Providers

Unreal Speech

TTS 1 model 52 voices based in United States self-serve API data from documentation synced 2026-11-16

Unreal Speech is a San Francisco text-to-speech API whose voices are powered by the open-weights Kokoro model. It offers synchronous, streaming, WebSocket-with-timestamps and long-form asynchronous endpoints, plus a Studio product.

Text-to-speech 1

CompareModelLangsFeaturesPriceStatus
kokoroKokoro 8 1/8 $16.00 per 1M chars Default

Voices 52

Browse and filter all of them.

Esc

↑↓ move↵ open