←
Stability AI905 posts
Stability AI avatar

Stability AI

@StabilityAI

We’ll help you make it like nobody’s business. Multimodal media generation and editing tools to get your idea to production. Self-deploy? 👍 Need a partner? 🤝

◷ Joined July 2020▧ 330 Photos and videos
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Nov 13

What does a painting sound like? And the one hanging next to it? Team Generative Gallery imagined an art gallery where every artwork has its own sound. Using Stable Audio 3.0, they built a prototype that generates music for each piece, and the music that connects them.

2:06
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Nov 12

There's a lot that's new in Stable Audio 🤘a new workspace to bring your projects together, two new apps for creating music and samples, and updates to our multitrack creation experience. Read our November Release Notes to learn more 👉 stability.ai/guides/whats-ne…

Post attachment
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Nov 4

You finally get the perfect snare. Ask for more punch, and it’s gone. Sculptro by Javor Vatchkov lets producers keep shaping a sample with Stable Audio 3.0, changing only what isn’t working. 3rd place at the @MusicHackspace ADE Lab Hackathon 🥉

2:10
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Nov 2

48 hours, one idea, one win. Meet Team Generative Gallery, winners of the ADE Lab Hackathon Stable Audio challenge. 🏆

1:04
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Oct 30

Our CEO @premakkaraju sat down for a chat with Roland’s @mccabep on building trust in AI tools for music creation, and our SVP of GTM @AnaGuillen joined @ElevenLabs' Bridget Ferris and Royall’s Anne Kavanagh to discuss how technology can grow the economic opportunity for music.

Post attachmentPost attachment
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Oct 30

That’s a wrap on @MusicTectonics! The Stable Audio team spent two days in Santa Monica showing how you can create with our tools, meeting people from across the industry, and joining the conversation on where AI and music go next.

Post attachment
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Oct 23

The best way to make AI work for you? Build with it. Meet Team Vision-studio at the @ADE_NL Lab Hackathon.

1:05
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Oct 23

Rapid fire with the ADE Lab hackers. Which side are you on? 👇

0:54
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Oct 22

24 hours in. The ADE Lab hackers gave us a quick look inside the projects they’re building on Stable Audio 3.0. 24 hours left. Let’s see what they come up with next.

2:07
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Oct 21

48 hours. One room in Amsterdam. Musicians, developers, and sound obsessives building on, breaking, and remixing Stable Audio 3.0. The Official ADE Lab Hackathon with @MusicHackspace starts now.

1:12
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Oct 15

We’re back with @MusicHackspace, and this time we’re in Amsterdam for @ADE_NL. We’re handing you Stable Audio 3.0 and seeing what you do with it. The challenge is simple. Build a tool other producers can use. Get started with Stable Audio 👉 bit.ly/4jZGGT2

Post attachment
Stable Audio avatar
⟳ Stability AI retweeted
Stable Audio@stableaudio·Oct 9

That melody stuck in your head deserves better than your voice memos folder. 🎙️ Dylan Ho, Gilberto Tumangday, and Le-Tao Li built a studio agent that turns a hum into the foundation of your session, powered by Stable Audio 3.0. Watch how it works 👇

1:36
Stability AI avatar
Stability AI@StabilityAI·Oct 8

What if making video-based world models smaller isn't just about better compression, but about making their representations easier to predict? Recent approaches to video generation explore building scenes from coarse to fine. The first few tokens capture the big picture, like a person playing a guitar, while later tokens progressively add visual details. Our Interactive Research team just published SemanTok, which takes this idea further. By making those early tokens more semantically meaningful, we give the model a clearer understanding of what's happening in a scene, making the representation easier to predict and video generation more efficient. The result: a model using SemanTok matches or beats the performance of a model more than three times its size. Read the full paper: stability.ai/research/semant…

0:09