Resources & Tools

Free and Open Source Text to Speech Tools for eLearning

Open source software can be used as we wish, without long-term commitments and with a community of professionals that extend and support them. This post is a post of the series “Free e-Learning Resources” and I am going to talk about free and open source text-to-speech tools for e-Learning.

We support Free eLearning! Do you?

I support Free eLearning

Before I present you the list I would like to answer two important questions:

1) Why not use Human voice over?
As a eLearning consultant I would prefer to use a human narration professional. However, you should consider the following factors:

  • It is more expensive
  • It needs more time
  • It is difficult to maintain the training
  • Few professional have the necessary skills
  • It is difficult to update the eLearning course
  • The pace is not steady
  • It is difficult to maintain your organizations’ identity

2) If I use text why I need to use voice?
For me it is unacceptable that eLearning organization create courses that they do not have voice. Come on guys are you serious! Are you familiar with the learning styles? How an auditory learner will succeed in your eLearning course? Some people will say that not all computers have speakers or that the voice is annoying. You are going to invest in your employees but you do not have money for headphones! Is it difficult to lower the volume or turn it off? Text and voice are extremely important factors to an eLearning course.

So, let see the list of the free and open source text-to-speech tools for e-Learning.

=> If you know a free or open source text-to-speech tool that is not included in the list I will highly appreciate if you write a comment with a link!

Free and Open Source Text to Speech Tools for e-Learning

The MBROLA Project
The aim of the MBROLA project, initiated by the TCTS Lab of the Faculté Polytechnique de Mons (Belgium), is to obtain a set of speech synthesizers for as many languages as possible, and provide them free for non-commercial applications.

The Festival Speech Synthesis System
Festival offers a general framework for building speech synthesis systems as well as including examples of various modules. As a whole it offers full text to speech through a number APIs: from shell level, though a Scheme command interpreter, as a C++ library, from Java, and an Emacs interface. Festival is multi-lingual (currently English (British and American), and Spanish) though English is the most advanced.

MARY is an open-source, multilingual Text-to-Speech Synthesis platform written in Java. It was originally developed as a collaborative project of DFKI’s Language Technology lab and the Institute of Phonetics at Saarland University and is now being maintained by DFKI. As of version 4.3, MARY TTS supports German, British and American English, Telugu, Turkish, and Russian; more languages are in preparation. MARY TTS comes with toolkits for quickly adding support for new languages and for building unit selection and HMM-based synthesis voices.

Free text to speech. Uses the world’s best text to speech (TTS) software. Upload documents, cut and paste text or link to feeds. Text reader converts text to speech automatically. Download audio and podcasts. It’s fast and easy to use. Get started right away! No software to download or install.

SpokenText lets you easily convert text in to speech. Record (English, French, Spanish or German) PDF, Word, plain text, PowerPoint files, and web pages, and convert them to speech automatically. Create .mp3 or .m4b (Audio Book) recordings (in English, French, Spanish and German) of any text content on your computer or mobile phone.

eSpeak uses a “formant synthesis” method. This allows many languages to be provided in a small size. The speech is clear, and can be used at high speeds, but is not as natural or smooth as larger synthesizers which are based on human speech recordings. Google has integrated eSpeak, an open source software speech synthesizer for English and other languages, in its online translation service Google Translate. The move allow users of Google Translate to hear translations spoken out loud (text-to-speech) by clicking the speaker icon beside some translations.

Praat is a free scientific software program for the analysis of speech in phonetics. It has been designed and continuously developed by Paul Boersma and David Weenink of the University of Amsterdam. It can run on a wide range of operating systems, including various Unix versions, Mac and Microsoft Windows (95, 98, NT4, ME, 2000, XP, Vista). The program also supports speech synthesis, including articulatory synthesis.

FreeTTS is a speech synthesis system written entirely in the JavaTM programming language. It is based upon Flite: a small run-time speech synthesis engine developed at Carnegie Mellon University. Flite is derived from the Festival Speech Synthesis System from the University of Edinburgh and the FestVox project from Carnegie Mellon University.

