codingayam/kokoro-82m-complete 📝🔢❓ → 🖼️
About
Kokoro by hexgrad - TTS Model (With all voices)
Example Output
Output
Performance Metrics
0.23s
Prediction Time
38.03s
Total Time
All Input Parameters
{ "text": "Hello, this is Kokoro, an open-weight text-to-speech model.", "voice": "af_heart" }
Input Parameters
- text
- Text to convert to speech
- speed
- Speech speed modifier. 1x = normal speed, 2x = 2x normal speed. Useful for mitigating rushing on long utterances.
- voice
- Voice to use for synthesis
Output Schema
Output
Version Details
- Version ID
230ab3a1d0356c9d29d3006b33fadaf28dc73ba681e181cbc97dabeed678172e
- Version Created
- September 9, 2025