Meta launches voice and expressive avatar features for the Muse app

Nov 6

1. 06:23

   Testing Catalog

   Meta Launches Muse Voice and Expressive Avatars for Muse Users

   Meta is rolling out Muse Voice and expressive avatars to Muse users in the US. The voice feature lets users think out loud, making it easier to brainstorm, plan trips, and prepare for interviews; the avatar makes facial expressions and gestures that match the conversation while listening and speaking. Muse is also beginning to launch in Mexico.

   Expand summary
2. 04:48

   Rohan PaulRelated discussion

   Rohan Paul joined this discussion ↗

   This post contributes to heat; it is not a formal report or confirmed fact.

3. 03:51

   cnBeta

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

   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.

   Expand summary
4. 03:51

   cnBetaRelated discussion

   cnBeta joined this discussion ↗

   This post contributes to heat; it is not a formal report or confirmed fact.

5. 03:48

   TechCrunch AI

   Meta Opens Muse AI Avatar Video Calls to Users Across the US

   Meta announced that the Muse Voice feature is now available to users across the US, allowing users to make phone calls and video calls to converse with the consumer-grade AI agent Muse. The feature debuted at the September Connect developer conference and is powered by two technologies, Muse Realtime Avatar and Muse Realtime Voice. The avatar, nicknamed Jolly, can be customized as a person, animal, or other character, and makes subtle facial expressions and gestures that match the tone of the conversation while speaking. Meta says real-time conversation is already supported on mobile, the web, and Mac, and will later come to its AI glasses and the Muse Charm hardware device launching before the end of the year.

   Expand summary
6. 03:42

   David Singleton

   Muse Launches Realtime Voice and Realtime Avatar Real-Time Voice Products

   Muse has launched Muse Realtime Voice and Muse Realtime Avatar, keeping voice, facial expressions, and gestures synchronized. The product responds instantly, and users can interject at any time while it is speaking. David Singleton said he is proud of the team that built the product.

   Expand summary
7. 03:25

   Unite.AISelected

   Meta Launches Real-Time Voice and Expressive Avatar for Muse Agent

   Meta announced that the Muse app now offers real-time voice conversation and expressive avatars on mobile, web, and Mac in the US, with conversations initiated via the phone icon in the top-right corner. Voice supports user interruptions, and the agent can continue executing tasks in the background during a conversation; users can choose voice-only, a side avatar, or a full-screen face-to-face view, with hundreds of voices available. Meta AI Research says the avatar is an audio-driven Diffusion Transformer that outputs 448x768, 25fps portrait video, with about 870 milliseconds from the user finishing speaking to the first byte of response; a single GB200 supports 12 concurrent real-time video generations, and distillation reduces each generation from 120 teacher evaluations to 2 student evaluations.

   Expand summary
8. 03:03

   The Verge AI

   Meta Launches Voice Mode and Animated Avatars for Muse AI Agent

   Meta CEO Mark Zuckerberg announced that the Muse AI Agent now supports real-time voice conversations, with the avatar at the top of the conversation animating in sync with what is being said, and users can adjust the tone through the conversation or avatar settings. A The Verge reporter, after testing on the iOS app, said voice responses were relatively fast, but pauses occurred when querying information, just like in text chat. The feature is currently rolling out to the app in the United States, and Meta says it will soon arrive on its AI glasses and will support the Muse Charm device planned to ship this year.

   Expand summary
9. 02:36

   AI at MetaRelated discussion

   AI at Meta joined this discussion ↗

   This post contributes to heat; it is not a formal report or confirmed fact.

10. 02:35

    Muse

    Muse launches voice feature, allowing conversations with Muse

    Muse announces the launch of the Voice feature: users can speak to Muse, and Muse will respond, for example going straight from "what should I cook" into cooking.

    Expand summary
11. 02:30

    Meta：Newsroom · AIFirst-partySelected

    Meta Launches Voice and Expressive Avatars for the Muse App

    Meta has introduced voice and expressive avatar features in the Muse app. Users can tap the phone icon in the upper right corner to start a real-time conversation and can interrupt mid-conversation. The feature first launches in the United States, covering mobile, web, and Mac, with hundreds of voices to choose from; the avatar makes facial expressions and gestures as the conversation proceeds. Voice conversations will also come to AI Glasses and Muse Charm. Muse Realtime Avatar and Muse Realtime Voice technologies support smooth real-time conversation.

    Expand summary