Seeing AI

Microsoft Corporation

About this app

Seeing AI is a free app that narrates the world around you. Designed with and for the blind and low vision community, this ongoing research project harnesses the power of AI to open up the visual world by describing nearby people, text and objects.

Seeing AI provides tools to assist with a variety of daily tasks:
• Read - Hear text as soon as it appears in front of the camera. Document alignment provides audio cues to capture a printed page and recognize the text along with its original formatting. Ask Seeing AI about the contents to easily find the information you need.
• Describe - Take photos to hear a rich description. Ask questions to focus on the information you care about. Explore photos by moving your finger over the screen to hear the location of different objects.
• Products - Scan barcodes and Accessible QR codes using audio beeps to guide you; hear the product name and package information when available.
• People - Save photos of friends and coworkers so you can recognize them later. Get an estimate of their age, gender, and expression.
• Currency - Recognize currency notes.
• Colors - Identify colors.
• Light - Hear an audible tone corresponding to the brightness of your surroundings.
• Photos and Videos in other apps - Just tap “Share” and “Recognize with Seeing AI” to describe media from Mail, Photos, WhatsApp, and more.

Seeing AI continues to evolve as we hear from the community, and AI research advances.

Questions, feedback or feature requests? Email us at [e-mail].

Ratings and reviews

For an initial release of an app that has OCR, color detection, people count and description, scene description, and more, very impressive! One break or make test of an OCR app is out of focus text that isn't perfectly straight. Holding a bag of candies and scanning the ingredients, out of focus and not aligned, did quite well! Impressed and will be quite useful for those with limited vision or aging eyes. Definitely fast enough to be used besides magnifying glasses. Fun, fast, useful!

Thanks for the app! Wishlist for future versions: don't lock text recognition language to the device's system, allow for several packs to be downloaded and switching between languages in-app; ideally, make AI recognize the language used in scanned text and switch automatically or warn that the text's language doesn't match any installed pack. An integration with a translation service would be another step forward.

I'm using a Samsung Ultra 25 and have tried to use the app install and reinstall multiple times. it won't shut up. and it's using a language model that my phone doesn't use, annoying high pitch and all of the speech controls are grayed out. I spent an hour trying to disable the talk back portion of it, verifying my phone talk back (which uses a viable speech model) was off.

What’s new

This release includes several bug fixes to make your experience even better.