UltraVoice is developing an artificial intelligence (AI) speech device called the UltraVoice Max AI or the Max AI for short. In the Max AI artificial intelligence is applied to the UltraVoice, the electrolarynx, the TEP or to esophageal speech to improve the sound quality of the voice and make it more natural and generally more understandable. AI can be used to analyze the user’s voice and create a personalized sound profile. This can help to reduce the metallic or robotic sound that is often associated with speech devices.
In the not too distant future, the Max AI could be used to analyze the user’s voice and create a personalized sound profile This would be helpful in recreating the speaker’s original voice before surgery if voice samples are available. If you anticipate surgery, record about 10 minutes of natural conversational speech for use in the Max AI. If you have had surgery already, save any voice recordings you may have as they will be useful later.
We have provided some speech samples below that show some of the Max AI capabilities. It should be noted that this product is still in development and significant improvements are expected when the product is actually available toward the end of 2023. People getting the UltraVoice Plus between June 1, 2023 and the Max AI launch date can expect to get a free upgrade when the Max AI is on the market. Don’t wait. Get the advantages of an UltraVoice Plus now and get upgraded to the UltraVoice Max AI when it becomes available soon.
Listen to the voice samples below of laryngectomees speaking followed by a simulation of how they would be expected to sound with the Max AI. Carl Andrews using an UltraVoice Plus (current product) saying, “Hello. This is Carl Andrews. You have reached the office of UltraVoice. We make the UltraVoice Plus. I am using the UltraVoice Plus now. Have a nice day.” Max AI capabilities.
Recording of Carl using the UltraVoice Plus
Simulation of Carl’s voice using Max AI
Recording of male electrolarynx user
Male electrolarynx user saying, “His salary had reached the ten thousand mark”
Simulation of male electrolarynx user with Max AI
Recording of female TEP speaker
Female TEP speaker saying, “The best I can figure is that I’m somewhere around fifty second or fifty third most popular this year.”
Simulation of female TEP speaker