§ models · storyline

ByteDance introduces SeedRealtime full-duplex audio-visual LLM

ByteDance releases SeedRealtime, a full-duplex audio-visual large language model capable of processing and generating audio and video simultaneously within a single model.

Aug 10 · 07:48:17 · primary fetch1 sourceupdated Aug 10 · 07:48:17

ByteDance Seed Introduces SeedRealtime: a Native Audio-Visual Full-Duplex LLM That Watches, Listens and Speaks in One Model MarkTechPost

read full article on MarkTechPost ↗

§ sources1 publication · timeline below

MarkTechPostByteDance Seed Introduces SeedRealtime: a Native Audio-Visual Full-Duplex LLM That Watches, Listens and Speaks in One Modelprimary07:48:17