PANews reported on April 9th ​​that ByteDance announced the launch of Seeduplex, a native full-duplex voice model. According to reports, compared to the previous generation half-duplex Doubao end-to-end voice model, Seeduplex is based on a new "listen and speak simultaneously" framework design, significantly improving the naturalness and smoothness of the interactive experience. Seeduplex is now fully available on the Doubao App.