Image Translate OCR Only

Detect and read text in a product image. Returns recognised regions with polygons, bounding boxes, text, and confidence — no inpainting, no translation, no rendering.

Endpoint

POST /v1/image-translate/ocr

Run only the OCR step from the full pipeline. Returns recognised text regions with their geometry and confidence scores. No image is modified, nothing is translated, no final image is produced. Use this when you only need text coordinates and content — for example, to pre-screen images or to drive a custom downstream workflow.

Cheaper per call than /translate.

Request Format

The endpoint accepts raw image bytes in the HTTP body. JSON-with-base64 is not accepted.

Header	Required	Notes
`Content-Type`	Yes	`image/jpeg`, `image/png`, `image/webp`, or `application/octet-stream`
`x-api-key`	Yes	Your API key

All other parameters travel in the query string:

Parameter	Type	Required	Default	Description
`source_language`	string	Yes	—	One of `ch`, `zh`, `zh-CN`, `zh-TW`, `chinese_cht`, `ja`, `japan`, `en`, or `auto`.

Response

{
  "success": true,
  "requestId": "550e8400e29b41d4a716446655440000",
  "data": {
    "regions": [
      {
        "polygon": [[10, 20], [210, 20], [210, 60], [10, 60]],
        "bbox": { "x": 10, "y": 20, "w": 200, "h": 40 },
        "text": "免费送货",
        "confidence": 0.98
      }
    ],
    "src_w": 790,
    "src_h": 1158,
    "regions_found": 1
  }
}

Field	Type	Description
`regions[].polygon`	number[][]	4-point polygon in original image coordinates.
`regions[].bbox`	object	Axis-aligned bounding box `{x, y, w, h}` in original coordinates.
`regions[].text`	string	Recognised text.
`regions[].confidence`	number	Recognition confidence, 0–1.
`src_w`, `src_h`	integer	Original image width and height in pixels.
`regions_found`	integer	Number of recognised regions returned.

Examples

cURL

curl -X POST "https://gateway.apinoa.com/v1/image-translate/ocr?source_language=zh-CN" \
  -H "x-api-key: $APINOA_API_KEY" \
  -H "Content-Type: image/jpeg" \
  --data-binary @product.jpg

Python

import requests

with open("product.jpg", "rb") as f:
    img_bytes = f.read()

r = requests.post(
    "https://gateway.apinoa.com/v1/image-translate/ocr",
    headers={
        "x-api-key": "YOUR_API_KEY",
        "Content-Type": "image/jpeg",
    },
    params={"source_language": "zh-CN"},
    data=img_bytes,
    timeout=60,
)
r.raise_for_status()
for region in r.json()["data"]["regions"]:
    print(region["text"], region["confidence"])

Limits

Limit	Value
Max image dimensions	8192 × 8192 px
Max request body	20 MB
Image format	JPEG, PNG, WebP

Errors

Code	HTTP	When
`BAD_REQUEST`	400	Empty body or invalid query params
`UNAUTHORIZED`	401	Missing or invalid API key
`UNSUPPORTED_MEDIA_TYPE`	415	`Content-Type` is not a binary image type
`PAYLOAD_TOO_LARGE`	413	Body > 20 MB
`INSUFFICIENT_BALANCE`	402	Your balance does not cover the call
`UPSTREAM_ERROR`	502	Recognition temporarily unavailable

Pricing

Each call is charged against your balance at the image-translate rate on the pricing page.

OCR Only

On this page