# ByteDance Launches Audio-Video Full-Duplex Large Model SeedRealtime

- Category: Flash (快讯)
- Published: 2026-08-05T11:54:00.000Z
- Source date: 2026-08-05
- HTML: https://www.88z.ai/en/news/flash-20260805-07903abac0262161
- Markdown: https://www.88z.ai/en/news/flash-20260805-07903abac0262161.md
- Other language: https://www.88z.ai/news/flash-20260805-07903abac0262161.md

ByteDance Seed launches SeedRealtime, a native audio-video full-duplex large model that integrates audio, video, and text via a unified architecture for real-time multimodal interaction.

## At a glance

- Natively integrates audio, video, and text via a unified architecture for real-time watch-listen-speak interaction
- End-to-end evaluations show a 50% reduction in conversational rhythm issues compared to cascaded models

## The update

The ByteDance Seed team has officially released SeedRealtime, a native audio-video full-duplex large model. Using a unified architecture, it natively integrates audio, video, and text data, enabling users to watch, listen, and speak simultaneously during real-time multimodal interactions. SeedRealtime features three core capabilities: joint audio-video understanding, proactive interaction, and smooth conversational rhythm. End-to-end evaluations show that issues related to conversational rhythm are reduced by half compared to traditional cascaded models, significantly improving interaction coherence and naturalness.

## Sources

- [字节跳动Seed](https://mp.weixin.qq.com/s/qtRD2Sh5ulevxJoQx0bnwQ) (2026-08-05)

This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.