Meta introduces Muse Voice Transcribe with real-time ASR, 70+ languages and 20+ speakers

Meta has introduced Muse Voice Transcribe, a real-time audio perception model developed by Meta Superintelligence Labs. It is an autoregressive multimodal model from the Muse Spark family.

Source: FoneArena2 September 2026 at 3:48 pm ISTrss

Read the original at FoneArena

About this page

Source-linked context

This is a Digite360 summary page, not a republication. We retain the source headline, a short excerpt and attribution so you can decide whether to read the complete report.

Original headline: Meta introduces Muse Voice Transcribe with real-time ASR, 70+ languages and 20+ speakers
Product category: mobiles
Curation state: ingested