Introducing AnySpeechRecognizer and AnyDecisionModel for Speech and Decisions on Apple Platforms

What happened

The authors announce two Swift packages for Apple platforms, AnySpeechRecognizer and AnyDecisionModel. AnySpeechRecognizer mirrors Apple's speech APIs while adding local Parakeet and Qwen3-ASR engines and speaker diarization for up to four speakers; AnyDecisionModel returns typed answers and probabilities for yes-or-no, multiple-choice, and rating-scale questions through local or hosted backends. Both support downloading open models from the Hugging Face Hub, and the reported speech evaluations cover macOS only, with no iPhone testing yet.

Read next

• More changes in today’s briefingGoogle DeepMind announces Gemini 4 Carbon with cybersecurity and long-horizon capabilities

The story so far

Hugging Face announced AnySpeechRecognizer and AnyDecisionModel, two Swift packages that give Apple-platform developers access to speech recognition and structured answers using local models or hosted backends. Both support downloading open models from the Hugging Face Hub and require Swift 6.2 or later and macOS 26 or iOS 26 or later. AnySpeechRecognizer mirrors Apple’s speech APIs, adds local NVIDIA Parakeet and Alibaba Qwen3-ASR engines running through Core ML, and supports speaker diarization for up to four speakers. The reported speech evaluations cover macOS only; the authors have not yet tested it on iPhones. AnyDecisionModel returns typed answers and probabilities for yes-or-no, multiple-choice and rating-scale questions through local or hosted backends. The Parakeet and Sortformer runtimes and the MLX backend require Apple silicon.