Latest news: Announcing our partnership with the University of Oregon
SoapBox
Play
Taking play seriously
Complex menus, clunky controllers, and confusing interactions. When it comes to entertainment, today’s kids have much higher expectations.
They’re looking for natural, immediate, and immersive play experiences that are also safe and private. With SoapBox’s voice engine, you can fulfill all of their expectations.
Our proprietary, privacy-first speech recognition tech powers voice-driven experiences for kids of all ages and accents across a diverse set of use cases. Integrate our off-the-shelf API to power command and control in gameplay, keyword spotting, moderation filters, search, and menus.
And when you need a custom approach for transcriptions, we can build custom models for you too.
Why add voice?

Gaming
Increases accessibility and reduces friction
Manages privacy and safety
Offers cross-platform scalability —console, mobile, XR

Media
Delivers interactive conversational storytelling
Promotes longer engagement between kids and their favorite characters
Scalable across media, from TVs to theme parks

Smart toys
Offers interactivity and friction-free, magical play experiences
Increases accessibility for younger children
Can be delivered as privacy-first experiences, offline or embedded
Use cases
Control
Up, down, left, right! Up, down, left, jump! Our voice engine offers robust keyword spotting for gameplay dialogue and voice commands, increasing ease of use and reducing friction. No customization required. Works for all words and phrases.
Search
Our Search feature increases accessibility for younger (e.g. early literacy) age groups and those with lower dexterity and typing proficiency. No customization required. Works for all words and phrases.
Conversations
With our voice engine you can allow kids to use their voices to interact with AI bots as well as with their favorite digital characters and companions.
Custom wakewords
Our Wakeword feature, built specifically for kids’ voices and behaviors, allows kids to activate dormant devices using custom words or phrases.
Voice activity detection (VAD)
With VAD, our voice engine reduces friction and increases privacy by automatically detecting when a child intends to engage or begins to speak, and opens the microphone to listen at that point only.
Features

Accurate
Human-level accuracy, down to the individual phonemes.

Flexible & customizable
Many use cases available off-the-shelf. Partner with us for bespoke solutions.

Easy integration
Lightweight and low-code API, integrates within hours.

Online / offline / embedded
Choose a delivery option tailored to your use case.
Voice is the natural interface; everything else is just a hack.
Dr. Patricia Scanlon, Founder & Executive Chair, SoapBox Labs

Partnering on Play
Looking for a trusted and world-class partner to help bring your voice-enabled entertainment solutions to life?
Enter SoapBox Studio, offering expertise and support across all areas from privacy and safety to conversational UX design, pilots, implementation, and scaling.
Frequently asked questions
What role will voice play in the metaverse?
With the metaverse, the future of human-computer action will evolve to become more natural and frictionless, with less reliance on a mouse, control pad, keyboard, or other physical input devices.
This inevitably means voice will become the default way that humans interact with technology. The first adopters will naturally be children, and we can already see kids today growing up as “metaverse natives” in the same way as Millennials and Gen Z have grown up as digital natives. Children are at ease inhabiting these multi-faceted, play/social/experience-based platforms and embracing and adopting new technologies.
It’s critical that kids be provided with the tools to maximize these experiences and ensure that they can do so safely and in an age-appropriate way. Speech recognition software for children can provide a range of critical services and will ultimately be a core part of the infrastructure of the metaverse.
To learn how SoapBox’s voice technology can be used in your immersive gaming or entertainment experience, please fill in the form on our Get Started page and we’ll be in touch to schedule a call.
What kinds of toys and games are best suited to voice-powered experiences?
Any toy or game that would be enhanced for kids by transforming it from a passive into an interactive and immersive experience is well suited for voice. Through the creative reviews undertaken by SoapBox Studio, we work with you to assess the value of adding voice to each product in your portfolio and develop a roadmap of “now”, “next”, and “later” opportunities.
What is interactive TV and what role does voice play in it?
When you add voice to TV shows, they are transformed into interactive experiences kids will love. With interactive TV, kids get the opportunity to drive their adventure, choosing the beginning, middle, and ending. They can unfold a new story — and potentially learn new things — every time they watch. Here’s an example of an interactive TV experience powered by SoapBox’s voice engine.
Tell me more about voice and AR games.
Voice-enabled gaming and AR experiences free up kids’ hands — and minds — for more immersive and frictionless adventure experiences. Voice-controlled gaming is particularly compelling for kids with low dexterity or who can’t easily type on a keyboard.
With voice, kids no longer need to manage controllers, work through menus, or press a myriad of buttons to drive their 3D characters. They can immerse themselves in the AR, using voice commands to drive their experience.
Can SoapBox power voice-enabled physical toys?
Yes we can and do! Voice-enabled entertainment experiences don’t always have to be connected to the cloud. Powered by an embedded chip, physical toys and robots can finally engage in conversations with their kid owners. They can respond to wake commands, follow voice controls, and have natural conversations with the kids who own and love them.
Have another use case for voice? Tell us about it on our Get Started page, and we’ll be in touch to schedule a call.