Audio model · ByteDance
Seed Audio 1.0
ByteDance's Seed Audio model for reference-guided speech
What is Seed Audio 1.0?
Seed Audio 1.0 is ByteDance's text-to-speech model. It generates audio from text and can take optional audio or image references to shape the voice.
Capabilities
- Turn written text into natural speech
- Guide the voice with audio or image references
Seed Audio 1.0 on Melius
Melius runs Seed Audio 1.0 alongside every other major image, video, audio, and text model, so you can generate with it, compare it against the field, and let the Mel agent route to it automatically — all on one infinite canvas. You only pay for what you generate.
Frequently asked questions
What is Seed Audio 1.0?
Seed Audio 1.0 is ByteDance's text-to-speech model. It generates audio from text and can take optional audio or image references to shape the voice.
How do I use Seed Audio 1.0 on Melius?
Open Melius, add a node, and pick Seed Audio 1.0 from the model picker — or just describe what you want and let the Mel agent route to it. You only pay for what you generate.