What is Voice Banking?
Voice banking is a way to preserve your voice using technology. It works by recording samples of your speech – usually between 150 and 300 phrases – which are then used to create a personalised synthetic voice that sounds like you.
This isn’t the generic, robotic text-to-speech voice you might associate with communication devices. It’s your voice. Your accent, your vocal characteristics, the way you sound. If your speech becomes difficult or impossible due to a progressive condition, this synthetic voice can be used on a tablet, phone, or dedicated communication device to help you communicate.
Every time you type a message, it’s spoken in your voice.
Why It Matters for Progressive Neurological Conditions
Certain conditions can gradually affect speech over time. Motor neurone disease, Parkinson’s disease, multiple sclerosis, and Huntington’s disease are some of the more common examples. For many people living with these conditions, speech changes aren’t immediate, but they can progress.
Thinking about losing your voice when you’ve just been diagnosed can feel overwhelming. It’s confronting. You might not be ready to consider it yet, and that’s completely understandable.
But voice banking isn’t about accepting that your voice will change. It’s about preserving options. Think of it as vocal insurance. You record it now, and it sits there. You only use it if you need to. And if you never need it, that’s fine too.
What voice banking does offer is the ability to maintain your identity. Your voice is a huge part of who you are. It’s how your family recognises you, how you express emotion, how you connect with the people around you. Voice banking means that even if your natural speech changes, you can still sound like yourself.
Timing Makes a Difference (But There’s Flexibility)
Voice banking works best when your speech is still clear and consistent. That’s because the quality of your recording directly affects the quality of your synthetic voice. If your speech is recorded before any significant changes occur, the result will sound more natural, more like the voice you’ve always had.
The earlier you record, the better the outcome. But that doesn’t mean you need to rush into it if you’re not ready. Processing a diagnosis takes time, and it’s okay to need space before making decisions about things like this.
The key thing to understand is that once speech clarity begins to decline, the recording quality can be affected. That doesn’t mean voice banking becomes impossible – there are services designed to work with speech that’s already changed, and alternatives like message banking that can still capture your natural voice in specific phrases. But the window for creating the highest-quality synthetic voice is while your speech is still largely unaffected.
You don’t have to do this today. But it’s worth knowing about sooner rather than later so you can make an informed choice when you’re ready.
What the Process Actually Involves
Voice banking isn’t as complicated as it might sound. Most people complete it in one session, or over the course of a week if they prefer to break it up.
You’ll be asked to read a set of predetermined phrases – usually between 150 and 300, depending on which service you use. These phrases are designed to capture the full range of sounds in your speech. The recording typically takes between one and two hours.
You’ll need a few things: a computer or laptop, a USB headset microphone (this ensures good sound quality), and a quiet room. Background noise affects the recording, so somewhere with soft furnishings and minimal echo works best. Your speech pathologist will guide you through the process and make sure the recordings are clear and consistent.
Once the phrases are recorded, they’re uploaded into a voice banking service such as Acapela, SpeakUnique, ElevenLabs or Apple Personal Voice, where they’re processed into your synthetic voice. The voice stays there until you’re ready to use it. You don’t need to pay for most services until you actually need to download and use the voice.
What to Expect from Your Synthetic Voice
It’s important to have realistic expectations. A synthetic voice won’t be an exact replica of your natural voice. It’s a close approximation. It will preserve your accent, your general vocal sound, and many of your vocal nuances, but it won’t capture every subtlety of human speech.
That said, modern voice banking technology has come a long way. The synthetic voice can respond to punctuation and formatting in your typed messages. If you use an exclamation point or type in all caps, the tone lifts. You can still convey emphasis and emotion, just in a different way.
It’s also worth noting that most people don’t particularly like the sound of their own voice when they hear it played back – think about listening to your voicemail greeting. A synthetic voice might feel a bit strange at first, but to the people who know you, it will still sound unmistakably like you.
Taking the First Step
If you’re considering voice banking, the first step is a conversation with a speech pathologist. They can talk you through the process, answer your questions, and help you decide if and when it’s right for you.
It’s okay to need time to process this information. It’s okay to not be ready yet. Voice banking doesn’t mean you’re giving up on your natural speech. It’s about keeping your options open and maintaining control over how you communicate in the future.
Your voice is part of your identity. It’s how you maintain relationships, stay connected to your community, and preserve your independence and quality of life. Whether that’s continuing to volunteer, staying active in social settings, or simply being able to communicate with the people you care about in a way that feels like you – voice banking can help make that possible.
When you’re ready to explore it, we’re here to support you.
