Kokoro-FastAPI---GPU

Kokoro-FastAPI---GPU

Docker app from grtgbln's Repository

Overview

Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching.
This is a version meant for Nvidia GPUs.

Runtime arguments

Web UI
http://[IP]:[PORT:8880]/
Network
bridge
Privileged
false
Extra Params
--gpus all

Template configuration

Web UI PortPorttcp

Container Port: 8880

Target
8880
Default
8880
Value
8880
Download ModelVariable

Download model on start

Target
DOWNLOAD_MODEL
Default
true|false
App DataPath

Path to the app data folder

Target
/app/api
Default
/mnt/user/appdata/kokoro-fastapi/data
Value
/mnt/user/appdata/kokoro-fastapi/data
Python PathVariable

Python path environment variable

Target
PYTHONPATH
Default
/app:/app/api
Value
/app:/app/api
Log LevelVariable

Logging level for the API

Target
API_LOG_LEVEL
Default
DEBUG
Value
DEBUG
Use GPUVariable

Enable GPU usage for PyTorch model inference

Target
USE_GPU
Default
true
Value
true
Python UnbufferedVariable

Set Python output to be unbuffered

Target
PYTHONUNBUFFERED
Default
1
Value
1

Details

Repository
ghcr.io/remsky/kokoro-fastapi-gpu:latest
Last Updated2026-06-01
First Seen2025-04-25

Run Kokoro-FastAPI---GPU on Unraid.

Kokoro-FastAPI---GPU is listed in Community Apps for Unraid OS. Explore Unraid to build a flexible home server, NAS, or homelab.