The new Muse Voice Transcribe model processes speech in 80-millisecond chunks and delivers final transcripts in roughly 0.16 seconds
Meta just gave every pair of its smart glasses a significant upgrade. The company’s Muse Voice Transcribe model, introduced on September 1, is now available across its entire smart glasses lineup, including Ray-Ban Meta and Oakley Meta devices, bringing real-time voice AI that processes audio faster than most people can blink.
The headline number: 0.16 seconds of final-transcript latency after someone finishes speaking. For context, the average human blink takes about 0.3 seconds. So this thing transcribes what you said before you finish blinking at the person you said it to.
Under the hood #
Muse Voice Transcribe works by chopping incoming audio into 80-millisecond chunks and processing them in near real-time. That granular approach delivers a 3.1% word error rate on English benchmarks, which puts it in competitive territory with the best speech-to-text systems available today.
The model handles speaker diarization for more than 20 speakers simultaneously, and it does so without requiring separate post-processing. Language support spans more than 70 languages.
For developers looking to build on top of it, Meta is offering the model through its Model API at $3 per 1,000 audio minutes. That works out to roughly $0.18 per hour of usage.
AI, tech, and the markets they move—in one daily briefing.
Daily. Free. Join 34,000+ readers across crypto, finance, and policy.
The bigger Muse picture #
Muse Voice Transcribe isn’t arriving in isolation. It follows the Muse Spark model, which Meta first introduced in April 2026 and began rolling out to users in June. Spark laid the groundwork for low-latency interactions on the glasses.
Meta’s smart glasses start at $299 for some 2026 models.
What’s coming next #
The company has a broader personal AI agent in development, codenamed Impacc, which is currently undergoing testing as of mid-September. That agent could eventually incorporate navigation capabilities.
Disclosure: This article was edited by Editorial Team. For more information on how we create and review content, see our