Free
Image to Text (OCR)
Extract text from an image or screenshot with vision AI.
Vision LLM OCRCopy editable textHandwriting and screenshotsFree
Frequently asked questions
Built with Pixeltable
Fact sheet
Last updated
| Modality | Image |
|---|---|
| Inputs | Image plus an instruction |
| Outputs | Model text about the image |
| Computed column | gemini.generate_content on the image and the prompt |
| What updates | A new or changed row recomputes only that row. Unchanged rows stay cached. |
| Canonical doc | gemini.generate_content |
Runnable sample
import pixeltable as pxt
from pixeltable.functions.gemini import generate_content
TableModel = pxt.model_base()
class Ocr(TableModel, name='ocr'):
source_image: pxt.Image
prompt: pxt.String
vision_response = generate_content(
contents=[source_image, prompt],
model='gemini-2.5-flash',
)Related tools
- Alt Text Generator
Modality: Image
Computed column: gemini.generate_content on the image and the prompt
Docs - Image Lab
Modality: Image
Computed column: Computed column on an Image column
Docs