Text-to-Speech Is for Everyone

by | Jun 13, 2024 | Accessibility, Digital Accessibility, Student

A woman in a beige hoodie wears headphones while sitting down at a desk. She faces a window with her back to the camera.

The academic life is filled with reading. Whether you are a student with copious amounts of coursework, or a professional academic balancing teaching, research, and keeping up with current literature, reading is central to success. While reading can be enjoyable, spending long amounts of time staring at a screen can leave you with tired eyes and a foggy brain.

Text-to-Speech (TTS) tools offer a potential solution to these challenges. These tools convert written text into spoken audio, giving your eyes a well-deserved break. Imagine listening to your books or papers while commuting to class, exercising at the gym, or even doing chores around the house. TTS tools can transform your reading experience, enabling you to absorb information more efficiently and comfortably. By incorporating a TTS tool into your workflow, you can learn on the go and potentially free up valuable time. No matter who you are, you may find that an AI text-to-speech tool can help alleviate the stress caused by your “to-read list.”  

Natural Reader

Natural Reader is a TTS tool that allows you to conveniently upload documents and webpages on your computer or mobile device. Within the reader you can control the audio speed, voice, and word pronunciation. Additionally, you can make annotations and highlights to keep track of important quotes as you listen. Despite occasional stilted voice output, Natural Reader is an excellent option for converting text to speech.

A screen capture of the Natural Reader software. The voice options and speed controls are at the top of the screen, and the text being read aloud is highlighted.

Natural Reader offers three main subscription levels for personal use:

  • Free Plan: This plan provides access to basic features like unlimited use of their “Free Voices” and functionalities like skipping text in parentheses, basic pronunciation editing, highlighting, annotating, and auto-scrolling.
  • Premium Plan: This plan includes all Free plan features along with access to their “Premium Voices” for unlimited listening across the desktop app, mobile app, and Chrome extension. Additionally, it unlocks features like Optical Character Recognition (OCR) for converting scanned documents and PDFs to readable text, MP3 conversion for personal use with a limit of 1 million characters per month, and AI Smart Filtering to skip irrelevant sections like page numbers or headers. This tier is freely available for students and faculty at the University of Chicago through the University group license. To gain access, send an email request to text.sds@uchicago.edu.
  • Plus Plan: This plan offers all the features of the Premium plan along with access to their “Plus Voices,” a collection of high-quality AI voices with a wider range of languages compared to the Premium tier. The Plus plan also increases the MP3 conversion limit to 500,000 characters per user per day for downloadable audio files.

Premium Voice Example

 

Sensus Access

If you’re affiliated with the University of Chicago and have an active @uchicago.edu email address, Sensus Access is a valuable resource for making your academic materials more accessible. Sensus Access converts documents into accessible formats such as machine-readable text PDFs, Word documents, EPUBs, or MP3s for listening on the go.

Unlike the options discussed above, Sensus Access is only available through a browser, and takes more time to convert uploaded documents. Once the conversion is completed, users will receive an email containing a link to the MP3 file. Additionally, there is no option to skip content such as references, footnotes, or watermarks unless you remove them yourself in a document editor.

Although it does not sound as polished or natural as the alternative options, Sensus Access is free and does not require you to contact anyone in order to use the tool. To learn more about how to use Sensus Access, check out this instructional video.

A screen capture of the Sensus Access media conversion webpage. Flags representing each of the supported languages is at the top of the screen, with the text "Alternate media made easy" and file upload type below it.

Sensus Access Example

 

Speechify

Speechify is another AI TTS tool, similar to Natural Reader. It has many of the same features, but includes numerous voices with different accents, pitch, and intonation that may be more engaging than the options available through Natural Reader’s Plus plan. Out of all the tools listed in this post, Speechify arguably has the most human-sounding voices, which make it easier to follow along without the text open in front of you. If you want an experience closer to audiobook listening, Speechify is a good choice.

