ByteDance
SeedRealtime
SeedRealtime is a native audio-visual, full-duplex large language model for continuous real-time interaction. Its unified end-to-end architecture combines audio, video and text so that it can perceive…
Explore modelEnglish
MODEL DIRECTORY
New releases, in one place. Explore models by their publication date.
SeedRealtime is a native audio-visual, full-duplex large language model for continuous real-time interaction. Its unified end-to-end architecture combines audio, video and text so that it can perceive…