Get Access to Cutting-Edge Voice AI For Your Perfect Synthetic Voice Persona

Custom text-to-speech voice offers an exciting new option for brands that are looking for a signature sound to communicate faster and more efficiently.

Download One-Pager

What is a Custom Text-to-Speech Voice and How Can I Use It?

Custom text-to-speech (a.k.a. synthetic voice) technology has made significant advances and
offers a flexible, one-of-a-kind voice that can be applied to:

Telephone IVR Systems
Google Home, Amazon Alexa
Voice-First Technologies

How Are Custom Text-to-Speech Voices Created?

Your custom synthetic voice, also known as text-to-speech voices are created in three easy steps:

Human Voice Recordings
The voice actor you have selected creates recordings, which will form the foundation of your custom text-to-speech voice.
Algorithm Training
Your human voice recordings are then used to train speech processing synthesis algorithms.
Custom Voice Engine Complete
With your custom voice engine, you can type any script and turn it into audio that sounds like the original voice talent.

Get Access to the World’s Top Voice Actors

Get Started Free

Voices is trusted by the world’s most prominent brands


Find Your Perfect Custom Text-to-Speech Voice Actor at Voices

At Voices, the number of project types that we can help you complete are nearly endless.
Our text-to-speech clients rely on us for all their voice over requirements.

How Voices works

Learn how Voices makes finding professional voice actors faster and easier than anyone else.

Voices’s SurePay™ service offers a proven, safe and sound way to pay

As an animation studio, each and every critical dollar put through your business helps you to create magic. Voices’s SurePay™ service keeps those funds secure, but offering a credible, safe, risk-free way to pay for the talent you hire.

Our voting feature enables teams of all sizes to work together

We know your animation studio has countless stakeholders, all who have a unique creative spin. Voices makes it easy to take everyone’s opinion into consideration. Our voting feature enables studios of all sizes to work together, even when you’re not in the same room.

Top Voice Actor Qualities

Here are the top 5 vocal qualities (known as ‘styles’) for text-to-speech projects that we recommend clients source
from Voices in order to achieve an engaging read, no matter the topic. Select a style to listen to voice actors.

What Content is Best Suited for Synthetic Voice?

Content that needs to be adaptable and is not necessarily predictable – You want to have a brand consistent experience for listeners whether they are listening to the recordings of the voice actor or synthesized sentences produced in his/her voice likeness.
Urgent content – when delays can impact businesses or lives, custom synthetic voices gets those alerts out fast without having to wait for a voice talent to be hired, record the script, and then send in the finished file.
High volume of content – when a project has thousands of lines of script.

You don’t have to make the choice to use all synthetic voice or all human voice.

In fact, these using both together is often an ideal solution. For example, you may want to have predictable content such as a to be read by a human actor and rely on his/her synthetic voice for unpredictable, frequently changing content for brand consistency.

Project Considerations for Creating Custom Text-to-Speech

Human voice talent need to record audio and consent to using their recordings to build a synthetic voice:

Creating a synthetic voice requires a human voice actor to record approximately 2-3 hours of speech. These recordings are then used to build the synthetic voice engine.

Human voice talent agree to the licensing terms of their synthetic voice:

Just as you set the terms of use for any recorded audio for business use, you will need to agree with the voice talent on the use of his/her synthetic voice double.

Create Your Brand’s Perfect Custom Synthetic Voice Persona

Learn how we can work together

Contact Us

Frequently Asked Questions

A synthetic voice is an artificially produced version of human speech.
Artificial intelligence or AI voice is a type of synthetic voice that uses ‘deep learning’, which is a type of artificial intelligence, to turn text into audible human-sounding speech.

You can produce a synthetic voice by first creating an account or signing-in to your account. You can then reach out to your Account Manager about the custom text-to-speech project you are interested in exploring. You’ll find your Account Manager’s contact information on the ‘My Home’ screen, immediately after logging into your account. Once contacted, your dedicated Account Manager will be in touch shortly to discuss the project with you in more detail.

Once your project is discussed with your account manager, then voice talent will be sourced for the job, based on the qualities you want the voice to convey. Once you and your voice talent agree to terms, production of your synthetic voice will commence. From actor selection to synthetic voice creation, the whole process can be completed in as little as two weeks after the voice actor completes the recording.

Currently, we are focused on English, including accents and dialects from around the world.
The usage rights of the project are something that can be negotiated with the voice talent. There is an annual subscription license fee associated with usage.

If you have more questions about the use of synthetic voices or customizing your text-to-speech voice, contact us today.