kjjk10/kokoro-82m 📝❓ → 🖼️

▶️ 27.4K runs 📅 Jan 2025 ⚙️ Cog 0.13.6 ⚖️ License
text-to-speech

About

Kokoro is a frontier TTS model for its size of 82 million parameters (text in/audio out).

Example Output

Output

Example output

Performance Metrics

0.80s Prediction Time
0.82s Total Time
All Input Parameters
{
  "text": "You open your eyes so that only a slender chink of light seeps in, and peer at the gingko trees in front of the Provincial Office. As though there, between those branches, the wind is about to take on visible form. As though the raindrops suspended in the air, held breath before the plunge, are on the cusp of trembling down, glittering like jewels.\n\nWhen you open your eyes properly, the trees’ outlines dim and blur. You’re going to need glasses before long.",
  "voice": "af_bella"
}
Input Parameters
text Type: stringDefault: Hello, world!
Text to convert to speech
voice Default: af
Voice to use
Output Schema

Output

Type: stringFormat: uri

Version Details
Version ID
882bc45ec70c819feeb972cb70af760fcfd67125bb66130e7b478e95bbd275d5
Version Created
January 8, 2025
Run on Replicate →