«
»

Flite – a small text to speech for embedded systems

Last time I wrote about Festival: Text to Speech on Linux. Now I found a derived version of them, it called Flite. Flite (festival-lite) is a small, fast run-time synthesis engine developed at CMU and primarily designed for small embedded machines and/or large servers. Flite is designed as an alternative synthesis engine to Festival for voices built using the FestVox suite of voice building tools. To enable it on Ubuntu (8.04), you just type:

sudo apt-get install flite

and then everything will be ready for you. To test it just type:

flite -t "Hello world"

and this will speak the sentence in quotation. If you want to generate the sound from file, use this command:

flite -f filename.txt

It’s a nice text to speech engine. I think I will try to port to an embedded device for the future project.

Related Posts

This entry was posted on Monday, October 13th, 2008 at 8:52 pm and is filed under Linux, Robotics and AI, Software. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.

2 Responses to “Flite – a small text to speech for embedded systems”

  1. Tom Hamelinckx on August 28th, 2009 at 1:52 am

    For those who want to port Flite to an embedded system: I can only encourage you.

    Due to the highly adaptable package, I was able to port the TTS-engine to an ARM7-processor, running the eCos embedded operating system.

    It struggled at first but after handling the ARM-to-thumb call-errors in the compiler, it turned out to run quite fast. (It was not the only thing running in the OS). We ran it completely in RAM and had only 4MB of that. Keeping in mind that the audio-samples were stored in the system: it proved to be very compact.

    Thanks to the developers at Carnegie Mellon University it still keeps getting more compact!

    I can only applaud this promising TTS-engine!

  2. This is very encouraging Tom. We want to use Flite with our chatbot (see http://www.worldsbestchatbot.com ) on an embedded system.

    Did you use an 8KHz voice or 16KHz?

    And how was the speech quality?

Leave a Reply