Salsa Sound has released MIXaiR version 2.0 to deliver multiple automated spatial audio mixes for the same listening experience, whether over headphones or loudspeaker setups. It requires no tracking or manual operation as the system takes audio feeds from existing broadcast microphones at a stadium. It relies on AI algorithms to detect, mix in and enhance the on-pitch sounds and create real-time mixes.

Salsa Sound says its AI-based solution gives broadcasters and sports organizations a way to create automated mixes and is designed to speed up audio workflows, automatically rendering to multiple formats and mixing multiple language versions or crowd flavors (e.g., home/away). Each mix is automatically made compliant to the requisite loudness standards and parameters required for social media platforms, linear broadcast, VOD or OTT.

MIXaiR 2.0 has been “trained” with hundreds of hours of content from English Premier League and Championship games to learn what sounds make up a great mix. The system automatically recognizes significant audio moments in the game and can automatically reduce profanity from pitch-side mics getting into the broadcast.

The newest version of MIXaiR transitions its technology from a 1RU hardware-based offering to a pure software solution that supports all major operating systems (macOS, Linux, Windows, etc.) as well as VMs and cloud platforms. This solution is scalable, cost-efficient and can be deployed onsite as part of a remote production workflow, over IP or in the cloud.

Here’s a video of how it works: