bytedance/seed-audio-1.0
Seed Audio 1.0 is a new audio model from Bytedance that can generate high-quality, natural sounding audio using text, reference audios or an image.
Inference
Commercial use
Partner
Prompt examples
Examples are generated using the Seed Audio 1.0. You can customize them by clicking on the "Playground" button.
Prompt: Opens with a classic upbeat sitcom intro tune—bright electric-guitar strumming, cheerful bass, crisp drums, playful and bouncy; plays a few seconds then fades out. Inside a pet store, relaxed atmosphere, very faint room tone. Dave (man around 30, American accent, low voice, forced composure, pretend-expert) says smugly and falsely composed: "Oh~ this Golden Retriever is so well taken care of, scientifically raised since a pup. How old's the little guy?" Lily (young woman around 25, American accent, bright lively voice, blunt) sincerely blurts out: "Sir… that's an alpaca. You kind of look like it" Immediately a classic sitcom "audience roaring" canned laughter bursts out, fading loud to soft. Dave (man around 30, American accent, low voice, forced composure, pretend-expert) says sharply and rudely: "I never want to hear from you again! I can't believe you would even think to say that to me" Immediately a classic sitcom "audience gasps" fading loud to soft. Abrubptly the sound cuts off