 is now publicly available. Whether you’re a professional musician, a budding enthusiast, or someone who hasn’t picked up an instrument since middle school band, we’re excited to make music with you.

Two years ago, we set out to create a new way of making sound. It started with the silly idea of generating images and turning them into music. We didn’t know if it would go anywhere, and we didn’t really care if anyone used it. We were building it for ourselves. 

As musicians, we marveled at how generative AI could inspire and challenge us. 

A lot has changed since then, but that sense of wonder has remained. We still don’t know where this will go exactly, but we’re on the journey now. Today, we invite you to join us in building the future of music together.

 you can create and listen to music made with our latest foundation model, FUZZ. We see FUZZ as a new instrument that can create full-length, high quality songs from text, audio, and visual prompts. 

FUZZ is uniquely designed to help you find your personal sound. The more you use Riffusion, the more the model adapts to your unique taste and aesthetic. Just like learning an instrument as a child, we see Riffusion and personalization as a journey of self discovery. 

Access to instruments has long been a barrier for artists, at times reserved for only the wealthy or elite. We feel it’s important for everyone to be able to play this instrument, so we’re offering Riffusion for free to as many as we can in this early beta phase. RIP GPUs. 

Thank you to everyone who helped us get here, especially the trusted artist community of professional and amateur musicians who have been making music on our private beta. There’s a long journey ahead, and we’re excited to take this step with you.