Sometimes, information technology's better to listen than to read. When you lot walk, bike, or drive, for example, information technology'southward safer to continue your optics focused on the world around you.

Text-to-speech (TTS) offers an alternative to listening to music, podcasts, or audiobooks. TTS tin can exist a neat mode to catch up on articles you intend to read. For instance, Mozilla'due south read afterwards service, Pocket, includes the ability to listen to articles.

TTS solves a slightly different problem than the assistive voice capabilities bachelor for the major platforms, such as Android TalkBack, iOS VoiceOver, Chromevox, Windows Narrator, and Mac VoiceOver. These tools typically read everything on a page–content plus navigation.

The following four TTS apps specialize in reading articles and documents you choose. While all of these apps provide text-to-speech capabilities, each app serves a slightly different set of needs. Some apps show the text every bit it is spoken, while others offer a diversity of voices.

All of these apps work on iOS, and support the capability to share an article from the browser to the app via the native iOS sharing system functions. Importantly, every bit of July 2017, all four of these apps are under active development: The iOS app for each was updated in June or July 2017 at least once.

1. Motoread

(iOS, Chrome, and Safari desktop extensions)

I think of Motoread as a podcatcher for articles: Transport an article to the app, so listen to saved articles afterwards. There are Chrome and Safari extensions that let you add an article to your Motoread list from your desktop browser with a click. (As of early July 2017, an Android app is listed as "coming shortly".)

The app reads manufactures in a single voice, although you may adapt the playback speed. You can also cull to display the text of the article equally you listen. The app is complimentary, although yous can upgrade (for $1.99/month or $19.99/year) to become the power to add together an unlimited number of articles.

two. Vocalisation Dream Reader

(iOS, Android)

Voice Dream Reader shows the text of the article being read, and highlights each give-and-take every bit it is spoken. Since the app was originally developed as an assistive tool, you can conform the size, font, spacing, and color of the text displayed during playback. Vocalization Dream supports adjustable playback speeds, and allows y'all to customize pause fourth dimension betwixt sentences, also. You can select from several organisation voices, and set a preferred speed, pitch, and book for the voice. You can as well add documents to listen to from Dropbox, Google Drive, Evernote, and other sources.

Voice Dream Reader typically costs $14.99, and a wide selection of boosted voices are available for purchase, too–at a cost of upwards to $4.99 per vocalization.

3. Speech Central

(iOS, macOS, Windows, Android)

Speech Central works on more than platforms than any of the other apps here, with apps bachelor for iOS, macOS, Windows, and Android (although the app is available from Amazon, non the Google Play store). It likewise supports the power to read text from other formats, such as Word, PDF, and more than. On iOS, the app supports the system voices, although you tin can conform the vocalisation pitch, as well as the default 1x speed to be slightly faster or slower.

Spoken communication Key shows the text, with a subtle colored vertical line displayed along the left side of the text of the paragraph as it is spoken. The app will denote the calculated reading fourth dimension for longer articles, which may be useful if you listen while traveling, and you can change playback speed (between .8x and 2x default speed). Speech Central besides offers the ability to shuffle voices, so you don't have to mind to several articles in a row read with the same synthesized voice.

The desktop platform apps are non free, at $6.99 for macOS and $9.99 for Windows 10, although the mobile apps are gratuitous, with an optional erstwhile $4.99 upgrade that gives you the ability to add together unlimited articles.

4. Audiobook Maker

(iOS)

Audiobook Maker was the only app of the iv to properly pronounce the words "alive" and "livestream" with the default voice setting. All the other apps pronounced the iv alphabetic character discussion "live" incorrectly for the context, as if it rhymed with "give." Audiobook Maker pronounced information technology correctly: "Alive" rhymes with "hive."

Audiobook Maker also was the only app with the choice to display one word at a time, centered in the screen. It also offered an option to highlight the discussion existence read, while showing the surrounding text, in an adjustable size font. As with other apps, y'all tin can adapt the speed, equally well as select from several voices and languages.

Audiobook Maker development is notwithstanding in procedure. For example, the app as well includes the ability to use your camera to take a photo of volume pages to be read. But when I took a photo of a page from a book, I saw a "less than a minute remaining" message that never left. To exist fair, the iOS app is named "Audiobook Maker – Early on Adopters." That said, the core functionality of text-to-oral communication works and the app is free (equally of July 2017).

Text to spoken language for developers

It'due south also never been easier to add text-to-speech communication capabilities to apps. Several large firms provide text-to-oral communication API services, such as Polly from Amazon, Bing Voice communication from Microsoft, and Text to Oral communication from IBM. In that location are smaller competitors in the field, like Responsive Voice, too. And search giants Google and Baidu have each released research papers that tout their progress toward increasingly natural sounding text-to-speech capabilities, chosen Deep WaveNet and Deep Vocalisation 2, respectively.

Do you utilise text-to-speech communication to mind to manufactures or documents? If so, what text-to-speech organisation and/or app do you use? And if you're a developer, have y'all integrated one of above API text-to-speech services into your app? If so, let me know which service and why — on Twitter (@awolber) or in the comments below.