Automator: Create a Narration/Podcast Track Application

With the addition of the new, high-quality voices in Mac OS X Lion, an idea on how to best implement these new features jumped into my head – why not use Automator to create custom, high-quality narrations?  For those of us who don’t feature a rich, enticing set of pipes to create entrancing and inviting narratives, this is a great, free alternative.

I’ve been a fairly avid user of Automator for awhile, and its ability to create a self-running, customized Application is a perfect example of an easy-to-develop efficiency booster.  Please read this previous post for other examples.  Here’s the workflow I came up with:

Before heading to Automator, be sure to visit the System Preferences < Speech < Text to Speech pane.  Select the default system voice and head to Customize…

[singlepic id=14 w=320 h=240 float=center]     [singlepic id=16 w=320 h=240 float=center]

Check off the Voices that strike your fancy and then advance.  Keep in mind that (1) foreign language voices actually speak in that foreign language and therefore require foreign text for input (stick with English dialects, if you only sport the American dialect, as I do) and (2) the voices are between 400mb-500mb apiece, so I wouldn’t go crazy with checkmarks all at once.

Step 1: Open Automator and use the “Application” template.

[singlepic id=12 w=320 h=240 float=center]

Step 2: Add the “Get Specified Text” action from the Text Library.  Choose “Options” and ensure the “Show this action when the workflow runs” is checked.

[singlepic id=15 w=320 h=240 float=center]

Step 3: Add the “Text to Audio File” action from the Text Library.  Again, choose Choose “Options” and ensure the “Show this action when the workflow runs” is checked.

[singlepic id=17 w=320 h=240 float=center]

Step 4: Head to File < Save and name your Application appropriately, saving in your Applications folder.

[singlepic id=13 w=320 h=240 float=center]

Step 5: Run your App!  It will ask you for text input, which you can either type or paste in and then it will ask you what system voice to use and where to save the subsequent AIFF audio file.

Pretty slick, huh?  You can visit this previous post for a couple of audio examples, including Australian Lee and Indian Sangeeta reading the first part of the Declaration of Independence.

[nggallery id=4]