AI startup Stability AI has released Stable Audio Open Small, a “stereo” audio-generating AI model that the company claims is the fastest on the market — and efficient enough to run on smartphones.

Stable Audio Open Small is the fruit of a collaboration between Stability AI and Arm, the chipmaker that produces many of the processors inside tablets, phones, and other mobile devices. While a number of AI-powered apps can generate audio, like Suno and Udio, most rely on cloud processing, meaning that they can’t be used offline.

Stability also claims that Stable Audio Open Small’s training set is made up entirely of songs from the royalty-free audio libraries Free Music Archive and Freesound. That’s as opposed to the training sets of the aforementioned Suno and Udio, which reportedly contain copyrighted content, posing an IP risk.

Stable Audio Open Small is 341 million parameters in size and optimized to run on Arm CPUs. (Parameters, sometimes referred to as weights, are the internal components of a model that guide its behavior.) Designed for quickly generating short audio samples and sound effects (e.g., drum and instrument riffs), Stable Audio Open Small can produce up to 11 seconds of audio on a smartphone in less than 8 seconds, claims Stability AI.

Here’s a sample generated by Stable Audio Open Small:

And here’s another one:

The model isn’t without its limitations. Stable Audio Open Small only supports prompts written in English, and Stability notes in its documentation that the model can’t generate realistic vocals or high-quality songs. The model also doesn’t perform equally well across musical styles, Stability warns — a consequence of its Western-biased training data.

In another potential wrinkle for devs, Stable Audio Open Small has somewhat restrictive usage terms. It’s free to use for researchers, hobbyists, and businesses with less than $1 million in annual revenue, but developers and organizations making over $1 million in revenue have to pay for Stability’s enterprise license.

Stability, the beleaguered firm behind the popular image generation model Stable Diffusion, raised new cash last year as investors, including Eric Schmidt and Napster founder Sean Parker, sought to turn the business around. Emad Mostaque, Stability’s co-founder and ex-CEO, reportedly mismanaged Stability into financial ruin, leading staff to resign, a partnership with Canva to fall through, and investors to grow concerned about the company’s prospects.

In the last few months, Stability has hired a new CEO, appointed Titanic director James Cameron to its board of directors, and released several new image generation models.

We’re excited to announce a big surprise for the AI community — TechCrunch Sessions: AI is getting a limited-time discount to broaden the number of people who can attend and learn from some of the brightest minds in the industry.

For just $292, you can get a general admission ticket — plus a 50% discount on a second — to attend our flagship AI-centric event at UC Berkeley’s Zellerbach Hall on June 5. We’re looking for everyone from those working in the industry to founders, academics, AI die-hards, and beyond to get the chance to learn from and engage with a full day of programming, including:

• The two winners of our competitive Audience Choice competition: Cohere’s Yann Stoneman on using generative AI in privacy-driven companies, and the Global Innovation Forum’s Hua Wang on moving swiftly while maintaining compliance.

And that’s on top of our consistent focus on networking opportunities, with attendees getting the chance to set up 1:1 sessions, meet with peers and potential partners, and start the relationships that lead to big deals down the road.

When the event itself is done, you’ll also get the chance to keep the momentum rolling with side events hosted by partners across Berkeley, California, including Tanka, Toyota, and MyHomie. Just because our event is done doesn’t mean your perks for getting a ticket should, after all.

Remember, this pricing is a limited-time offer, so act now and head here to reserve your slot at one of the most exciting events within the AI space this year!

Meta said on Tuesday its Ray-Ban Meta smart glasses would be available for sale in India starting May 19 at a starting price of ₹29,990 (about $353).

The smart glasses are currently available for pre-order on Ray-Ban’s site, and will be stocked in Ray-Ban stores at launch.

Meta said the smart glasses launching in India will support Meta AI, which can answer questions about what’s in front of you, translate both audio and video live, send messages via your phone, make calls for you, and more.

The smart glasses currently support live translation for English, French, Italian and Spanish even when users are offline. Notably, Meta hasn’t added support for Indian languages yet.

Meta has said it would enable the glasses to connect and play music through apps like Spotify, Amazon Music, Shazam and Apple Music in India.

The company has so far sold around 2 million pairs of the glasses since they launched in 2023.