Shop Mobile More Submit  Join Login


Submitted on
January 4, 2010
Image Size
448 KB


61,799 (4 today)
105 (who?)
This is a Flash animation containing some audio files generated by:

Link: GLaDOS Voice Generator

The motivation: I've read some tutorials around the web on how to generate such GLaDOS-y sound files, and they're perfect, save one thing: sound files have to be created manually (using a text-to-speech software or recording from microphone, then applying effects). That's perfect for mapmaking, but what I would really love to have is a direct GLaDOS text-to-speech tool that I could use for stuff like reading my news, telling me how many emails I have in the morning, reading their subject lines, etc. So, of course, it would be pretty pointless to create these sounds by hand...
So I've dropped the idea for a while (that was somewhere mid-2008). But every few month, I'd stumble upon a random Portal-related video on YouTube for some reason... and I'd inevitably hear GLaDOS's voice again, and the idea would come back to me.
This happened again 2 days ago, and this time I swore to myself I'd just do the damn thing. I happened to have set up a server with a graphical environment a few months ago, which would allow me to run graphical applications (I'm looking at you, Melodyne), so all I needed to do was to automate the text synthesizing part (easy), then importing that file into Melodyne (easy), and then creating a script that would know where to click or what button to press to apply the effects needed to get the GLaDOS effect I want (much harder). But I gave it a shot, and while it is painfully slow (the server is running Linux, so it has to run Melodyne through Wine, and its processor isn't exactly a beast either), so it can take up to 5 minutes for one message to be synthesized. That is fast enough for my needs alone, but now what if I wanted to let others profit from my work? That's what I told myself yesterday, so I coded up a little queuing web-based front-end for the thingy. It queues up messages and slowly processes them on a first-come-first-serve basis. And today, it's complete!

Description: This tool lets you type in some text, and the server will generate a GLaDOS-like reading of the text.
Who/what is GLaDOS? The main antagonist in Portal, a video game by Valve. See the Wikipedia article on GLaDOS for more information.

About GLaDOS's voice: GLaDOS was voiced by Ellen McLain, a professional voice actress. This tool is automated, thus cannot rely on professional voice acting; instead, it uses text-to-speech synthesis to generate a female voice, then distorts it to make it more GLaDOS-like. This process is quite long and obviously produces results of poorer quality than the voice you hear in Portal; do not expect Portal perfection.

The technique: There are various tutorials around the web on how to do this. There's also a video tutorial here.
The problem is that this method makes use of GUI (graphical user interface) software, which cannot be easily automated. What this tool does is, indeed, to automate them anyway, despite the shortcomings of such a method. Here is what happens when you enter a message in the form above:
  • The message gets queued in a database.
  • The queue is processed at regular interval through a script ran with a cron job.
  • Once the message arrives in front of the queue, the server generates the initial voice sound file using Festival with the nitech_us_slt_arctic_hts voice.
  • The server is running Linux, so it has to run an X server and launch Melodyne through Wine.
  • A Python script takes care of opening the file in Melodyne and to apply the method described in the tutorial, using shortcut keys when possible, or by taking screenshots to determine where to click on screen when there is no shortcut key to perform a certain action.
  • The Python script then exports the file as a 44,100 kHz 16-bit linear PCM .wav file
  • The cron job script picks up the file and sends a link to it by email to the recipient.
  • Done. The server moves on to the next message, if any.

Portal and GLaDOS are property of Valve.
Add a Comment:
oldmonk1 Featured By Owner Jul 17, 2012
Phase two complete. Now moving subject Q-527 to Phase three of testing.
WindyPower Featured By Owner Jul 19, 2012
> continue testing
Neko-Noskire Featured By Owner Apr 25, 2012
that is awesome now we just need a sensual human sounding one for the evil glados mental breakdown
jakanddaxterfan51 Featured By Owner Mar 20, 2012
i know how to make a better one. submit me the sayings and ill do it
AlexSamuels Featured By Owner Jan 11, 2012
You sir, are amazing!
WindyPower Featured By Owner Jan 11, 2012
makosanders Featured By Owner Oct 8, 2011  Hobbyist Interface Designer
So it was you who made that generator that resembled an email phishing scam =J
I suppose I can try it in confidence now.
But I needn't, knowing what's going on behind it t_t

If you ever do implement this in a way that is more.. respectable, please tell me. I need an efficient, pleasant voice synth to make a sense augmentation. An aural HUD, so to speak.

Nothing in the repos is as tolerable is this, good sir.

It sounds like you've dipped your toes in the waters of aural augmentation already?
WindyPower Featured By Owner Oct 8, 2011
I uh... don't really know what you're talking about o_O

It is not an email phishing scam, as you do not need to enter your email. If you do, you'll get notified when it's done, if you don't, then you won't.

What do you mean "a more respectable way"? Or "sense augmentation"/"aural augmentation"? And what repos? >:
Daz3626 Featured By Owner Aug 5, 2011
Any voices that GPS and other things have are made from sound files anyway. Maybe you could create them in GLaDOS' voice and swap the files around.
WindyPower Featured By Owner Aug 20, 2011
Indeed, one guy asked me if he could use it for that, and he did
Add a Comment: