Tether AI Research today announced the release of QVAC TranscribePsy, a compact 254 million-parameter multilingual automatic speech recognition model designed to run entirely on-device, without the need for cloud processing. The model can transcribe 10 minutes of audio in 1.65 seconds on an iPhone 17 Pro Max, emphasizing user data privacy and supporting 25 European languages (laptop) or 8 European languages (mobile). Paolo Ardoino, CEO of Tether, stated that the future of AI should not allow centralized platforms to pry into personal lives, and TranscribePsy demonstrates the rapid, powerful, and fully localized capabilities of advanced voice AI.