Meta ships Muse Realtime Avatars, calling real-time videogen infra its hardest problem
ukhndlwl · x · 2026-09-25
Meta's MSL team launched Muse Realtime Avatars, bringing any character into live conversation, rebuilt on a new realtime AI inference stack for voice and video at scale. Meta's Alexandre Conneau notes demos are easy — the hard part is optimizing latency/concurrency so quality, stability and unit economics hold at scale across models, hardware, LLM orchestration and the RTC stack.
Related event: Meta Unveils Muse Realtime Avatar: Sub-second Realtime Digital Humans(18 posts)→
More from Infra
- Gas-for-AI-datacenters forum co-located with CoRL shows energy demand spillover — carlosdponx · 2026-11-12
- a16z podcast: Mike Volpi on Cisco's 70+ acquisition playbook and the AI buildout — a16z · 2026-11-12
- AMD to pass Intel in server revenue by mid-2027 as share gains 6 points a year — BenBajarin · 2026-11-12
- Study: Reflective Data Center Roofs Actually Cool Daytime Ground by 1.8-2.2°C — SumitGup · 2026-11-12
- Tsinghua's BaGuaLu-2 tames MoE expert-load spikes at runtime, accepted to SC26 — jiqizhixin · 2026-11-12
- antirez backs low-bit DeepSeek 4.1 Flash over Qwen 27B dense on Apple M5 Macs — antirez · 2026-11-12