The Festvox project aims to make the building of new synthetic voices more systemic and better documented, making it possible for anyone to build a new voice.

Flite: a small, fast run time synthesis engine
Flite (festival-lite) is a small, fast run-time synthesis engine developed at CMU and primarily designed for small embedded machines and/or large servers. Flite is designed as an alternative synthesis engine to Festival for voices built using the FestVox suite of voice building tools.

The Epos Speech Synthesis System
Epos is a language independent rule-driven Text-to-Speech (TTS) system primarily designed to serve as a research tool. Epos is (or tries to be) independent of the language processed, linguistic description method, and computing environment.

by Christopher Pappas M.B.A., M.Ed. 

  • I'm involved with Vocabulary which has an interesting strategy for voice. In principle, we want every word, letter, and sentence spoken by a professional voice talent (at least professional calibre). Since we have a vocabulary of around 45K words and many words, have multiple meanings and sentence, this is a big investment we've made.

    BUT, we also let individuals write their own sentences and for these, we use synthetic voice. WE also use synthetic voice on sentences that we have just put up, or improved, until we can get the human voice recorded.

  • Hi BBat50,

    thank you for your info! Extremely interesting resource! It is not open source but it is free for teachers and parents.

    Have a wonderful day,
    Christopher Pappas

  • Adobe Captivate ships with Text-to-Voice software built in. Very handy. 🙂

  • Thanks for the info – this will come in handy.

  • Prodyot

    Very useful list.
    Thanks for posting it.

  • Subhendu

    I am developing robotics using openCV hand gesture recognition. I want to add the following into it , ie, when it recognizes the specific hand it will spell out what that means. This will put an end of communication barrier between the deaf and the normal people.
    Can this be done ?

  • dan

    I was looking for eSpeak, I wanted something compatible with microsoft “voice” in windows XP for use in ventrilo, I didn’t test all but it seems eSpeak is the only one, am I right or there is another one?

  • MIchael

    Great article Christopher,

    You have compiled a great list here! However, I have found that no matter what text-to-speech program I use, there are far too many oddities in pronunciation to efficiently and cost effectively use one for narration. Besides, finding a professional narrator is easy, and depending on who you choose, and it can be inexpensive as well.

    Check out The Narrator Files. They price narration by the page, and they have exemplary voice talent.



  • Warren
  • mahdi

    I need to match voice of my teacher with text in swf format .Do you know any software that help me?

  • Ben Kaufmann

    The current best text to speech software is Text Speaker. It has customizable pronunciation, reads anything on your screen, and it even has talking reminders. It is great for learning languages as it highlights the words as they are being read. The bundled voices are well priced and sound very human. Voices are available in English, French, Italian, Spanish, German, and more. Easily converts blogs, email, e-books, and more to MP3 or for listening instantly.

  • Thanks for sharing this!

    For fast, easy, reliable and high-quality translation of legal documents, try TranslateDay! TranslateDay translates legal documents from English to Spanish/French/German. Visit their site

  • Obi Nome

    Not very helpful at all…

    I would like a program to download for mac that JUST INSTALLS AND WORKS. None of this poorly programmed build packages and other irrelevant disjointed crap…

    If anyone is reading this wondering if there are any good text to speech programs that you can use offline for free that are easy to install for the average person who hasn’t been locked away for 5 years learning complicated computer science. THE ANSWER IS NO. NOT YET.

    Also all the websites that host the programs here look like they were made back in 1995 by teenagers…

    Where is the innovation?

    Though I thank the creator of efrontlearning for helping me come to my conclusions. 🙂

  • malorie grebetr

    If learning makes you bored you can use this online homework helper, affordable for all international students.

  • Thank you for the article. I’ve seen here something else that looks like –

  • Rajesh Kumar

    Aziksa is also a cloud based learning company with expertise of delivering blended virtual training to large enterprises. Our vision is to enable companies to deliver their training to customers, partners and employees at an optimized cost and quality. For more information and free trail you can reach out here

  • Thanks for sharing such useful information. keep posting and sharing these kind of information.