§ feed · storyline
Microsoft releases VibeVoice speech-to-text model with speaker
Microsoft releases VibeVoice, an MIT-licensed speech-to-text model with speaker diarization that transcribes one hour of audio in roughly nine minutes on Apple Silicon hardware.
Microsoft's MIT licensed VibeVoice speech-to-text model (think Whisper with speaker diarization) is really good - my notes on running the 5.71GB 4bit MLX conversion on an M5 MacBook, using about 60GB of RAM at peak and transcribing 1hr of audio in ~9 mins simonwillison.net/2026/Apr/27/...
§ sources1 publication · timeline below