# Volcengine Launches Doubao Audio Generation Model 1.0

- Category: Flash (快讯)
- Published: 2026-06-24T11:58:00.000Z
- Source date: 2026-06-24
- HTML: https://www.88z.ai/en/news/flash-20260624-22477883b5599893
- Markdown: https://www.88z.ai/en/news/flash-20260624-22477883b5599893.md
- Other language: https://www.88z.ai/news/flash-20260624-22477883b5599893.md

Volcengine has released the Doubao Audio Generation Model 1.0, which supports text or audio reference inputs to generate complete audio end-to-end, including multi-character dialogues, emotions, and background music, while maintaining consistent voice tones over long durations.

## At a glance

- Supports text or audio reference inputs for end-to-end complete audio generation
- Single prompt orchestrates multi-roles and background, maintaining voice consistency over time

## The update

Volcengine has officially launched the Doubao Audio Generation Model 1.0. This model supports text descriptions or audio reference inputs for the first time, enabling end-to-end generation of target audio content. With a single prompt, users can orchestrate multi-character dialogues, specify emotional tones, and integrate background music and atmospheric effects to directly produce complete audio works. Furthermore, the model maintains high voice consistency during long-duration audio generation tasks, ensuring the coherence and professionalism of the output, thereby providing a more efficient one-stop solution for audio creation.

## Sources

- [火山引擎](https://mp.weixin.qq.com/s/iL0uyUjOMUEfudeuDP6wQQ) (2026-06-24)

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.
