"Text to Speech" or "Speech to Text"?

There are a lot of searches that find this blog using the phrases "speech to text" and "text to speech" or equivalents using words like "voice", "speaking", "typing", and so on. It seems from the logs, that a lot of people aren't sure what the difference is between "speech to text" and "text to speech" so I thought I'd clarify.

"Text to speech" is where the computer speaks. The computer can speak anything and it's still text to speech - it could speak what you're typing, announce the time to you, speak some pre-typed words from a file, read a book to you, let you navigate the computer with the VoiceOver screen reader, anything you can imagine.

"Speech to text" is where the person speaks and (hopefully) the computer can understand the speech. The [msd] program is the only program currently that understands speech well enough to do this.

Another variation of the computer "understanding" speech is called "Command and control" software. With this type, you can only tell the computer certain pre-defined commands like "open Safari", "page down", "check for email", and so on. It can't be used to dictate words to go in your email messages, for example. It can be useful if typing is difficult or slow for you as it can replace some of the typing, but it won't replace all of it.

- Ricky Buchanan

[msddisclaim]

[msdbanner]