Research engineer Hoon Shin built this liquid metal soundscape with our Audio Decision…
This is a dev post classified by AGK Intelligence as Backend & APIs (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Research engineer Hoon Shin built this liquid metal soundscape with our Audio Decision API. Using the model’s span feature, it picks out and identifies each sound, then renders it as an object morphing in and out of existence. Voices are read for age and language, while laughter and cheers are read for emotion and intensity, and the louder the room gets, the more the sea moves. Not a product, just a glimpse of what this model makes possible. When AI can actually hear, things get a lot more interesting.
Posted by Hume AI (23.7k followers) 2 h ago · 14 likes · 952 views · view the original post on X. Kept by the Dev Radar as Backend & APIs.
More dev work like this
- Build on your timeline. Modern Treasury brings your payments infrastructure together… — @ModernTreasury
- Today we're introducing Verda Inference, in preview, with day-0 access to Kimi K3.1 Pro,… — @verdacloud
- ✨ NEW: Multichain Transfers API — @Alchemy
- If you're new to building on Canton, here's three places to start: — @CantonFdn
- Your Ethereum deposits no longer need to wait 13 minutes. — @Quicknode
- When it comes to agents, businesses today have two options: allow them or block them. — @0xidanlevin
- Turn phone numbers into identity intelligence. — @telnyx
- Starkzap is the easiest way to go from zero to building with privacy on Starknet. — @Starknet
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.3k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-04 18:20 UTC. Full method.