Seed Audio 1.0

ByteDance's Seed Audio model for reference-guided speech

Seed Audio 1.0 on Melius

  1. Turn written text into natural speech

    Add Seed Audio 1.0 to a audio node and turn written text into natural speech without leaving your canvas.

  2. Guide the voice with audio or image references

    Add Seed Audio 1.0 to a audio node and guide the voice with audio or image references without leaving your canvas.

Try out Seed Audio 1.0 on Melius

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?

Melius is a node-based canvas: add a audio node, pick Seed Audio 1.0 from the model picker, and connect it to whatever should feed it or follow it. You only pay for what you generate.

Explore other models