Speech-to-Text: Dictation software for OS X
- Speech-to-Text: Dictation software for OS X
- “Text to Speech” or “Speech to Text”?
- Voice Commander
- MacSpeech Dictate is highly recommended
- MacSpeech Dictate 1.2 Upgrade Released
- MacSpeech Dictate Instructional Videos
This article is a significantly updated version of the article “Speech-to-Text: Dictation software for OS X“, originally published in November 2007.
Speech-to-text software, sometimes known as dictation software, is something that lets you talk to the computer in some form and have the computer react appropriately to what you are saying. This is totally different to text-to-speech software that can read out text already in the computer, although the two are often confused.
There are two types of speech-to-text software available. One type is called “command and control” and it lets you speak commands to your computer to control it - for example a command that it understands might be, “go to the Apple website” or, “tell me the time”, but you can only speak things the computer is already set up to understand; you can’t use this software to write an email or use iChat.
Command and control software for the Mac - known as “Speakable Items” (or sometimes, confusingly, “spoken commands”) - is already built into every OS X computer, although most people don’t know about it. So you don’t need to download, buy, or install anything to get this software to work. You would probably need a good USB microphone though, and if you don’t have American-accented English then the computer probably won’t understand you very well. Some resources for getting you up and running with Speakable Items include:
- MacWorld Article about Speakable Safari Bookmarks and other aspects of OS X Speakable Items
- Apple Support Articles about Speakable Items
The other type of speech-to-text software is usually called “dictation” software. This is the type that lets you write an article like this one, type stuff to your friends in iChat, or type an email. There used to be a version of IBM’s ViaVoice for OS X but it hasn’t been updated for several years and is no longer available. There is only one dictation-capable speech-to-text software available for OS X which is being updated and developed and it’s MacSpeech Dictate. Dictate is the successor to a program named iListen which MacSpeech used to produce.
Like all dictation-capable text-to-speech products, MacSpeech Dictate works very well for some people and very badly for others. Whether it will work for you depends on many things including: how much effort you’re willing to put into learning it, how good your microphone is, your age (text to speech usually works less well for children), how much your accent matches what the program expects, and whether your voice changes a lot through the day. MacSpeech Dictate is also very new software - it was only released on the 15th of February, 2008 - and like most new software it’s missing some major features. Ones which will be of significance to users with a disability include:
- No way to control the mouse by voice
- Can’t be taught new words, such as names or jargon specific to your profession
- Correction it doesn’t yet learn from being corrected
MacSpeech have announced that correction and spelling features are currently in private beta testing and will be released in a free upgrade as version 1.2 as soon as possible.
I tried using the old iListen a few years ago and could not get results that were useful, an on-screen keyboard was the best solution at the time. Although MacSpeech Dictate is in its infancy as a program, its recognition of my particular voice is hugely better than iListen’s was. This is not surprising though, as MacSpeech Dictate’s speech recognition engine is based on the same engine used by Windows’ Dragon NaturallySpeaking - widely recognised as the best consumer speech recognition available.
MacSpeech Dictate requires the Tiger or Leopard operating system and a compter with an Intel chipset. It’s currently available for English dialects only - US English, US Teen English, UK English, Australian English, Indian English (as in India, not Native American), South-East Asian English.
- Ricky Buchanan, ATMac
I am an old rascal (pilot WW II). I am in pretty good shape for my age, with one exception, I am profoundly deaf. What I need to communicate is something like an ipod with speech to text. I’m sure there are may people with the same problem. The problem is social isolation which lowers the quality of life.
HELP!
@Alan: Unfortunately, the technology isn’t good enough for what you need yet. The iPods can’t do speech to text and even if you carried a laptop around it’s speech to text functions have to be trained for a specific person’s voice, and that person has to speak very clearly and carefully for the speech to text to work. So the sucky thing is that the computers just aren’t smart enough for you yet
I’m not sure there’s anything technology wise that can help you with chatting with a random person. I can’t think of anything that would really be better than a pencil and paper and getting people to write stuff down for you.
I’m at Accessing Higher Ground and heard of a nice device called the Ubi Duo (demo at Grant Laird, Jr’s Blog).
It looks pretty cool!