jaaari/kokoro-82m 📝🔢❓ → 🖼️

▶️ 51.5M runs 📅 Jan 2025 ⚙️ Cog 0.13.6 🔗 GitHub ⚖️ License
long-form-tts multilingual text-to-speech

About

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

Example Output

Output

Example output

Performance Metrics

1.41s Prediction Time
1.42s Total Time
All Input Parameters 
{
  "text": "Hi! I'm Kokoro, a text-to-speech voice crafted by hexgrad — based on StyleTTS2. You can also find me in Kuluko, an app that lets you create fully personalized audiobooks — from characters to storylines — all tailored to your preferences. Want to give it a go? Search for Kuluko on the Apple or Android app store and start crafting your own story today!",
  "speed": 1,
  "voice": "af_nicole"
}
Input Parameters
text (required) Type: string
Text input (long text is automatically split)
speed Type: numberDefault: 1Range: 0.1 - 5
Speech speed multiplier (0.5 = half speed, 2.0 = double speed)
voice Default: af_bella
Voice to use for synthesis
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Processing text (352 chars) with voice='af_nicole' at speed=1.0
Version Details
Version ID
f559560eb822dc509045f3921a1921234918b91739db4bf3daab2169b71c7a13
Version Created
January 29, 2025
Run on Replicate →