Use the following interactive web application to evaluate Cloud Vision and
return image annotations for your image file. Test computer vision capabilities
such as object detection, label detection, [optical character recognition
(OCR)](https://docs.cloud.google.com/vision/docs/ocr), and [SafeSearch](https://docs.cloud.google.com/vision/docs/detecting-safe-search)
detection. Click the **Show JSON** button to view the raw API response.

## Interactive image demo

Before you try the demo, note the following requirements and limitations:

- Maximum file size is 20 MB.
- You must use a [supported image format](https://docs.cloud.google.com/vision/docs/supported-files). PDF and TIFF files are not supported for the demo.
- Your browser must have JavaScript enabled.
- The demo text^†^ is available only in English. However, you can provide images in any of the [supported languages](https://docs.cloud.google.com/vision/docs/languages).

> [!NOTE]
> **Note:** Vision API offers two [feature types](https://docs.cloud.google.com/vision/docs/features-list#text-detection) for text detection (also called optical character recognition, or OCR). The text detection feature used in this demo is [`DOCUMENT_TEXT_DETECTION`](https://docs.cloud.google.com/vision/docs/pdf). Results from this feature may differ from results returned from a [`TEXT_DETECTION`](https://docs.cloud.google.com/vision/docs/ocr) feature request.
>
> This demo uses the `builtin/latest`
> model for text detection. See
> [Release notes](https://docs.cloud.google.com/vision/docs/release-notes)
> for a list of recently updated models in Vision API.

## Demo instructions and controls

^†^  

**Demo instructions**: Try the API. Drag an image file here or
browse from your computer.

**Demo tabs**: Objects, Labels, Properties (Dominant Colors, Crop Hints, Aspect
Ratio), Safe Search (Adult, Spoof, Medical, Violence, Racy). Likeliness values
are Unknown, Very Unlikely, Unlikely, Possible, Likely, and Very Likely.

**Demo buttons** : Show JSON,
Reset,
New file.