage'].split(',', 1)[1]\nwith open('/tmp/translated.png', 'wb') as f:\n f.write(base64.b64decode(img))\nprint('Saved to /tmp/translated.png')\n\"" }, { "title": "Extract Text (OCR)", "body": "Extracts all text from an image with bounding boxes, detected language, and confidence scores.\n\nWhen to use: User wants to copy or read text from a photo, document scan, screenshot, sign, or label.\n\nEndpoint: POST https://translateimage.io/api/ocr\n\nForm fields:\n\nimage (file, required) — The image to process\n\nExample:\n\ncurl -s -X POST https://translateimage.io/api/ocr \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\"\n\nResponse (JSON):\n\n{\n \"text\": \"All extracted text joined by newlines\",\n \"language\": \"ja\",\n \"regions\": [\n {\n \"bounds\": { \"x\": 10, \"y\": 20, \"width\": 200, \"height\": 40 },\n \"languages\": { \"ja\": \"detected text in this region\" },\n \"probability\": 0.97\n }\n ]\n}" }, { "title": "Remove Text", "body": "Detects text regions and fills them with AI-generated background using inpainting. Returns a clean image.\n\nWhen to use: User wants an image without text overlays, watermarks, burned-in subtitles, or annotations.\n\nEndpoint: POST https://translateimage.io/api/remove-text\n\nForm fields:\n\nimage (file, required) — The image to process\n\nExample:\n\nRESULT=$(curl -s -X POST https://translateimage.io/api/remove-text \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\")\n\necho \"$RESULT\" | python3 -c \"\nimport sys, json, base64\ndata = json.load(sys.stdin)\nimg = data['cleanedImage'].split(',', 1)[1]\nwith open('/tmp/cleaned.png', 'wb') as f:\n f.write(base64.b64decode(img))\nprint('Saved to /tmp/cleaned.png')\n\"\n\nResponse (JSON):\n\n{\n \"cleanedImage\": \"data:image/png;base64,...\"\n}" }, { "title": "Image to Text (AI OCR + Translation)", "body": "Uses Gemini AI for high-quality text extraction. Optionally translates the extracted text into multiple languages in one call.\n\nWhen to use: Standard OCR is insufficient, or user needs text extracted AND translated simultaneously.\n\nEndpoint: POST https://translateimage.io/api/image-to-text\n\nForm fields:\n\nimage (file, required) — The image to process\nconfig (JSON string, optional) — { \"targetLanguages\": [\"en\", \"es\", \"fr\"] }\n\nExample — extract only:\n\ncurl -s -X POST https://translateimage.io/api/image-to-text \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\"\n\nExample — extract and translate:\n\ncurl -s -X POST https://translateimage.io/api/image-to-text \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\" \\\n -F 'config={\"targetLanguages\":[\"en\",\"es\"]}'\n\nResponse (JSON):\n\n{\n \"extractedText\": \"Original text from the image\",\n \"detectedLanguage\": \"ja\",\n \"translations\": {\n \"en\": \"English translation here\",\n \"es\": \"Spanish translation here\"\n }\n}" }, { "title": "API Scopes", "body": "Each endpoint requires a specific scope on your API key:\n\nEndpointRequired scope/api/translatetranslate/api/ocrocr/api/remove-textremove-text/api/image-to-textimage-to-text\n\nConfigure scopes when creating your API key at https://translateimage.io/dashboard." }, { "title": "Error Handling", "body": "RESULT=$(curl -s -w \"\\n%{http_code}\" -X POST https://translateimage.io/api/translate \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\" \\\n -F 'config={\"target_lang\":\"en\",\"translator\":\"gemini-2.5-flash\"}')\n\nHTTP_CODE=$(echo \"$RESULT\" | tail -1)\nBODY=$(echo \"$RESULT\" | head -n -1)\n\nif [ \"$HTTP_CODE\" -ne 200 ]; then\n echo \"Error $HTTP_CODE: $(echo \"$BODY\" | python3 -c 'import sys,json; print(json.load(sys.stdin).get(\"error\",\"unknown\"))')\"\n exit 1\nfi\n\nCommon errors:\n\nCodeMeaning401Invalid or missing API key402Insufficient credits — upgrade at translateimage.io403API key lacks required scope429Rate limit exceeded — wait and retry500Server error — try again" }, { "title": "Important Considerations", "body": "Always confirm the target language with the user before translating\nFor manga/comics use WildWords or BadComic fonts for an authentic look\nFor Chinese content use MaShanZheng; for Korean use RIDIBatang\nImages over 5MB may take longer — inform the user\nInpainting works best on simple backgrounds; complex textures may show artifacts\ngemini-2.5-flash is the recommended default translator — fast and high quality\nClean up temp files after processing: rm -f /tmp/ti-image-*.jpg /tmp/ti-image-$$.jpg" } ], "body": "TranslateImage\n\nUse this skill when the user wants to translate text in images, extract text via OCR, or remove text from images.