Text-to-speech

 

3D Outside the Box includes a text-to-speech synthesizer that speaks text that's typed into it. You can use it to generate speech for your animations.

Here are some sample wave-files generated by the text-to-speech engine: (Technical information: The TTS voice is produced from my own voice. I have recorded 4000 sentences, and haven't done any hand-correcting of the units.)

Comparison of voice quality using different voice-file sizes

Transplanted prosody quality

When you create a voice file from your recordings you can specify how large a voice file to create.

 

This shows a comparison of different levels of synthesized prosody, including the original wave from which the prosody came. (The TTS voice and the original recording have the same voice because they're both recorded by me. Unless you create your own TTS voice, your transplanted prosody voice will be different than the original recording.)

 

Modified voice

Other voices

These voices are easy-to-control modifications of the original voice.
  • Low male (change formants and pitch) - play (47kb)
  • Female (change formants and pitch) - play (54kb)
  • Whisper (transfer voiced energy to unvoiced) - play (60kb)
  • Strange (non-integer harmonics) - play (47kb)
  • Foreign (change phonems) - play (48kb)
Here are voices created from the CMU Blizzard challenge databases.
  • Female 1 - play (70kb)
  • Female 2 - play (70kb)

 

The text-to-speech engine in 3DOB differs from other text-to-speech engines on the market because it supports:

 

To use text-to-speech, you need to:

  1. Download 3DOB from here and install it.

  2. Download and install the large text-to-speech voices from here. The voices will (normally) be installed into "c:\program files\mXac\mXac Interactive Fiction".

  3. Run the wave editor provided in 3DOB.

  4. Under the "FX" menu, select "Text-to-speech" followed by "Text-to-Speech".

  5. In the "Text-to-speech" dialog, press the "Load in a different text-to-speech" voice and select one the installed voices.

  6. Type the text you want spoken and press the "Do text-to-speech" button.

  7. It will fill the wave with the synthesized voice; press "Play" to hear it.

  8. You can experiment with transplanted prosody using the "Transplanted prosody" menu under "FX".

  9. If you wish to create your own text-to-speech voice, run the "mXac Natural Language Editor" installed with 3DOB.

 

Other text-to-speech voices and lexicons

At the moment I don't have any other text-to-speech voices or lexicons, but if you happen to create one, E-mail me your web page so I can add the link here.