Model Details
Full Model IDhexgrad/Kokoro-82M
Pipeline / Tasktext-to-speech
Library—
Downloads (all-time)10.1M
Likes7.3K
Last Modified4/10/2025
Author / Orghexgrad
PrivateNo — public
⚡ Quick Usage (Python)
Using the 🤗 Transformers library. Install with pip install transformers
from transformers import pipeline
# Load the model
pipe = pipeline("text-to-speech", model="hexgrad/Kokoro-82M")
# Run inference
result = pipe("Your input here")
print(result)🏷️ Tags
text-to-speechenarxiv:2306.07691arxiv:2203.02395base_model:yl4579/StyleTTS2-LJSpeechbase_model:finetune:yl4579/StyleTTS2-LJSpeechdoi:10.57967/hf/4329license:apache-2.0region:us
More text-to-speech Models
See all →🚀 Use This Model
Access model files, inference API, and full documentation on Hugging Face.
Open on Hugging Face →Browse Model Files ↗← Browse All Models🤖 Task: text-to-speech
This model is designed for the text-to-speech task. Explore more models for this use case.
All text-to-speech Models →📊 Popularity
⬇ Downloads10.1M
❤️ Community Likes7.3K
🛠️ Requirements
- →Check docs for installation steps.
- →Python 3.8+ recommended for Transformers.
- →GPU (CUDA) speeds up inference significantly.
- →Use model.half() for fp16 on limited VRAM.