# Doubao Real-time Audio-Video Call Model 1.0 API Fully Launched

- Category: Flash (快讯)
- Published: 2026-11-19T11:58:00.000Z
- Source date: 2026-11-19
- HTML: https://www.88z.ai/en/news/flash-20261119-178e911225930624
- Markdown: https://www.88z.ai/en/news/flash-20261119-178e911225930624.md
- Other language: https://www.88z.ai/news/flash-20261119-178e911225930624.md

Volcano Engine launches the Doubao SeedRealtime 1.0 API for real-time audio-video calls, using an end-to-end architecture to unify audio-visual processing and expression, supporting low-latency interaction and proactive scene understanding.

## At a glance

- End-to-end model unifies audio-visual expression to reduce latency and loss
- Supports continuous scene understanding and proactive speech, including multi-person distinction

## The update

Volcano Engine has fully launched the Doubao SeedRealtime 1.0 API for real-time audio-video calls. This model employs an end-to-end architecture that unifies sound, visuals, temporal data, and linguistic expression, supporting real-time interaction with continuous multimodal information streams. This design allows users to see, listen, and speak simultaneously, effectively reducing the latency and information loss associated with traditional multi-module serial processing. The model can continuously understand contexts and proactively initiate conversations. Official demonstrations include six use cases, such as distinguishing individuals in group dining settings, customizing travel itineraries, and translating and explaining menus at Sichuan restaurants.

## Sources

- [火山引擎](https://mp.weixin.qq.com/s/fyNH7Y6o32kxc4GeK8Qb3A) (2026-11-19)

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.
