Meta launches an AI that can distinguish 20 voices in a single recording

Meta unveiled Muse Voice Transcribe, an AI model that performs real‑time speech transcription while distinguishing up to 20 different speakers and detecting pauses. The model will be offered via Meta’s API and the Meta AI app for macOS.

Summary written by Kernelia from the original article by Hipertextual. The story and its rights belong to its author.