Google Vision OCR

Class: GoogleVisionOCRBlockV1

Source: inference.core.workflows.core_steps.models.foundation.google_vision_ocr.v1.GoogleVisionOCRBlockV1

Detect text in images using Google Vision OCR.

Supported types of text detection:

• text_detection: optimized for areas of text within a larger image.
• ocr_text_detection: optimized for dense text documents.

You need to provide your Google Vision API key to use this block.

Type identifier

Use the following identifier in step "type" field: roboflow_core/google_vision_ocr@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
ocr_type	str	Type of OCR to use.	❌
language_hints	List[str]	Optional list of language codes to pass to the OCR API. If not provided, the API will attempt to detect the language automatically.If provided, language codes must be supported by the OCR API, visit https://cloud.google.com/vision/docs/languages for list of supported language codes..	❌
api_key	str	Your Google Vision API key.	✅

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to Google Vision OCR in version v1.

• inputs: Local File Sink, LMM, Depth Estimation, OpenAI, Classification Label Visualization, Google Vision OCR, Stability AI Image Generation, Camera Calibration, Ellipse Visualization, SIFT, Blur Visualization, Stitch OCR Detections, Circle Visualization, Dot Visualization, Image Blur, LMM For Classification, Clip Comparison, Background Color Visualization, CSV Formatter, Stitch Images, Instance Segmentation Model, Multi-Label Classification Model, CogVLM, Image Slicer, Roboflow Dataset Upload, Absolute Static Crop, Twilio SMS Notification, Color Visualization, Pixelate Visualization, Florence-2 Model, OpenAI, Label Visualization, Google Gemini, Stability AI Inpainting, Single-Label Classification Model, Polygon Zone Visualization, Relative Static Crop, VLM as Detector, OCR Model, Roboflow Dataset Upload, Keypoint Visualization, Bounding Box Visualization, Mask Visualization, Model Comparison Visualization, Llama 3.2 Vision, Slack Notification, Object Detection Model, VLM as Classifier, Image Preprocessing, Line Counter Visualization, Roboflow Custom Metadata, Grid Visualization, Anthropic Claude, SIFT Comparison, Webhook Sink, Image Convert Grayscale, Halo Visualization, Trace Visualization, Corner Visualization, Polygon Visualization, Triangle Visualization, Model Monitoring Inference Aggregator, Keypoint Detection Model, Florence-2 Model, Image Contours, Perspective Correction, Dynamic Crop, Crop Visualization, Camera Focus, Reference Path Visualization, Email Notification, Image Slicer, Image Threshold
• outputs: LMM, Classification Label Visualization, Stitch OCR Detections, LMM For Classification, Clip Comparison, Line Counter, Instance Segmentation Model, CogVLM, Byte Tracker, Roboflow Dataset Upload, Distance Measurement, Twilio SMS Notification, Florence-2 Model, Byte Tracker, OpenAI, Label Visualization, Path Deviation, Roboflow Dataset Upload, Detections Stitch, Bounding Box Visualization, Llama 3.2 Vision, Model Comparison Visualization, Slack Notification, Pixel Color Count, Detections Consensus, Detections Merge, Halo Visualization, Detection Offset, Overlap Filter, Triangle Visualization, Model Monitoring Inference Aggregator, Time in Zone, Reference Path Visualization, Perspective Correction, Dynamic Crop, Time in Zone, Cache Get, Detections Classes Replacement, Detections Transformation, Florence-2 Model, Cache Set, Local File Sink, Path Deviation, OpenAI, Google Vision OCR, Stability AI Image Generation, Ellipse Visualization, Size Measurement, Blur Visualization, Circle Visualization, Dot Visualization, Image Blur, CLIP Embedding Model, Background Color Visualization, Color Visualization, Detections Filter, Byte Tracker, Pixelate Visualization, Google Gemini, Stability AI Inpainting, Polygon Zone Visualization, Detections Stabilizer, Keypoint Visualization, Mask Visualization, Velocity, Image Preprocessing, Line Counter Visualization, Roboflow Custom Metadata, Anthropic Claude, Webhook Sink, SIFT Comparison, YOLO-World Model, Trace Visualization, Instance Segmentation Model, Corner Visualization, Polygon Visualization, Segment Anything 2 Model, Crop Visualization, Email Notification, Line Counter, Image Threshold

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Google Vision OCR in version v1 has.

Bindings

• input

  • image (image): Image to run OCR.
  • api_key (Union[string, secret]): Your Google Vision API key.

• output

  • text (string): String value.
  • language (string): String value.
  • predictions (object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.

Example JSON definition of step Google Vision OCR in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/google_vision_ocr@v1",
    "image": "$inputs.image",
    "ocr_type": "<block_does_not_provide_example>",
    "language_hints": [
        "en",
        "fr"
    ],
    "api_key": "xxx-xxx"
}