How to Convert Images to Text in Thunkable (using the mobile camera)?

Questions about Thunkable
1

Hi everyone,

I’m currently participating in the Technovation Challenge, where we’re creating an app to solve a community problem. I started developing the app in MIT App Inventor and successfully implemented an image-to-text feature using the ML Kit Text Recognition extension (link to extension).

However, I’ve switched to Thunkable to support iOS devices, but I haven’t found a way to implement the same functionality. I’ve seen that it’s possible to use the OCR.space API (link to API), but this requires uploading images to a server, which is not ideal for my use case. I’d like to use the mobile camera to capture images and directly convert them to text without needing to upload the image.

Does anyone know how to achieve this in Thunkable? Are there any extensions or other methods that work well for this scenario?

Thanks in advance for your help!

2

You can use the image recognition block in Thunkable: Camera Blocks | Thunkable Docs.

Otherwise, you’d need a third-party API.

1 Like
3

Thanks for the quick answer @tatiang

I’ll definitely give it a try but do you know whether the description of the image include the embedded text (if any)? Thanks again!

4

Oh sorry, I forget as I haven’t used it in a while. To get good results, you need to pay for an API with OCR capabilities. There is no way around that.