jaaari / kokoro-82m

Kokoro v1.0 - text-to-speech (82M params, based on StyleTTS2)

  • Public
  • 3.5M runs
  • T4
  • Commercial use
  • GitHub
  • Weights
  • License
Run with an API
Playground API Examples README Versions

Run jaaari/kokoro-82m with an API

Input schema

textstring

Text input (long text is automatically split)

speednumber

Speech speed multiplier (0.5 = half speed, 2.0 = double speed)

Default
1
Minimum
0.1
Maximum
5
voicestring

Voice to use for synthesis

Default
"af_bella"

Output schema

Type
uri