Kokoro-FastAPI---CPU
Kokoro-FastAPI---CPU
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 running on CPUs. It is not recommended to run this on a CPU unless you have a very powerful CPU, as it will be slow. If you have a GPU, please use the GPU version of this container.
This is a version meant for running on CPUs. It is not recommended to run this on a CPU unless you have a very powerful CPU, as it will be slow. If you have a GPU, please use the GPU version of this container.
Runtime arguments
- Web UI
http://[IP]:[PORT:8880]/- Network
bridge- Privileged
- false
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
ONNX Optimization - Thread CountVariable
Number of threads to use for ONNX model inference
- Target
- ONNX_NUM_THREADS
- Default
- 8
- Value
- 8
ONNX Optimization - Inter Op Thread CountVariable
ONNX inter operation thread count
- Target
- ONNX_INTER_OP_THREADS
- Default
- 4
- Value
- 4
ONNX Optimization - Execution ModeVariable
ONNX execution mode
- Target
- ONNX_EXECUTION_MODE
- Default
- parallel
- Value
- parallel
ONNX Optimization - Optimization LevelVariable
ONNX optimization level
- Target
- ONNX_OPTIMIZATION_LEVEL
- Default
- all
- Value
- all
ONNX Optimization - Memory PatternVariable
Enable ONNX memory pattern optimization
- Target
- ONNX_MEMORY_PATTERN
- Default
- true
- Value
- true
ONNX Optimization - Arena Extend StrategyVariable
ONNX arena extend strategy
- Target
- ONNX_ARENA_EXTEND_STRATEGY
- Default
- kNextPowerOfTwo
- Value
- kNextPowerOfTwo
Log LevelVariable
Logging level for the API
- Target
- API_LOG_LEVEL
- Default
- DEBUG
- Value
- DEBUG
Categories
Details
Repository
ghcr.io/remsky/kokoro-fastapi-cpu:latestLast Updated2026-05-31
First Seen2025-04-25
Run Kokoro-FastAPI---CPU on Unraid.
Kokoro-FastAPI---CPU is listed in Community Apps for Unraid OS. Explore Unraid to build a flexible home server, NAS, or homelab.