According to Beating monitoring, audio AI company Noiz has completed a seed round financing of tens of millions of yuan, with the latest investor being GSR Ventures. Unlike most audio models, Noiz does not intend to continue competing in music generation, speech recognition, or TTS, but rather wants AI to understand the physical world behind sounds. For example, upon hearing a door close, the model does not just recognize that 'the door closed,' but also understands the material of the door, how much force was used, how far away the sound originated, and how the room's structure alters the sound. Noiz is specifically collecting data that includes spatial, material, distance, and directional information. What it ultimately aims to build is more like a 'sound-based world model': given the current environment and ongoing events, the model directly deduces what should be heard at that moment. In this way, audio models can go beyond dubbing and sound effect tools to enter real-time games, virtual worlds, and robotics, enabling machines to understand what is happening around them through sound.