Some people eat, sleep and chew gum, I do genealogy and write...

Friday, February 11, 2011

RootsTech -- Text to Audio and Voice Recognition? Not Yet?

Ann Roach, one of the prime movers and those responsible for the whole RootsTech experience, explores the potential of text to audio and voice recognition as it impacts the genealogical research process. I have written about these technologies recently and was interested to see if there is anything I've missed as a result of my "bad attitude." The title of her presentation was, "Letting Technology Work for You: Speech Recognition and Text-to-Audio Conversion." The keynote address by Curt Witcher went over time and everyone was rushing around trying to get to the first class of the day.

Brief summary of Ann's presentation:

Creating MP3 files out of text and drive down the road and still write a book. How do we find enough time to do all things we need to do in life? Text to Speech. She reviews NaturalSoft from Mentions OneNote, now available for Mac and moves quickly on from application to application, including Google Translate and several others including the PomeGranate Phone. (Look it up)

Note aside, I suggest you may wish to do a search on both text to speech and speech to text as well as voice recognition to get a real idea of the many applications available.

Continuing on with the presentation, on with speech recognition. Dragon Speech Recognition Software including the iPhone Dragon App. She emphasizes that you need to train the program carefully so it will work properly. Also uses the App for writing E-mails. On to the next App, Speak it. Most of these Apps are available for both iPhone and Android, perhaps with a slightly different name.

Maybe I will get the time to try some of these myself. Thanks to Ann for a great overview.


  1. They're still not ready for the average person. You must have perseverance and patience to get these things trained, and also to train yourself to speak in the way that is most effective for the software to understand you.

    Speech recognition is HARD, that's why it takes a human brain to do it well.

  2. Text to Audio works very well. 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. 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.

  3. If you want to create mp3 files of your text document then the best app is "Text Spekaer". I am using it for the same purpose. I can listen to audio file of my docs anywhere with this app. Tried many others but this is best. Works great.