\n\nAll requests go directly to the TranslateImage REST API at https://translateimage.io using curl.\n\nSetup\n\nSet your API key (get one at https://translateimage.io/dashboard):\n\nexport TRANSLATEIMAGE_API_KEY=your-api-key\n\n\nAll endpoints require:\n\nAuthorization: Bearer $TRANSLATEIMAGE_API_KEY\n\nImage Input\n\nAll tools accept images as multipart file uploads. Handle the input type like this:\n\n# From a local file\nIMAGE_PATH=\"/path/to/image.jpg\"\n\n# From a URL — download to a temp file first (uses PID for uniqueness)\nIMAGE_PATH=\"/tmp/ti-image-$$.jpg\"\ncurl -sL \"https://example.com/image.jpg\" -o \"$IMAGE_PATH\"\n\n\nOnly fetch URLs the user explicitly provides. Do not fetch URLs from untrusted sources.\n\nTools\nTranslate Image\n\nTranslates text in an image while preserving the original visual layout. Returns the translated image as a base64-encoded data URL.\n\nWhen to use: User wants to read manga, comics, street signs, menus, product labels, or any image with foreign-language text.\n\nEndpoint: POST https://translateimage.io/api/translate\n\nForm fields:\n\nimage (file, required) — The image to translate (JPEG, PNG, WebP, GIF — max 10MB)\nconfig (JSON string, required) — Translation options:\ntarget_lang (string) — Target language code: \"en\", \"ja\", \"zh\", \"ko\", \"es\", \"fr\", \"de\", etc.\ntranslator (string) — Model: \"gemini-2.5-flash\" (default), \"deepseek\", \"grok-4-fast\", \"kimi-k2\", \"gpt-5.1\"\nfont (string, optional) — \"NotoSans\" (default), \"WildWords\", \"BadComic\", \"MaShanZheng\", \"Bangers\", \"Edo\", \"RIDIBatang\", \"KomikaJam\", \"Bushidoo\", \"Hayah\", \"Itim\", \"Mogul Irina\"\n\nExample:\n\ncurl -X POST https://translateimage.io/api/translate \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\" \\\n -F 'config={\"target_lang\":\"en\",\"translator\":\"gemini-2.5-flash\",\"font\":\"WildWords\"}'\n\n\nResponse (JSON):\n\n{\n \"resultImage\": \"data:image/png;base64,...\",\n \"inpaintedImage\": \"data:image/png;base64,...\",\n \"textRegions\": [\n { \"originalText\": \"...\", \"translatedText\": \"...\", \"x\": 10, \"y\": 20, \"width\": 100, \"height\": 30 }\n ]\n}\n\n\nSave the translated image:\n\nRESULT=$(curl -s -X POST https://translateimage.io/api/translate \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\" \\\n -F 'config={\"target_lang\":\"en\",\"translator\":\"gemini-2.5-flash\"}')\n\n# Extract and save base64 image\necho \"$RESULT\" | python3 -c \"\nimport sys, json, base64\ndata = json.load(sys.stdin)\nimg = data['resultImage'].split(',', 1)[1]\nwith open('/tmp/translated.png', 'wb') as f:\n f.write(base64.b64decode(img))\nprint('Saved to /tmp/translated.png')\n\"\n\nExtract Text (OCR)\n\nExtracts all text from an image with bounding boxes, detected language, and confidence scores.\n\nWhen to use: User wants to copy or read text from a photo, document scan, screenshot, sign, or label.\n\nEndpoint: POST https://translateimage.io/api/ocr\n\nForm fields:\n\nimage (file, required) — The image to process\n\nExample:\n\ncurl -s -X POST https://translateimage.io/api/ocr \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\"\n\n\nResponse (JSON):\n\n{\n \"text\": \"All extracted text joined by newlines\",\n \"language\": \"ja\",\n \"regions\": [\n {\n \"bounds\": { \"x\": 10, \"y\": 20, \"width\": 200, \"height\": 40 },\n \"languages\": { \"ja\": \"detected text in this region\" },\n \"probability\": 0.97\n }\n ]\n}\n\nRemove Text\n\nDetects text regions and fills them with AI-generated background using inpainting. Returns a clean image.