Voice banking is the process which allows individuals, who are at a risk of losing their voice due to an illness such as ALS or Motor Neurone Disease, to preserve and create a digital version of their voice. They can complete this process by recording a set of phrases which the voice banking technology converts into a personalised synthetic voice.
This voice can then be added onto a speech-generating communication device which allows individuals to ‘speak’ in a voice that sounds similar to their natural voice.
With recent advancements in Artificial Intelligence (AI) and deep learning technologies, it’s much quicker and easier to create a personalised digital voice than people might think and in this blog we are going to show you how.
1. What to consider when choosing a voice banking provider?
Traditionally, voice banking is seen as a lengthy process as it requires a lot of time and money. Individuals are often asked to record 500-1500 sentences in order to create a new voice. Additionally, some solutions require external software, a good USB microphone headset and various other testing. There are also huge differences in cost options which can vary from £100 to £5000. As you can see, there is a huge list of things to consider and it can be a daunting process so it’s not a surprise that it causes a lot of stress and worry!
We wanted to create a solution that would take the pain away from voice banking by making it faster and more accessible for everyone. We also wanted to make it so easy that people could just grab their phone and start creating a new voice immediately.
As a result, we created a free iOS voice banking app which allows individuals to create a personalised digital voice without the need to download any additional software, invest in a USB microphone headset or waste time on testing. We also introduced a milestone-based technology which allows people to record as little or as much as they want. This allows them to manage this process by breaking it into smaller steps. Individuals can start with as little as 30-100 sentences and gradually build it up. The more they record, the better their new voice will sound. If individuals don’t feel comfortable with recording on their phone, they can also record on a computer or a tablet. In this case, it is recommended to use a USB microphone headset.
2. How long will it take me to create a new digital voice?
An individual’s voice is very unique and personal so it depends on how healthy their voice is. For example, if people decide to bank their voice soon after their diagnosis while their voice is still healthy, it will most likely take them a shorter amount of time. Whereas people who have already lost some of their voice might need more time to record shorter phrases. It also depends on the provider and the solution they offer.
On average, with The Voice Keeper, this process takes about 10 minutes of recording per day for 2 to 4 days. Our milestone-based technology allows people to break the process into smaller steps and which often takes away the pressure associated with recording too much at the same time. Once individuals are happy with their voice, they can either purchase their voice or save it and purchase it when they are ready to use it.
3. What should I do when I’m happy with the voice I have created?
Once an individual is happy with the voice they have created, most solutions have a one-time payment which allows them to download their new voice on to their communication device. With The Voice Keeper for example, this amount is $299 (£245) for a Windows SAPI version, compatible with all major communication software, or a significantly lower amount of $75 (£60) to keep their new digital voice on The Voice Keeper app and use the app as a text-based communication aid.