Skip to main content
  1. Home
  2. Emerging Tech
  3. News

Project Soli isn’t in wearables yet, but these guys used it to create invisible violin

Add as a preferred source on Google

Playing the world’s tiniest violin used to be a way to dismiss over-sensitive whiners, but now, thanks to the good folks over at cutting edge design studio [Design I/O], it’s the description of an awesome DIY project that allows would-be musicians to create a violin sound simply by rubbing their fingers together.

The project uses Google Soli, the search giant’s purpose-built interaction sensor that uses radar for motion tracking of the human hand. While Google is using it for proper grownup applications like objection recognition and next-gen wearables, however, [Design I/O]’s project offers something a bit more musical.

IMG_0157
Image used with permission by copyright holder

In order to do this, it also relies on Wekinator, a free machine learning tool used to train and detect the violin gestures, as well as open source C++ toolkit openFrameworks for communicating with the Soli and playing the sweet, sweet music. Once all of these pieces are put together, what results is a device capable of working out whether or not a violin gesture is being made and playing back a violin sample accordingly.

Recommended Videos

“This is, I believe, the first time someone has made the small violin gesture actually play music,” [Design I/O] partner Theodore Watson tells Digital Trends. “When we first saw the Soli demo last year, the gestures used in the demo reminded us so much of the smallest violin joke that we thought we would try it out if we ever got hold of a dev kit.”

Watson says he would describe the tiny violin as more of a “speed project” than the somewhat more serious interactive projects he normally works on. But he says that he and his [Design I/O] collaborators, “thought it would be a fun and accessible way for people to understand what types of things are possible with this incredibly innovative technology.”

It’s hard to disagree with that logic — particularly when the end result is as cool as this!

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Virgin Galactic is charging $750,000 for three minutes of weightlessness, and nearly 700 people are already in the queue
Three minutes of floating, one very expensive ticket.
Virgin Galactic featured image

I’ll be honest with you. Three minutes of weightlessness for the price of a very nice house sounds absurd to me. Even so, hundreds of people have already lined up to experience it.

Most recently, Virgin Galactic unveiled Apeiron, the first spaceplane in its new Delta class. The company flew it from its Arizona factory to Spaceport America in New Mexico, where it will begin flight testing.

Read more
Google is making Gemini and Search work better with the apps you love
Gemini's guest list is growing, and your favorite apps are invited.
Gemini AI on a phone.

Google has been finding more ways to make Gemini a part of your daily routine, from putting together playlists to ordering groceries through your favorite apps. Now it's expanding those capabilities to more services, with Google Search joining in, too.

The company has announced a new Connected Apps Platform that makes it easier for developers to bring their services to both Gemini and Search. Alongside this, Google is adding new partners to its growing lineup, bringing more of the apps people already use into its AI ecosystem.

Read more
AI bots are now trying to sabotage public health policies, like banning disposable vapes
Thousands of AI bots voted in a public health poll to block sales restriction on disposable vapes. It's like Big Tobacco is back from the dead.
Woman smoking a vape.

In the broad context of AI and its perceived harms, health and medical risks often pop up in the conversation. The warnings even come from frontier AI labs, such as ChatGPT-maker OpenAI and Anthropic, both of which have warned about misusing AI to cook up bioweapons. Security experts have already spotted a few such incidents in the wild, especially with the usage of AI models without any solid guardrails. 

Well, it appears that the risks run deeper. As per an analysis appearing in the British Medical Journal (BMJ), AI bots are now being deployed to influence public policies governing health risks to citizens. In this instance, an attempt was made using AI bots to thwart regulations that aim to restrict the sale of disposable vapes, all while disguising the manipulation efforts as a response from real humans. 

Read more