Gradio

Kokoro is an open-weight TTS model with 82 million parameters.

This demo uses native US English and British English speakers. But also supports multiple languages using G2P and phonemizer. Select your language below!

Input Text

Up to ~500 characters per Generate, or ∞ characters per Stream. Supports IPA within ()[] parethesis and brackets.

Voice

Quality and availability vary by language

Hardware

GPU is usually faster, but has a usage quota

Language

Select language for G2P processing

Speed

0.5 2

Output Audio

Tokens used to generate the audio, up to 510 context length.

💡 Customize pronunciation with Markdown link syntax and /slashes/ like [Kokoro](/kˈOkəɹO/)

💬 To adjust intonation, try punctuation ;:,.!?—…"()“” or stress ˈ and ˌ

⬇️ Lower stress [1 level](-1) or [2 levels](-2)

⬆️ Raise stress 1 level [or](+2) 2 levels (only works on less stressed, usually short words)