Meta launches Muse Realtime Avatar, eyeing real-time interactive video generation
alex_conneau · x · 2026-09-24
Alex Conneau, who leads Meta's voice efforts, announced Muse Realtime Avatar, built on the earlier Muse Realtime Voice work by teams across Voice, VideoGen, Infra and Product.
He framed Avatar as just the beginning: the long-term goal is real-time interactive videogen — AI you talk to via voice, expressing itself through increasingly rich visual worlds — the "#SeeTheAGI" research journey started two years ago, with "a lot more coming."
Related event: Meta Unveils Muse Realtime Avatar: Sub-second Realtime Digital Humans(18 posts)→
More from Multimodal
- Ditto launches swap-anything video tool to replace any video's main character — yoobinray · 2026-11-12
- Fable 5.2 impresses with pixel art gaussian splats, posts go viral — Flomerboy · 2026-11-12
- Seedream 5.5 nails a consistent character sticker set at just $0.02 per image — azed_ai · 2026-11-12
- Ant Group's open-source Ming-3.0-tts-0.5B tops Open TTS Leaderboard with 0.88 WER — NielsRogge · 2026-11-12
- Viggle Remake recreated in ComfyUI: swap any character in your videos with MiniMax H3 — TheLocalLab · 2026-11-12
- Pika Integrates Seedream 5.5: Split Images Into 100+ Layers for Precise Multi-Turn Edits — aziz4ai · 2026-11-12