Creating an audio blog reply using Festival

I listened to Dave Winer’s Coffee Notes for 24-Oct-2004 podcast on the way home tonight and felt compelled to reply to him with an audio reply email about Richard Scoble/Scooble’s voice mail. Here is how I created it.

* Get the Festival Speech Synthesis package for your Debian GNU/Linux box


$ sudo apt-get install festival

[...bunch of status about installing a festival and dependancies removed...]
$

* Create a snappy reply. I like emacs. This is exactly what hi-dave.txt looks like:

Hi Dave!

This is Marc No-zell and I just listened to your Coffee Talk with
Richard Scoble. It sounds like Microsoft’s voice mail system is using
a descendant of the DECK-talk system that was created by DECK in the
1980s.

I’m creating this audio reply using the Festival Speech Synthesis
System on my Deb-ian GNU Linux laptop. Neener, neener, neener!

Well, thanks for the Coffee Notes!

Now I did do a little cheating here. Festival follows strict pronunciation rules and sometimes gets words wrong. For example my surname would be said as ‘nozzel’, so I spell it how I want it to sound. The same is true for DECtalk and DEC, which sounds like ‘dec-tork’ and ‘december’ (trying to be a little too clever ;-)

* Convert from text to wave format:


$ text2wave hi-dave.txt -o hi-dave.wav

* Convert from wav to mp3 format


$ lame hi-dave.wav hi-dave.mp3

* Listen to the result:


$ xmms hi-dave.mp3

Tags: , , , , ,

9 Responses to “Creating an audio blog reply using Festival”

  1. Chris Pirillo Says:

    I think you mean “Robert Scoble.” ;)

  2. Marc Nozell Says:

    My bad!

  3. Scott Says:

    Just in case you ever get near a Mac OSX machine, do a ‘man say’ to see the man page on the built in ’say’ command. I think it’s derivative of the older Mac OS 9 speech synthesis engine and it’s pretty decent. It allows you to select voice, a file of text to be spoken (or a string in the command), and can output direct to the speaker or to an AIFF file. From there I guess you could mp3 it with any number of command line or GUI tools.

    I used to love using it to spook my daughter while she was playing one of her edutainment CD-ROM games. Just a quick ssh into the iMac followed by “say Abby you should go to bed now” at the remote unix shell really had her going. ;-)

    Podcasting … yet another reason for me to look into getting an iPod. But doesn’t Apple have enough of my $$ already? :-P

    Hope you caught the eclipse tonight (between watching the game innings…) I did some more hacking of my webnotes stats feature while waiting for the eclipse to hit its peak. My first major dabbling in a dynamically rendered page (all in python, no less).

  4. lah Says:

    Very cool. Hadn’t even crossed my mind to do something like this. So many possibilities with this festival tool. With the right scripts, you could setup a secret little obscure email address that you can email everytime you want to post an audio blog entry.

    For those who want to actually record their own voice, I once proposed that you can record a voice mail on your free SIPphone.com account and have it auto-forwarded to an email address where you can do what you please with the audio — e.g. have a script to automatically convert the wav file to mp3 and update to a blog.

  5. Daniele Says:

    I’m trying to use festival to save wav in italian language. The command “text2wave” has something to use “–language italian –tts”?

  6. lsi Says:

    it would be better with other languages support, but thanks..

  7. Oyunlar Says:

    link does not work (Coffee Notes for 24-Oct-2004).

  8. Rich Says:

    Other languages would be nice to have them in as well, I agree.

  9. kl Says:

    thank you!

Leave a Reply