remsky/Kokoro-FastAPI

Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching

55
/ 100
Established

This project helps content creators, educators, and developers quickly turn written text into natural-sounding speech across multiple languages like English, Japanese, and Chinese. You provide text and select voices, and it outputs high-quality audio files, even allowing for custom voice mixes. It's designed for individuals or teams needing on-demand, customizable text-to-speech capabilities.

4,585 stars.

Use this if you need to generate spoken audio from text for videos, e-learning modules, virtual assistants, or any application requiring custom voice output without external cloud services.

Not ideal if you require real-time, ultra-low latency speech generation for live conversations, or if you need to clone specific unique voices from audio samples.

content-creation e-learning audio-production localization voice-over
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

4,585

Forks

764

Language

Python

License

Apache-2.0

Last pushed

Jan 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/remsky/Kokoro-FastAPI"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.