While it excels in reading out text, Speechify has a number of other issues that you should consider before adopting it as your primary TTS tool. The reader often struggles with skipping through footers, headers, and reading multilingual documents. Additionally, you cannot highlight in the document reader, and there is no free option available to those affiliated with UChicago. Finally, Speechify offers a “Canvas integration” which involves asking for your Canvas API token. While this may seem harmless, this gives speechify full access to your Canvas data, just as if you gave it your username and password. To read more about this security risk, see our previous post: Protect Your Canvas Data: API Tokens and Security Risks. 

A screen capture from the Speechify web-based reading environment. The media player controls are at the bottom of the screen with the text being read highlighted above it.

Speechify primarily runs in your browser, and has a browser extension compatible with Chrome and Safari. Similar to Natural Reader, Speechify also has an app that allows users to upload scans and images from physical documents from their mobile device.

Speechify Example

 

Adobe Acrobat

You may find it simplest to use the built-in tools that come with frequently used applications like Adobe Acrobat. The free version of Adobe Acrobat offers a sufficient text-to-speech option in a pinch, although it may sound less natural compared to other options explored here. However, despite its limitations, it can be a reliable choice for individuals who prefer to take notes while they listen. While it may not offer the advanced features of a specialized TTS software, its familiarity and ease of use make it a valuable tool in certain situations.

A screen capture of the Adobe Acrobat PDF reader with the drop down menu open demonstrating how to navigate to the read aloud option.

Adobe Acrobat Example

 

Immersive Reader

Finally, if you prefer the Microsoft Suite, you’ll be pleased to know that the Immersive Reader tool is available in Word, OneNote, Outlook, Excel, etc., in addition to Canvas. Immersive Reader offers a read aloud option with both male and female voices, as well as speed control. Pairing this with other Immersive Reader features like line focus and page color adjustment allows you to create an engaging, distraction free reading experience.

For longer documents like papers, articles, or book chapters, using the Immersive Reader in Word is the best option. While using it, you can still add comments, highlight, underline, and make any other necessary edits. If you do not have access to your document in .DOCX format, Sensus Access can be used to convert it through the Accessibility Conversion option, which allows you to specify the .DOCX format as an output. Although the conversion and upload process takes a few extra steps, you may find them worthwhile to tailor the reading experience that works best for you.

A screen capture of the Microsoft Word software with the Immersive Reading tool selected. The media player controls are on the top right, and three lines of text are focused on in the middle of the screen.

Immersive Reader Example

 

Feature Comparison at a Glance

In the following table, you will find a brief comparison of each tool discussed above.

Natural Reader

Sensus Access

Speechify

Adobe Acrobat

Immersive Reader in Microsoft Word

Cost

The Premium tier is free under the UChicago group license.

Free with an @uchicago email

Paid

Free with Adobe Acrobat

Free with Word

Voice Options

100+

One for each language offered

100+

Male or Female

Male or Female

Multiple Language Support

Yes

Yes

Yes

Yes

Yes

Speed Control

Yes

Yes

Yes

Yes

Yes

Content Skipping options

AI skipping for headers and footers. Effective most of the time.

No

AI skipping for headers and footers, but rarely effective.

Manual

Manual

Offline Functionality

Yes

No

Yes

Yes

Yes

MP3 Download

Yes

Yes

Yes

No

No

Annotation

Yes

No

No

Yes

Yes

Mobile App

Yes

No

Yes

Yes

Yes

 

Conclusion

In the end, selecting the right text-to-speech software for you depends on your unique requirements and preferences. Whether you prioritize natural-sounding voices, ease of use, or annotation capabilities and MP3 conversion, there is a TTS tool out there that can enhance your reading experience. Ultimately, the right TTS tool is the one that best fits into your workflow, helping you to absorb information efficiently and comfortably. Happy listening!

Further Resources and Getting Help

If you have any questions about Canvas or other tools for teaching with technology, Academic Technology Solutions is here to help. You’re welcome to attend one of our workshops, stop by our office hours (no appointment required), or set up a consultation with us.