A Guide To ModelTalker Voice Banking

ModelTalker is an engine for creating voices from recordings of a patient’s natural voice. The result is a synthesized voice similar to what the person might sound like if he or she weren’t limited by speech disorders. One of the great benefits of ModelTalker is that the synthetic voices created are virtually unlimited and can be used in the ModelTalker Text-to-Speech system to express words and phrases that have not been previously recorded by the user.

The prospect of banking your voice may seem daunting, but the process is simple.

The steps are simple:

• Register with ModelTalker and create a login or password.
• Either download the ModelTalker program on your PC or Laptop or use the Web version.
• Using a USB microphone, make sure your voice quality and sound is clear.
• Record the 10 sentences given by ModelTalker until you receive the green light.
• After receiving your initial recording, ModelTalker with then ask you to record about 1600 sentences. This will take about five to eight hours and can be done in multiple sessions.
• ModelTalker then develops your own personal synthesized voice.
• Finally, you will be sent a link to download your file and you will be able to download this on to Predictable or ChatAble through iTunes (wired connection) or directly on to the app (internet required).

ModelTalker has wowed users with MND and ALS

Jerry Bowen and Peter Pierce are Predictable users with ALS and MND, respectively, who are reaping the benefits of creating their ModelTalker voice.

Jerry Bowen was recently diagnosed with ALS. Luckily for Jerry, his daughter, a speech pathologist, was well aware of the steps to take and encouraged Jerry to be proactive. Jerry’s first action was to turn to technology and, after being identified as an ideal candidate by another speech pathologist, banked his voice with ModelTalker. Jerry was quick to follow this up by downloading Predictable so he can use his Voice wherever, whenever.

Peter, former DJ and BBC Golf sound man, now living with MND, is a Predictable user. He had banked a ModelTalker voice in 2009 when he recognized his voice would soon deteriorate. Fearing that Peter would have a “Stephen Hawking type, robot synthesized voice,” he quickly entered the process of creating a ModelTalker voice while he still had time. Peter was delighted when he found that ModelTalker would be integrated in to Predictable 4.0. Although Peter is still able to use his voice, to describe Predictable, Peter identified the app as “liberating”.