Useful, an AI company focused on improving human-machine communication, has open-sourced Moonshine, a new speech-to-text model that aims to significantly reduce the latency of voice interfaces. According to Useful founder Pete Warden, Moonshine returns results 1.7 times faster than OpenAI’s Whisper model while matching or exceeding its accuracy. The model’s variable-length input window allows it to process short audio clips five times faster than Whisper. Moonshine’s low resource requirements enable it to run locally on devices without a network connection, ensuring privacy and instant access anywhere in the world. The company has already showcased Moonshine’s capabilities in its Torre translator, which offers near-instant translations during conversations.