So, if SpeechDetector currently does its work behind the scenes and doesn't provide the sort of information the documentation suggests that is should: a) what is the work it is doing behind the scenes and b) why does the documentation suggest that it returns a bool called speechDetected ?

Getting a similar error now - strange thing for me is that it had been working just fine for a couple days, now not working for no apparent reason. Running all the latest betas (macOS and Xcode), internal drive. Here's the console output: Passing along InferenceError::inferenceFailed::Error Domain=com.apple.UnifiedAssetFramework Code=5000 "There are no underlying assets (neither atomic instance nor asset roots) for consistency token for asset set com.apple.modelcatalog" UserInfo={NSLocalizedFailureReason=There are no underlying assets (neither atomic instance nor asset roots) for consistency token for asset set com.apple.modelcatalog} in response to ExecuteRequest