‘SayText’ reads aloud the text in the image. It is intended for visually impaired users. SayText is a free spin off product from the DocScanner team.
- Place the iPhone center of a document and double-tap the “Take picture” -button
- Slowly elevate the iPhone upwards from the document, until the whole document is in picture. A beep sound indicates, that the document has been detected. The camera will shoot automatically when focused
- While the OCR is running, tap the screen to hear the progress status
- When the OCR is ready, swipe right on the screen to listen the document
Voice – Take Pictures & Have Them Read w/ Fast OCR
By Shalin Shah
Take a picture of anything that has words on it, and Voice will read it to you! Designed for iOS 8, this simple and easy to use interface will let you listen to all your books/words/documents/magazines in a matter of seconds.
Running late for work? Just snap a photo of a newspaper article, put on your headphones, and let Voice do the reading for you while you drive peacefully without grieving over not being able to read the news for today.
People with visual impairment or dyslexia can easily snap a photo of anything and have it read in a matter of seconds. Whether it is a menu at a restaurant, a medicine label, and expiration date on a milk carton, or even an information board at a museum.
Foreign exchange students can read and listen to an english book at the same time using this app. Thus, listening to pronunciation and following along, word-by-word.
– Book mode – reads multiple pictures or pages one after another but it takes the same processing time as it does for a single picture. As the initial image is being read, the next image is being processed in the background, and so on… therefore it does not use additional processing time.
– Multiple languages – Reads/Detects in over 30 different languages
– Field of view report – says when all 4 corners of the document are visible
– Auto capture photos without any user interaction.
– Precise document area boundaries detection for better recognition
– Smart Crop – offers the possibility to estimate the quality of the document area boundary detection and make a decision about cropping (to improve processing time).
– Two-dimensional geometric and three-dimensional perspective distortion correction (for better OCR).
– Improved accessibility and made fully compatible with VoiceOver
– Document image auto alignment and rotation.