# Send Translate Image to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- 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.
## Suggested prompts
### New install

```text
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.
```
### Upgrade existing

```text
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.
```
## Machine-readable fields
```json
{
  "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": {
    "downloadUrl": "/downloads/translate-image",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=translate-image",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "metadata.json"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "translate-image",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-04T05:09:04.669Z",
      "expiresAt": "2026-05-11T05:09:04.669Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=translate-image",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=translate-image",
        "contentDisposition": "attachment; filename=\"translate-image-1.0.3.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "translate-image"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "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."
      ]
    }
  },
  "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"
  }
}
```
## Documentation

### TranslateImage

Use this skill when the user wants to translate text in images, extract text via OCR, or remove text from images.

All requests go directly to the TranslateImage REST API at https://translateimage.io using curl.

### Setup

Set your API key (get one at https://translateimage.io/dashboard):

export TRANSLATEIMAGE_API_KEY=your-api-key

All endpoints require:

Authorization: Bearer $TRANSLATEIMAGE_API_KEY

### Image Input

All tools accept images as multipart file uploads. Handle the input type like this:

# From a local file
IMAGE_PATH="/path/to/image.jpg"

# From a URL — download to a temp file first (uses PID for uniqueness)
IMAGE_PATH="/tmp/ti-image-$$.jpg"
curl -sL "https://example.com/image.jpg" -o "$IMAGE_PATH"

Only fetch URLs the user explicitly provides. Do not fetch URLs from untrusted sources.

### Translate Image

Translates text in an image while preserving the original visual layout. Returns the translated image as a base64-encoded data URL.

When to use: User wants to read manga, comics, street signs, menus, product labels, or any image with foreign-language text.

Endpoint: POST https://translateimage.io/api/translate

Form fields:

image (file, required) — The image to translate (JPEG, PNG, WebP, GIF — max 10MB)
config (JSON string, required) — Translation options:

target_lang (string) — Target language code: "en", "ja", "zh", "ko", "es", "fr", "de", etc.
translator (string) — Model: "gemini-2.5-flash" (default), "deepseek", "grok-4-fast", "kimi-k2", "gpt-5.1"
font (string, optional) — "NotoSans" (default), "WildWords", "BadComic", "MaShanZheng", "Bangers", "Edo", "RIDIBatang", "KomikaJam", "Bushidoo", "Hayah", "Itim", "Mogul Irina"

Example:

curl -X POST https://translateimage.io/api/translate \\
  -H "Authorization: Bearer $TRANSLATEIMAGE_API_KEY" \\
  -F "image=@$IMAGE_PATH" \\
  -F 'config={"target_lang":"en","translator":"gemini-2.5-flash","font":"WildWords"}'

Response (JSON):

{
  "resultImage": "data:image/png;base64,...",
  "inpaintedImage": "data:image/png;base64,...",
  "textRegions": [
    { "originalText": "...", "translatedText": "...", "x": 10, "y": 20, "width": 100, "height": 30 }
  ]
}

Save the translated image:

RESULT=$(curl -s -X POST https://translateimage.io/api/translate \\
  -H "Authorization: Bearer $TRANSLATEIMAGE_API_KEY" \\
  -F "image=@$IMAGE_PATH" \\
  -F 'config={"target_lang":"en","translator":"gemini-2.5-flash"}')

# Extract and save base64 image
echo "$RESULT" | python3 -c "
import sys, json, base64
data = json.load(sys.stdin)
img = data['resultImage'].split(',', 1)[1]
with open('/tmp/translated.png', 'wb') as f:
    f.write(base64.b64decode(img))
print('Saved to /tmp/translated.png')
"

### Extract Text (OCR)

Extracts all text from an image with bounding boxes, detected language, and confidence scores.

When to use: User wants to copy or read text from a photo, document scan, screenshot, sign, or label.

Endpoint: POST https://translateimage.io/api/ocr

Form fields:

image (file, required) — The image to process

Example:

curl -s -X POST https://translateimage.io/api/ocr \\
  -H "Authorization: Bearer $TRANSLATEIMAGE_API_KEY" \\
  -F "image=@$IMAGE_PATH"

Response (JSON):

{
  "text": "All extracted text joined by newlines",
  "language": "ja",
  "regions": [
    {
      "bounds": { "x": 10, "y": 20, "width": 200, "height": 40 },
      "languages": { "ja": "detected text in this region" },
      "probability": 0.97
    }
  ]
}

### Remove Text

Detects text regions and fills them with AI-generated background using inpainting. Returns a clean image.