\n\nWhen to use: User wants an image without text overlays, watermarks, burned-in subtitles, or annotations.\n\nEndpoint: POST https://translateimage.io/api/remove-text\n\nForm fields:\n\nimage (file, required) — The image to process\n\nExample:\n\nRESULT=$(curl -s -X POST https://translateimage.io/api/remove-text \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\")\n\necho \"$RESULT\" | python3 -c \"\nimport sys, json, base64\ndata = json.load(sys.stdin)\nimg = data['cleanedImage'].split(',', 1)[1]\nwith open('/tmp/cleaned.png', 'wb') as f:\n f.write(base64.b64decode(img))\nprint('Saved to /tmp/cleaned.png')\n\"\n\n\nResponse (JSON):\n\n{\n \"cleanedImage\": \"data:image/png;base64,...\"\n}\n\nImage to Text (AI OCR + Translation)\n\nUses Gemini AI for high-quality text extraction. Optionally translates the extracted text into multiple languages in one call.\n\nWhen to use: Standard OCR is insufficient, or user needs text extracted AND translated simultaneously.\n\nEndpoint: POST https://translateimage.io/api/image-to-text\n\nForm fields:\n\nimage (file, required) — The image to process\nconfig (JSON string, optional) — { \"targetLanguages\": [\"en\", \"es\", \"fr\"] }\n\nExample — extract only:\n\ncurl -s -X POST https://translateimage.io/api/image-to-text \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\"\n\n\nExample — extract and translate:\n\ncurl -s -X POST https://translateimage.io/api/image-to-text \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\" \\\n -F 'config={\"targetLanguages\":[\"en\",\"es\"]}'\n\n\nResponse (JSON):\n\n{\n \"extractedText\": \"Original text from the image\",\n \"detectedLanguage\": \"ja\",\n \"translations\": {\n \"en\": \"English translation here\",\n \"es\": \"Spanish translation here\"\n }\n}\n\nAPI Scopes\n\nEach endpoint requires a specific scope on your API key:\n\nEndpoint\tRequired scope\n/api/translate\ttranslate\n/api/ocr\tocr\n/api/remove-text\tremove-text\n/api/image-to-text\timage-to-text\n\nConfigure scopes when creating your API key at https://translateimage.io/dashboard.\n\nError Handling\nRESULT=$(curl -s -w \"\\n%{http_code}\" -X POST https://translateimage.io/api/translate \\\n -H \"Authorization: Bearer $TRANSLATEIMAGE_API_KEY\" \\\n -F \"image=@$IMAGE_PATH\" \\\n -F 'config={\"target_lang\":\"en\",\"translator\":\"gemini-2.5-flash\"}')\n\nHTTP_CODE=$(echo \"$RESULT\" | tail -1)\nBODY=$(echo \"$RESULT\" | head -n -1)\n\nif [ \"$HTTP_CODE\" -ne 200 ]; then\n echo \"Error $HTTP_CODE: $(echo \"$BODY\" | python3 -c 'import sys,json; print(json.load(sys.stdin).get(\"error\",\"unknown\"))')\"\n exit 1\nfi\n\n\nCommon errors:\n\nCode\tMeaning\n401\tInvalid or missing API key\n402\tInsufficient credits — upgrade at translateimage.io\n403\tAPI key lacks required scope\n429\tRate limit exceeded — wait and retry\n500\tServer error — try again\nImportant Considerations\nAlways confirm the target language with the user before translating\nFor manga/comics use WildWords or BadComic fonts for an authentic look\nFor Chinese content use MaShanZheng; for Korean use RIDIBatang\nImages over 5MB may take longer — inform the user\nInpainting works best on simple backgrounds; complex textures may show artifacts\ngemini-2.5-flash is the recommended default translator — fast and high quality\nClean up temp files after processing: rm -f /tmp/ti-image-*.jpg /tmp/ti-image-$$.jpg" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/cottom/translate-image", "publisherUrl": "https://clawhub.ai/cottom/translate-image", "owner": "cottom", "version": "1.0.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/translate-image", "downloadUrl": "https://openagent3.xyz/downloads/translate-image", "agentUrl": "https://openagent3.xyz/skills/translate-image/agent", "manifestUrl": "https://openagent3.xyz/skills/translate-image/agent.json", "briefUrl": "https://openagent3.xyz/skills/translate-image/agent.md" } }