Frame OCR

Run OCR on a single image or key video frame and return structured text — subtitles, receipts, and on-screen copy.

Capability ID: video.engine.vision.ocr_frame
Playground trial available
Publisher: ONLINESVR

# Frame OCR

Recognize text from images or video frames.

## Use cases
- Subtitle / on-screen text extraction
- Receipt and label OCR
- Vision pipeline preprocess

## Try
Playground trials when entitlement allows.

Frequently Asked Questions

How do I run this Capability?

Use Try for free (Playground) when enabled, or submit via Gateway after sign-in.

Is the Store listing the same as execution permission?

No. Published listing is discovery only; each run still checks identity, entitlement, schema, and release.