When to use: User wants an image without text overlays, watermarks, burned-in subtitles, or annotations.

Endpoint: POST https://translateimage.io/api/remove-text

Form fields:

image (file, required) — The image to process

Example:

RESULT=$(curl -s -X POST https://translateimage.io/api/remove-text \\
  -H "Authorization: Bearer $TRANSLATEIMAGE_API_KEY" \\
  -F "image=@$IMAGE_PATH")

echo "$RESULT" | python3 -c "
import sys, json, base64
data = json.load(sys.stdin)
img = data['cleanedImage'].split(',', 1)[1]
with open('/tmp/cleaned.png', 'wb') as f:
    f.write(base64.b64decode(img))
print('Saved to /tmp/cleaned.png')
"

Response (JSON):

{
  "cleanedImage": "data:image/png;base64,..."
}

### Image to Text (AI OCR + Translation)

Uses Gemini AI for high-quality text extraction. Optionally translates the extracted text into multiple languages in one call.

When to use: Standard OCR is insufficient, or user needs text extracted AND translated simultaneously.

Endpoint: POST https://translateimage.io/api/image-to-text

Form fields:

image (file, required) — The image to process
config (JSON string, optional) — { "targetLanguages": ["en", "es", "fr"] }

Example — extract only:

curl -s -X POST https://translateimage.io/api/image-to-text \\
  -H "Authorization: Bearer $TRANSLATEIMAGE_API_KEY" \\
  -F "image=@$IMAGE_PATH"

Example — extract and translate:

curl -s -X POST https://translateimage.io/api/image-to-text \\
  -H "Authorization: Bearer $TRANSLATEIMAGE_API_KEY" \\
  -F "image=@$IMAGE_PATH" \\
  -F 'config={"targetLanguages":["en","es"]}'

Response (JSON):

{
  "extractedText": "Original text from the image",
  "detectedLanguage": "ja",
  "translations": {
    "en": "English translation here",
    "es": "Spanish translation here"
  }
}

### API Scopes

Each endpoint requires a specific scope on your API key:

EndpointRequired scope/api/translatetranslate/api/ocrocr/api/remove-textremove-text/api/image-to-textimage-to-text

Configure scopes when creating your API key at https://translateimage.io/dashboard.

### Error Handling

RESULT=$(curl -s -w "\\n%{http_code}" -X POST https://translateimage.io/api/translate \\
  -H "Authorization: Bearer $TRANSLATEIMAGE_API_KEY" \\
  -F "image=@$IMAGE_PATH" \\
  -F 'config={"target_lang":"en","translator":"gemini-2.5-flash"}')

HTTP_CODE=$(echo "$RESULT" | tail -1)
BODY=$(echo "$RESULT" | head -n -1)

if [ "$HTTP_CODE" -ne 200 ]; then
  echo "Error $HTTP_CODE: $(echo "$BODY" | python3 -c 'import sys,json; print(json.load(sys.stdin).get("error","unknown"))')"
  exit 1
fi

Common errors:

CodeMeaning401Invalid or missing API key402Insufficient credits — upgrade at translateimage.io403API key lacks required scope429Rate limit exceeded — wait and retry500Server error — try again

### Important Considerations

Always confirm the target language with the user before translating
For manga/comics use WildWords or BadComic fonts for an authentic look
For Chinese content use MaShanZheng; for Korean use RIDIBatang
Images over 5MB may take longer — inform the user
Inpainting works best on simple backgrounds; complex textures may show artifacts
gemini-2.5-flash is the recommended default translator — fast and high quality
Clean up temp files after processing: rm -f /tmp/ti-image-*.jpg /tmp/ti-image-$$.jpg
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: cottom
- Version: 1.0.3
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-04T05:09:04.669Z
- Expires at: 2026-05-11T05:09:04.669Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/translate-image)
- [Send to Agent page](https://openagent3.xyz/skills/translate-image/agent)
- [JSON manifest](https://openagent3.xyz/skills/translate-image/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/translate-image/agent.md)
- [Download page](https://openagent3.xyz/downloads/translate-image)