This option is for people who are at risk of losing the ability to speak due to medical conditions and who need to bank their voice for use in a communication device. Here’s what you will need to do:

  1. Register with us to create a secure account.
  2. Choose the recording method you want to use: MTVR (Windows only) or our web-based recording tool.
    • If using MTVR, install it, go through the tutorial, and get set up to record.
    • If using the web recorder, follow our interactive online training.
  3. Record 10 test sentences, upload them to our server, and wait for an email from us.
    • If everything is fine, we will provide instructions for moving on to step 4.
    • If we see any problems, we can suggest ways to fix them and may ask you to repeat step 3.
  4. Record one of our voice banking inventories and any custom material you want to add.
    NOTE: As our technology has improved over the years, the amount of recording needed has significantly decreased and our instructions for how to speak when recording have changed as well. Our latest “Gen3” inventory consists of about 300 sentences that are designed to elicit more expressive speech that we can model with our new generative AI technology. We could easily create very realistic personal voices with fewer than half that number of recordings, but with the 300 sentences we are able to capture more of each individual’s expressive speech qualities. We also continue to provide a standard voice-banking inventory of over 3000 sentences intended more for creating older-style concatenative speech voices and the ability for clients to record custom sentences of their own design, e.g., for message banking. Specifically, your inventory options are:

    • Gen3 — We recommend this inventory of ~300 sentences designed to prompt you for examples of expressive speech. If you want a Gen3 voice, this is all you need.
    • Standard — over 3000 sentences suitable for building a first generation voice based on unit selection synthesis. At least 250 of these sentences would have to be recorded to make a voice using the Gen3 technology, but it would lack the expressiveness of voices built from our Gen3 inventory.
    • Custom — 10 example sentences plus as many additional custom sentences as you’d like. These can be used both to build your personal synthetic voice (typically along with recordings from another inventory), or as messages to play back.
  5. Audition several versions of your voice to select one to purchase.
  6. Pay for and download your voice to your computer, mobile device, or speech generating device.

If you are ready to have us walk you through the steps, let’s