On August 5, ByteDance announced the official launch of SeedRealTime, a large full-duplex native audio and video model. According to the introduction, as a key step towards full-modal interaction, SeedRealTime uses a unified architecture to natively integrate audio, video, and text, and can interact in real time on a continuous multi-modal stream of information, bringing a new experience of “watching, listening, and speaking.” Currently, SeedRealtime has fully launched the Doubao app.

On August 5, ByteDance announced the official launch of SeedRealTime, a large full-duplex native audio and video model. According to the introduction, as a key step towards full-modal interaction, SeedRealTime uses a unified architecture to natively integrate audio, video, and text, and can interact in real time on a continuous multi-modal stream of information, bringing a new experience of “watching, listening, and speaking.” Currently, SeedRealtime has fully launched the Doubao app.