Reportedly: Xiaomi open-sources MiDashengLM-Spatial, an end-to-end spatial audio understanding large model
Reported by IT Home and Pandaily · not yet confirmed by the company or a second independent outlet. We update this page when it is.
Xiaomi released MiDashengLM-Spatial, an open-source end-to-end spatial audio understanding large model, with weights and inference code under Apache 2.0. It builds on MiDashengLM-7B and adds spatial perception and reasoning. The model will be applied in Xiaomi smart home and car cockpit scenarios, IT Home reported.
China context
- Original name
- 小米
- Outside China
- Open weights · ithome.com
- Claims
- Company-reported; not yet independently evaluated
- For builders
- Developers can access the model weights and code under Apache 2.0, enabling integration into spatial audio applications without licensing fees.
- For investors
- Xiaomi's open-source spatial audio model may accelerate adoption of spatial audio in consumer devices, potentially affecting companies in smart home and automotive audio.
Translated from Chinese. Quotes and facts link to the original sources.
Xiaomi announced MiDashengLM-Spatial, described as the industry's first open-source end-to-end spatial audio understanding large model. It retains basic audio understanding while adding spatial perception and reasoning, moving from 'understanding sound' to 'understanding the space where sound is located'. The model is based on MiDashengLM-7B and will be gradually applied to Xiaomi smart home and car cockpit scenarios to improve interaction in the 'Human x Car x Home' ecosystem.
MiDashengLM-Spatial extends MiDashengLM-7B with spatial audio capabilities, enabling perception of sound direction and spatial distribution. The release includes model weights and inference code under Apache 2.0. Test data images are referenced but not detailed in the text.
Developers outside China gain access to an open-source spatial audio model that can be integrated into smart home and automotive applications, potentially reducing the cost of building spatial audio features. Xiaomi's move puts pressure on other audio AI providers to match open-weight spatial capabilities.
For Xiaomi, the model strengthens its 'Human x Car x Home' ecosystem by enabling more natural spatial audio interactions. For external developers, the Apache 2.0 license allows commercial use and modification, lowering barriers to entry for spatial audio applications.
A verifiable next signal is whether Xiaomi publishes benchmark results or a technical report for MiDashengLM-Spatial, and whether third-party developers adopt the model for non-Xiaomi hardware. The claim of being 'industry's first' remains company-reported until independent evaluation.