←News detail

cnBetaUpdated Nov 6 04:21

Meta adds real-time voice conversation and dynamic avatars to its Muse AI assistant

AI summary

Meta adds real-time voice conversation and animated avatars to its Muse AI assistant, supporting natural turn-taking and real-time interruption. Users can choose a style from hundreds of voices, or describe speed, tone, and accent in text to let Muse adjust itself. During conversations, the Muse avatar displays corresponding expressions and gestures based on the content, and Meta says the experience is powered by Muse Realtime Voice and Muse Realtime Avatar technology. A Verge reporter found during testing that Muse usually responds quickly, but occasionally pauses when looking up information; the avatar animation performs well but is sometimes slightly eerie, and the voice also cannot fully imitate the Mark Zuckerberg persona the reporter selected.

Why read this

AI score 58

The original text records three capabilities: real-time voice interruption, voice customization, and animated avatars, and also preserves details about response pauses during testing and the somewhat eerie appearance of the avatar.

Topics

Tags

Body · AI translation

Users can directly speak out ideas that haven't yet been fully developed, letting Muse listen and help brainstorm and plan trips as they go; they can also use it to simulate interviews, rehearse speeches, or prepare proposals. Voice supports natural turn-taking and real-time interruptions, and users can choose a style from hundreds of voices, or describe in text the desired speaking rate, tone, and accent, letting Muse adjust itself accordingly.

During the conversation, Muse's avatar will display corresponding facial expressions and gestures based on what is being discussed. Meta says this experience is powered by Muse Realtime Voice and Muse Realtime Avatar technology. When a The Verge reporter tried it out, they found that Muse usually responds quickly, but occasionally pauses when looking up information; the avatar's animation performs well, though it is sometimes slightly eerie, and the voice cannot fully imitate the Mark Zuckerberg persona the reporter selected.

Source

cnBeta