VocaTone Studio gives a voice to the world

Kenosha-based tech startup VocaTone Studio was among the most talked about startups at this year’s Early Stage Symposium. The company won over the audience while competing in the Elevator Pitch Olympics at the event, capturing the coveted People’s Choice Award for its presentation of an AI-based audio tool the founders have been working on for more than 10 years.

The tool itself is technically complicated, but the concept behind it is not.

VocaTone Studio has created a novel piece of technology that allows musicians and other content creators to access an electronic vocalist. First, the user selects the type of vocalist desired, everything from an operatic voice to a heavy metal vocal style are available. Then the user enters the words the electronic vocalists will sing. With just a few keystrokes, human vocals pour from the computer speakers exactly as the creator imagined it. All at a fraction of the cost of hiring human talent.

Utilizing AI technology, the company has created a program that has an expansive vocabulary. When new audio files are uploaded into the program, each of the voice databases “learn” inflection and vocabulary from the new audio file. The company has collected the voices of over 300,000 vocalists in its ever-expanding database.  

Right now, the tool can sing fluently in over 70 languages, and that number is growing rapidly.

While many startups developing cutting edge technology are new organizations, the voice technology engineers behind VocaTone Studio have been collaborating with each other for more than a decade. Company founders Gregory Grissom, Natalia Shmueli, Diana Outlaw, and KK Jenkins met each other online in a vocal synthesis chat room while in high school and have been creating innovative technology together ever since.

Largely self-taught, the teens began experimenting with vocal technology freeware at a time when their peers were just discovering Minecraft. In 2011, the friend group’s online activity caught the attention of an audio company and before long the teenagers began creating products for the company. The team specialized in Vocaloid technology, a vocal synthesis engine.

During this time, the team created the Vocaloid character named Oliver. Despite existing only in the online world, Oliver has a fanbase, a line of merchandise and has even starred in the animated Netflix series, Bee and PuppyCat.

VocaTone Studio, the latest project from the group, was launched in 2021 and has been certified as a Qualified New Business Venture by the Wisconsin Economic Development Corporation. This work fills the need in the industry for vocal tools that use languages other than English.

According to Forbes, there are an estimated 50 million digital content creators worldwide. Studies suggest that just 17% of the world’s population speaks English, which leaves many creators without the option to use the current wave of vocal synthesis software. VocaTone Studio aims to change that.

The applications for VocaTone Studio voice technology appears to be endless. From enhancements to current speech recognition software, to the use of vocal instruments across media platforms, music education and even as a tool to preserve dying languages, the technology provides solutions to gaps in current voice synthesis technologies.

The young company is currently investigating opportunities in a number of startup accelerators and exploring options with early-stage startup investors.

To connect with VocaTone Studio, click here.