Submission by Mila

History is preserved in text—but its sound is lost. Chronoscapes reconstructs historical audio scenes by turning archival documents into music and soundscapes grounded in real evidence. Given an era, event, or location, it retrieves context-rich, sound-relevant passages—news reports, eyewitness accounts, and cultural fragments—using Turbopuffer for fast semantic search across large-scale archives. A sample of the 340GB American Stories collection, comprising millions of digitized historical documents, was used to ground the system in authentic historical material. Chronoscapes then analyzes this content to extract latent sonic signals such as mood, tempo, instrumentation, and environmental texture. These signals are structured and transformed into immersive audio using ElevenLabs, generating both period-appropriate music and environmental sound. For deeper immersion, Chrono Radio turns any historical theme into a continuous broadcast: a living station where AI-voiced DJs introduce each track with context drawn from the archive, weaving music and narration into an unbroken journey through time. A query like “letters home from soldiers in the 1940s and the radio swing music that kept them going” becomes an hour of era-faithful sound, paced and hosted as if heard on the original airwaves. Instead of imagining the past, Chronoscapes makes it audible—bridging archival data and generative audio to bring history back to life.