AIThe Decoder1h ago
Meta's new real-time audio model is the foundation for AI assistants
Meta's new real-time audio model is the foundation for AI assistants that never stop listening
TL;DRMeta released a fast speech-to-text model that transcribes audio in real-time with high accuracy.
Why it matters: Enables always-on AI assistants that can understand and respond to spoken commands instantly and naturally.
Meta's Superintelligence Labs have released Muse Voice Transcribe, a real-time transcription model that processes speech in 80-millisecond chunks, tells speakers apart, and detects sentence boundaries. According to Artificial Analysis, it delivers the most accurate streaming…
Read full articleSource: The Decoder · Opens in new tab