Model family1
Seed Audio
ByteDance’s speech model — a script read in a voice you describe or attach
Seed Audio is ByteDance’s speech line. Seed Audio 1.0 is sold here for text-to-speech: it reads a script in a voice you describe, or in a voice from a recording you attach with the speaker’s permission, and it is priced by the length of the script.
Releases1
Releases
Strengths and limits
Strengths and limits
Key Features
- Speech in a voice from a recording you are entitled to use.
- Priced by the length of the script.
Where it falls down
- A recording must be of your own voice or used with the speaker’s permission.
- The number of reference recordings per request is capped.
Model1
Model
Capability tables and prices are read from the live model catalogue.
| Model | Tools | Duration | Resolution | Audio | Credits |
|---|---|---|---|---|---|
| Seed Audio 1.0 | Text-To-Speech | — | — | from 1 credit · ≈ $0.06 |
Tools1
Tools
Audio
Frequently Asked Questions
ByteDance’s speech model. ByteDance describes it shaping a voice from a text description, an authorised reference sample, or both.
Ready to Get Started?
Every tool shows its price in credits before you run it.