VoiceBankNOW is a 501c3 non-profit 100% volunteer organization, providing virtual voice education and resources with impartiality.
VBN is not affiliated, associated with or funded by any other company.
VBN mission
VoiceBankNOW is dedicated to empowering individuals who have or at risk of losing their natural voice, with the tools and knowledge to preserve their voice and maintain their ability to communicate.
​
This site provides a guide to help you navigate the growing options in the world of digitally recording voice, ie voice banking, synthesize or clone it, and use it in applications on a phone, tablet or computer. VBN does not provide these services, is not affiliated with, endorse, or sponsored by any companies that do provide these services. We strive to present unbiased information and feedback from the standpoint of users without natural voices, using technology for daily communication.​
Your voice matters.
Your voice tells a story of who you are, it is a unique fingerprint of identity. Tone, pitch, modulation, and even accent convey your personality and establish a sense of self. The hint of New Jersey may come out just in the word quarter, a tinge of Maine may still linger long after you have moved to Southern California. We don't realize just how much our voice is ourself till its gone. Connecting with others through voice is a vital part of the human experience.
​
Voice disorders impact functioning and quality of life. Aphonia (loss of voice) and dysphonia (voice disorders) have been linked to anxiety, depression, stress, loss of self-esteem and social isolation. ​
What is Voice Banking?
Voice Banking is digitally recording your natural voice for the purpose of creating a synthesized voice to be used in communication applications.
​
Synthesized Voice is an artificial production of human speech. Your recorded speech is used to create a voice that sounds much like your natural voice to be used by applications on a phone or computer with text or voice input.
​
Traditional voice banking/ voice synthesis companies record your voice dynamically online. Typically they will give you sentences to read in a simple guided process. You need a quiet place, a recording device (different companies recommend different mics), and your voice. Yes, you still need to HAVE your voice in order to bank it. A synthesized voice will be created, which can the be loaded into applications either on the a computer, dedicated AAC (augmentative alternative communication) computer, or a phone app. One advantage of these systems is you do not have to be online, connected to internet, to use them.
​
Voice Cloning, or ai voice cloning, is a technology that uses artifical intelligence to create a synthetic voice that is virtually identical to your natural voice. They have a much more natural intonation, cadence and ability to show expression, that traditional voice synthesis does not.
​
In order to create a cloned voice you will need to have banked (recorded) a high quality digital recording of your voice with a minimum of 2 minutes material, preferably 3+ hours. The recording needs to be only your voice with as little background noise as possible.
Currently, the applications to generate speech using a Cloned Voice are primarily designed for use in voice dubbing, entertainment, gaming, etc. They are great for producing a pre-recorded speech. However, the applications to use these for on demand communication, ie everyday talking, are not fully developed...YET. In addition, these systems all require you to be connected to the internet and there tends to be a bit more lag time between typing and the generated speech. It doesn't sound like a big deal, but when you are trying to keep up with conversation by natural voicers that awkward pause can be cumbersome and break flow.
Virtual Voicing is the use of a synthesized voice to speak.