Bring your unique characters to life with custom AI voices

Request access

Try our hyper-realistic voices

Zeena Qureshi

CEO & Co-founder

July 30, 2021

Break free from familiar voices 

If you watched a movie trailer released in the 1980s, 1990s, or early 2000s, chances are you know the voices of Don LaFontaine and Hal Douglas. Even if their names aren’t instantly recognisable, their voices would probably be very familiar. These two A-list voice actors recorded thousands of film trailers as well as TV commercials and video games. 

Game, animation, and film studios know that using the same actors for multiple projects can offer consistency and a level of familiarity that audiences enjoy. But if you want your new digital assistant or the characters in your new game to sound truly unique, you might want to break free from using familiar voices.

Sonantic offers custom voice models that let you craft completely new voices for your project. By using custom models, you can construct voices for new characters, experiment with those voices throughout your project, and differentiate your end products from those of your competitors.

Building custom voices

We have a collaborative, end-to-end process in place for producing custom voices. “Everything we’ve learned from developing our hyper-realistic stock voices is applied to a custom model,” says Sonantic’s CTO and Co-Founder John Flynn. 

Before developing a new model, we work with each client to understand their specific vision for a new voice. We want to capture as many desired vocal attributes as possible, including the emotional range, pitch, and other characteristics. Our proprietary Voice Engine accounts for all of these nuances, allowing our team to match any voice, accent, and/or delivery style.

Before starting the modelling process, we first receive consent from the actor to synthesise their voice. Then we onboard the actor to our Voice Engine. The actor has the ability to train their own AI to match their own performance skills. Our team can direct the actor and continuously monitor the quality of performances to guarantee the best results. The Voice Engine then makes several models automatically, enabling researchers to choose the right representation of the voice for the project.

If the custom voice actor isn’t available or cannot record data for any reason, our team can also create a voice from pre-existing recordings of the actor’s voice. For us, the more data you can provide, the better.

If there is limited acting data available, we can apply more advanced techniques to create a model. “One of our recent custom projects involved a well-known person who had lost their voice, so the data was very limited,” says Flynn. “We're really proud of how realistic and natural the resulting AI voice was. It was very true to the recordings. Needless to say, the client was super happy."

Maximising creativity and differentiation

Custom AI voices from Sonantic free you to experiment with vocal performances throughout extended pre-production and production processes. As your team adds characters, modifies dialogue, or otherwise fine-tunes the script, you want to hear how those changes will sound in your final work. Using our custom AI voice capabilities allows you to continue to experiment throughout the project—all while hearing the precise voice you have in mind.

If you plan to use AI voices in your final product, our custom models let you move beyond familiar-sounding voices to differentiate your product. You can produce the exact voice you want and deliver high-quality performance in an instant. Your game, animation, film, or digital assistant will have a voice that does not sound like any other.

Experience custom voices firsthand

Our clients are continually discovering new ways to benefit from custom models. In our next blog posts, we’ll take you behind the scenes to show you how we produced a custom voice for a very high-profile actor. We’ll explain how the resulting model offered creative options for a particular project while opening new possibilities for the actor.

Ready to hear one of our custom voice models firsthand? Contact us to explore custom voices we’ve already created and start envisioning how you want your new voice to sound.

→ Return to blog

Heading

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.

  • It prevents you to directly style elements of a RT when this RT is bound to the CMS. I hope this limitation will be removed soon, but in the meantime the workaround is pretty easy to handle. Proceed as follow:
  • CMS. I hope this limitation will be removed soon, but in the meantime the workaroun
  • Vents you to directly style elements of a RT when this RT is bound to the CMS. I hope this limitation will be removed soon, but in the meantime the wor