Meta opens real-time video calls with Muse AI agents to US users
Meta has opened real-time video calls with its Muse AI agent to all US users. Users can converse with animated avatars that support outfit changes. Technically, Muse Realtime Voice outputs speech tokens carrying voice and expression information, while Muse Realtime Avatar converts the same stream into lip-synced video. Meta uses knowledge distillation to enable student models to replicate 120 times the effect of the teacher model per video block with only two forward passes.
Continue looking at this topic
OpportunitiesMastering AI + Short Video Matrix for Customer Acquisition in 30 Days: From Scratch to Solo Operation ↗Hotly discussed viewsAI is tasked with creating educational videos based on implementation plans: how do we avoid scenarios where the visuals look great but the information is wrong? ↗News and AnalysisAI video can now reach 10 minutes: Should creators extend duration or rewrite scripts first? ↗Open-source projectandrew-babo/muse4ai ↗Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original