Seed Audio 1.0
Generate high-quality, natural sounding audio from text, reference audio, or images.
About
A sophisticated audio generation model from ByteDance that produces natural speech and sound effects. It supports multimodal inputs, allowing users to guide generation with text prompts, reference audio clips, or even images.
Details
- Built with
- Unknown
- Creator
- Source date
- Published on X Jun 25, 2026
- Listed
- Added to Dropday 1h ago
- Evidence
- Strong
The page is a live, functional model playground hosted on fal.ai with an interactive interface and API documentation.
Prompt
Interior, the glass lamp room atop a stone lighthouse at the height of a night storm. Rain lashes the windows. Wind howls. Waves boom far below. The rotating lens hums and clicks.
Timeline
Teaser
Video
Playable
Product
Loading…
