Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

Moonshine Voice has released new open-source speech-to-text models that outperform OpenAI's Whisper Large V3 in accuracy while using significantly fewer parameters and delivering much faster processing speeds. The Moonshine Medium Streaming model achieves 6.65% word error rate compared to Whisper's 7.44%, processes audio in just 107ms versus over 11 seconds for Whisper, and uses only 245 million parameters instead of 1.5 billion. These models are optimized for real-time voice applications with flexible input windows and caching capabilities that eliminate Whisper's computational waste from fixed 30-second processing chunks.