TTS

TTS is an acronym for Text To Speech which is a voice synthesizing technology used to read electronic text and produced voice output. Also known as "Read Aloud." The opposite direction would be called Dictation.

Overview

TTS creates sound by interpreting electronic text and then synthesizing the voice. There are several different techniques used to create the voice. In most cases the voice has a distinctly computer like sound but some of the newer technologies support very human like voices. TTS can be accomplished by software or hardware.

Synthesized speech can be created by concatenating pieces of recorded speech that are stored in a database. Systems differ in the size of the stored speech units; a system that stores phones or diphones provides the largest output range, but may lack clarity. Systems are not mutually exclusive. For example a diphone system may have a list of keywords that are often mispronounced. When a word in this list is encountered a recorded word is substituted.

Alternatively, a synthesizer can incorporate a model of the vocal tract and other human voice characteristics to create a completely "synthetic" voice output. This provides a human voice that sounds similar to the person used for the vocal tracts.

The Microsoft Speech API (SAPI 5.1) speech engine has a robotic voice by default but can be augmented with the addition of human voices. This is the primary engine used on Windows systems. Speech processors for Windows include: Microsoft Narrator, JAWS and NVDA.

Voices

To avoid the computer sounding voice you will need to obtain a specific voice implementation that sounds like a human voice. These are available from

• AT&T Natural Voices
• NeoSpeech
• Acapela
• Real Speak - from Nuance
• IVONA

These are available in many languages.

There is also "Eloquence" - very efficient synthesized speech also from Nuance.

eBook Reader support

Current eBook Readers that include TTS support are:

• Microsoft Reader
• Adobe Reader
• yRead for Windows - see yRead
• IVONA Reader for Windows - A mini reader is available for free.
• eCub is a conversion tool with TTS support.
• Amazon Kindle 2 - Version 2 and later
• Hanlin V5, Hanlin V3plus - some vendor versions but not all.
• Boox i62 and others from Onyx that have sound available.
• PocketBook Color Lux

Android Speech engines

(source http://hyperionics.com/TtsSetup/eng/TtsInfo.html)

• Google TTS - Install first, if not present on your device. Free, now pre-installed on most devices or available for download from Google Play. Medium quality, unless using network speech generation.
• Vocalizer - TTS Good quality voices, free app, voices for purchase, but offers a one week free trial of available voices. Currently @Voice app author's favorite.
• Acapela Free app, voices for purchase. Good quality.
• CereProc - TTS Good quality voices available from Google Play.
• SVOX - Classic Free app, voices for purchase. Good quality.
• eSpeak - Free Very bad, "robotic" voice, but can speak very fast if you learn to understand it. Over 40 languages.
• Hear2Read - Provides free Indic TTS voices (Kannada, Telugu, Punjabi, Tamil, Gujarati, Marathi, Sanskrit, maybe more in the future)
• Eloquence TTS - For purchase. Robotic sound, but valued for some people because it can speak very fast. 10 languages included with a single purchase.
• SpeechLab - (Bulgarian language only, for purchase) SpeechLab 2.0 is a high quality Bulgarian Text-to-Speech engine developed by the Bulgarian Association for Computational Linguistics.
• Aharon - Hebrew TTS Free demo Hebrew TTS voice, actual product for purchase.
• Samsung TTS - Comes only pre-installed with Samsung devices. Medium to good quality.

iOS TTS

There are some apps but the built in one is great. Here is how to Enable Text to Speech in iOS

1. Launch “Settings” and tap on “General”
2. Scroll down to “Accessibility” and tap on “Speak Selection”
3. Slide the Speak Selection toggle to “ON”
4. Optionally, adjust the “Speaking Rate” slider to an appropriate setting

To use tap and hold on some text to bring up the menu or ask Siri.

Unix Speech engines

For variants of Unix including Linux

• Flite - A small, fast speech synthesis engine
• Festival - A good, but slow speech synthesizer. Festival Speech Synthesis System Copyright © University of Edinburgh, 1996,1997. All rights reserved.
• MBROLA - Mbrola related speech synthesizers (English, French, Spanish, German)
  • TTS tools multiple languages
  • Mbrola Binary and Databases

For more information

• http://www.bookcourier.com/ - text to speech hardware.
• http://www.nextup.com/ - text to speech software that works with Word, PDF, and HTML files. They also have plugins for browsers.
• DTBook is the standardized format for books that are to be read via TTS.
• SSML - A W3 standard for a synthesized markup language.
• Audio books - for other voice choices.
• http://en.wikipedia.org/wiki/Speech_synthesis
• http://www.textaloud.com
• DRM for a discussion on eBooks that are disabled from TTS engines.
• eSpeak - A free opensource TTS engine
• https://freetts.sourceforge.io/docs/index.php A free speech synthesizer (called freeTTS) written in Java.
• CSS aural Reference- This is the CSS entries specific to TTS.