vladpolbennikov/kokoro-82m-all-voices 📝🔢 → 🖼️

▶️ 928 runs 📅 Sep 2025 ⚙️ Cog 0.16.7 🔗 GitHub ⚖️ License
long-form-tts text-to-speech

About

Kokoro v1.0 2025 Jan 27 - text-to-speech (82M params, based on StyleTTS2)

Example Output

Output

Example output

Performance Metrics

0.53s Prediction Time
0.55s Total Time
All Input Parameters 
{
  "text": "Hey there! Great to meet you! And yep, this is actually my voice! I’d genuinely love to get to know more about you. What’s something you’re super into these days? Maybe you’ve got a hobby or a passion you could tell me about?",
  "speed": 0.8,
  "voice": "af_heart"
}
Input Parameters
text (required) Type: string
Текст для синтеза
speed Type: numberDefault: 1
Скорость воспроизведения (1.0 — без изменений)
voice Type: stringDefault: af_heart
Голос (например 'af_heart')
Output Schema

Output

Type: string • Format: uri

Version Details
Version ID
dd1276d5d756b0cdfaa795f400ead9d6fe1c1d7812f72703dbeea1705cb7dfa1
Version Created
September 18, 2025
Run on Replicate →