zonos mark

Zonos Text to Speech

Zyphra/Zonos-v0.1-transformer is a transformer-based text-to-speech (TTS) model that converts written text into spoken audio. It’s suited for straightforward speech synthesis workflows where cost is driven by the amount of input text (pricing based on text length).

Use this model

Speed

Price

Inputs

Text

Outputs

Audio

Lab

Zyphra

Zonos Text to Speech sample outputs

Captured directly from our eval suite. Click any tile to inspect the full render.

Launch your first agent today

Build without code. Share without limits.

Create an Agent