Jin Daily AI Trivia : ByteDance Seed Audio 1.0 is here
ByteDance just launched Seed Audio 1.0, and this one is not just another text-to-speech model.
It can generate audio end-to-end from text, image, and audio input.
One single prompt can control the whole scene:
· Dialogue · Emotion · Tone · BGM · Ambience · Multi-speaker voice consistency
AI voice (i think should just call audio right now) generation is getting scary good now :D
PS: There is also Seed Music 1.0 coming out soon. and Seedream 5.0 Pro which can do layer edit on image. Seedance 2.5 etc. Bytedance on the roll !!
