Text-to-Speech, OCR Software and Apps
Text-to-Speech software and apps
This document contains some definitions of the issues and software, and lists of the software and mobile apps that perform these services.
This document is bring provided by Lorelei Pepi,
(faculty, ECUAD). If there are any suggestions for improvements or additions,
please email her at lpepi@ecuad.ca
DOWNLOAD this information as a PDF document for your use.
What's the problem and are there solutions?
Because of different reading, perception, and processing issues that we have as people, reading large amounts of text can be a significant challenge for some people. This might arise from Dyslexia, ADHD, or being on the autism-spectrum, as well as other processing issues that can affect reading and comprehension experiences.
Classes that rely on assigned reading that contains lengthy articles and chapters can become massive hurdles for people. This includes trying to do homework on time and attempting to comprehend and process what is written. These kinds of limitations might even cause someone to choose to never engage with this kind of content because it's so exhausting and frustrating.
The good news is that there are digital tools that can help make engaging with written materials possible, effective and enjoyable.
The bad news is that not all digital content is created or provided in a way that immediately allows these tools to work. More good news is that this can be remedied.
Let your faculty know
You can let your faculty know that it would be a meaningful difference to students in the class to have text-to-speech accessible readings assignments provided. This is about equitable supporting of accessibility needs.
Definitions
Optical Character Reader (OCR)
Optical character recognition or optical character reader (OCR). OCR's are scanning software that convert images of text into machine-encoded text. This includes the ability to convert scanned documents, photos of documents, a scene photo (for example the text on signs and billboards in a landscape photo) or from subtitle text superimposed on an image.
OCR is a step to make it possible to use text-to-speech software services. This is necessary if the document or image is not already selectable text.
What's the problem with assignments that are scanned page images? This prevents Text-to-Speech (TTS) apps from accessing the text content because the text you see is not converted into "selectable" and "active" text in a page. People that rely on TTS have to perform another set of tasks in order to make the content available to them. The good news is that there are software and mobile apps that can do this, and there are many free options. There is still some work involved, but it can be done.
Your own web search: Image-to-Text or Picture-to-Text
In looking for a mobile app or desktop software that can convert images to digitized text, you can also use search of "OCR software", and also phrases like “image to text software” or “picture to text software”.
Text-to-Speech Software
Text-to-speech software / app is an electronic reader that can translate digitized text content into an audible spoken-reading experience. There are free and paid options.
Some TTS software will allow you to choose different audio speeds, apply different types of reading voices, highlight text in the document as the audio is read aloud, and create digital audio files so they can be saved and listened to again.
Some of these apps can do both OCR and TTS.
Fonts: Open Dyslexia
People with dyslexia will experience text letters, symbols and numbers appearing intermixed with forwards and backwards positioning, making it very hard to read effectively. These designers created a special font that they say can make it easier for people with dyslexia to read text. It’s free, and they ask for donations if you can afford it.
Want to know more about these kinds of fonts? Check this site out.
Software and Mobile Apps
Text-to-Speech TTS Readers
Balabolka (Windows), uses OCR-ready text.
Natural Reader (Windows, Mac) uses OCR-ready text on different types of documents. Available as a desktop software and a web browser service, Free and paid versions for students up to professional uses.
Text-to-Speech Reader This is a web browser based reader, available in mobile apps and desktop. "Upload any text, file, website & book for listening online, proofreading, reading-along or generating professional mp3 voice-overs".
Zabaware Text-to-Speech Reader (Windows) This is a web browser based reader.
Voice Dream Reader is for mobile devices, Apple and Android.
Optical Character Readers (OCR) (some include Text-to-Speech)
Desktop/Web-based
A selection of free Windows-based OCR software
Adobe Acrobat Pro has OCR built in.
Microsoft Word
For many users, Microsoft Word is the default app to convert picture to text. The reason is its fast procedure and the fact that everyone has already installed this program on their PCs. This method involves a two-fold procedure to extract text from an image. First, you need to save the image file as PDF using MS Word before converting it into the editable text. Note that Word often distorts the formatting especially if your image file contains tables or graphics. Also, expect a lot of spelling mistakes that need to be corrected manually.
Google Docs
How to prepare a file and convert it
Use a file extension to use Google Docs to convert picture to 5text inside of Google Docs. Simply drag and drop your image or click to upload and watch as Optical Character Recognition (OCR) is automatically applied to extract your text. Next, you can make quick edits in the preview box, before hitting the "Insert" button to insert your text into a doc. Supports PNG, JPG, BMP, and PMB files - perfect for quick note-taking from screenshots.
Mobile Device apps
Google Lens (Google app) and LiveText (iOS only) are ways to use your phone camera to have image-text converted. Good for “on the go” efforts.
Image to Text document scanner app for Android devices
VDScan is an iPhone app that does OCR and Text-to-Speech. "Scan paper documents, labels, signs with the camera and recognize text. Listen using built-in text-to-speech. Save and export. Unlimited use: no subscriptions or additional charges."
Microsoft Lens (Lens for iOS), Office Lens
Trims, enhances, and makes pictures of whiteboards and documents readable.
You can use Microsoft Lens to convert images to PDF, Word, PowerPoint, and Excel files, digitize printed or handwritten text, and save to OneNote, OneDrive, or your local device. You can even import images that are already on your device using Gallery.
Google Keep (iOS and Android)
This app will OCR an image, while the primary function of this software is making notes. Using its built-in OCR feature, you can quickly extract text from images and make notes. Since it is a free OCR cell phone app, don’t expect super-high accuracy of your extracted text.
Adobe Scan (iOS and Android)
The Adobe Scan scanner app turns your device into a powerful portable scanner that recognizes text automatically (OCR) and allows you to save to multiple files formats including PDF and JPEG.
"The most intelligent scanner app!" Scan anything — receipts, notes, documents, photos, business cards, whiteboards — with text you can reuse from each PDF and photo scan.
Text Fairy (Android)
Free
• Extract text from images.
• Edit, share, or export as PDF
• Works offline to protect your privacy.
• Reads text out loud. (Text-to-speech, TTS)
• Recognizes printed text from more than 110 languages.