LatentScore Heads to SIGGRAPH 2026 in LA

LatentScore got a talk at SIGGRAPH 2026 in Los Angeles, July 19-23. The session walks through the retrieval architecture and where it fits for procedural audio in games, film, and interactive media. Read the research post or try the demo.

Most procedural audio tools either play canned samples or wait for a beefy GPU to spin up a diffusion model. LatentScore does neither. Text in, structured synth configurations out, runs on a laptop CPU. The synthesizer is the renderer; the LLM-distilled retrieval is what gives it a sense of taste.

I think the pipeline transfers well outside of music too - any time you need responsive, content-aware audio at scale and a sample library is too rigid to be useful.

If you’ll be in LA and want to chat, reach out on LinkedIn. There’s also a companion short paper at NIME 2026 in London in June if that’s closer.