Seed Audio Adds Doubao Seed-Audio 1.0 for Full-Scene AI Audio Creation

Seed Audio, an AI music creation workspace, has announced support for ByteDance and Volcengine's newly released multimodal audio generation model, Doubao Seed-Audio 1.0. This model represents a significant shift from traditional text-to-speech or music-only generation to full-scene audio creation, where dialogue, emotion, accents, background music, ambience, and sound effects can be generated together seamlessly. The model is designed to address the needs of a broad range of creators, including video creators, marketers, podcast teams, game developers, educators, and social media editors, who often require audio that fits a specific scene rather than isolated clips. Seed Audio has integrated Doubao Seed-Audio 1.0 into its platform, which centers around the Seed Audio Agent, a guided creation environment that helps users translate plain-language goals into actionable music directions. The platform also offers a suite of tools, including the AI Music Generator for creating songs and instrumentals, AI Cover for generating new vocal or style versions, Extend for lengthening tracks, Add Tracks for adding accompaniment or vocals, Mashup for combining source ideas, Replace Section for targeted revisions, and Vocal Remover for separating vocals and instrumentals. Additionally, users can explore public tracks via Explore and manage their works through My Works. Seed Audio aims to streamline the creation process, allowing users to draft, refine, and finish audio assets without losing the original idea. For visual assets, the company also offers i2v.ai, an AI image and video generation platform that pairs naturally with Seed Audio for projects requiring both sound and visuals.

The integration of Doubao Seed-Audio 1.0 into Seed Audio's workspace underscores a broader industry trend toward contextual audio creation. Unlike traditional models that focus solely on text-to-speech or music generation, Doubao Seed-Audio 1.0 is positioned for end-to-end audio creation, enabling the generation of entire audio experiences that include voices, music, spatial texture, and sound effects. This capability is particularly valuable for projects like podcast trailers, short dramas, and game teasers, where multiple audio elements must work together harmoniously. Seed Audio's platform enhances this by providing a workflow that supports generation, editing, and refinement, reducing friction for creators who often need to iterate on their audio assets. The company's spokesperson emphasized that creators need more than just a model response; they need a way to draft, refine, reuse, and finish audio assets, which Seed Audio aims to provide through its agent-based environment and comprehensive toolset.