Text-to-Speech Tools & Resources

A quick guide to some free Text-to-Speech solutions for the Microsoft Windows platform, Apple Mac and various podcasting applications.
New TTS and speech recognition technologies are constantly being developed to enhance the latest operating systems, search engines and audio services. Quite often the end user is unaware of the existence of these technologies seemingly buried deep within the operating system. There are however many programs and services that utilize these systems, several of which are mentioned here. All of these resources are free to download or use online, supported by links to free eBooks and speech technology resources including related Microsoft blogs, spoken audio search engines and a brief history of speech synthesis.
Desktop Applications & Podcast Tools
A free, open source Windows program that creates MP3 audio files from RSS feeds. It can be used to create audio versions of text-only blogs. Simply drag an RSS feed link onto the inteface to convert RSS to MP3. It can also be run from the command line for faster processing in the background. AutoCast uses LAME and relies on the Microsoft Speech SDK. See Wikipedia Autocast for a definition of autocasting.
A free desktop application for Microsoft Windows using Microsoft Agent animated characters. You can select any text in any application and press Ctrl+C to have it read by a talking character. You can also have regular time announcements and additional characters can be downloaded as they become available.
An online application that instantly turns your blog’s RSS feed into a Podcast. Here’s the spoken feed for DISS: http://www.feed2podcast.com/podcast/42180750.xml
Click on the following link below to hear it played using the Big Contact Audio Feed Player
A small Windows program that translates text RSS Feeds into spoken MP3 files.
Another small Windows application that will load a plain text (TXT) or HTML file and read it out loud using human speech.
Free eBooks
Complete text works you can download for free including books and dictionaries.
Pprovides full text of public domain books.
The open-access text archive where all collections are free to use.
Has a library of 17000 free ebooks whose copyright has expired in the USA.
Also has a selection of free ebooks to download. 
Speech Technology Resources
The following sites provide further information about TTS and speech recognition systems. The selection of demos below show the variety of products available including their level of sophistication and realism. 
Acapela HQ TTS Interactive Demo choose male or female voices in a selection of languages.
AT&T Labs Text-To-Speech online demo speaks your text.
AT&T Natural Voices Demo another online text input interface.
Cepstral Voices Demo cross platform TTS software.
KAE Labs VocalWriter MP3 Demos Page of software that can sing lyrics.
Loquendo TTS Demo very realistic with emotional/physical effects.
MBROLA Project provides a collection of voice synthesis audio samples.
Nuance RealSpeak™ Demo select from Telecom or Solo modes, also very realistic.
Oddcast TTS Demo an example of animated character driven communications. An earlier version circa 2003
can be found here. Other uses for Oddcast technology can be found via their Homepage and on the Persuadatron.
Yamaha Vocaloid Audio Demos a vocal-synthesizing software that enables song writers to generate authentic-sounding singing on their PCs by simply typing in the lyrics and music notes of their compositions.
Books2Burn translates text files into a series of audio files (Apple AIFF format) which can then be converted to mp3’s or other formats using programs like LAME or iTunes. Open source software that works on Panther and later only.
Explains several creative (and free) ways to use speech synthesizers. Also provides links to music related speech synthesis resources.
Microsoft Blogs
Focuses on TTS developments, language and technology.
Provides a quick overview of people who blog on speech and natural language technology at Microsoft.
Software Development
FreeTTS 1.2 – A speech synthesizer written entirely in the JavaTM programming language.
Related Posts
A search engine that lets you search inside the audio of podcasts by using speech recognition technology to convert speech into text.
Uses speech synthesis technology to read the results of your search. You can choose between a female voice and either of two male voices. A drop down box allows you to select from just the title information to a more information dense summery including the URL, title and description. The search results are provided by Google.
Explores the history and development of speech synthesis including original audio demonstrations, early voice synthesis techniques used in music and film productions, BBC’s Doctor Who and the Daleks, recent software developments.
Thanks to Blake Handler for the tips and Windows Vista samples of "Anna" in his post: FREE Microsoft Text-to-Speech Software & "How to". His Space The Road to Know Where provides lots of useful information about Microsoft products and services.

Technorati Tags: , , , , , , , , , , ,

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s