skills.rest
marvelousempire
marvelousempireCOMMUNITY
Explore all skills by this author →
GitHub

kokoro-fastapi

Integrate and manage Kokoro FastAPI for text-to-speech with ONNX and GPU PyTorch.

Updated Aug 27, 2026
Search Tags:#fastapi#docker#pytorch#tts#onnx#kokoro-fastapi
One-click install
npx skills add https://github.com/marvelousempire/ai-skills-library --skill kokoro-fastapi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: kokoro-fastapi
Source: https://github.com/marvelousempire/ai-skills-library/tree/main/skills/external/kokoro-fastapi
Command: npx skills add https://github.com/marvelousempire/ai-skills-library --skill kokoro-fastapi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps you integrate and manage the Kokoro FastAPI service, which is a Docker-friendly FastAPI wrapper for Kokoro TTS with CPU ONNX and optional GPU PyTorch paths, streamlining the process of using Kokoro TTS API and self-hosted TTS OpenAI compatible services.

Core Features & Use Cases

  • Integration: Facilitates the integration of Kokoro FastAPI into your environment.
  • Management: Provides guidance on managing and using Kokoro FastAPI for TTS.
  • Use Case: If you need to use Kokoro TTS API or Kokoro FastAPI, this Skill can help you set up and manage the service.

Quick Start

Use the kokoro-fastapi skill to integrate Kokoro FastAPI into your environment.

Frequently Asked Questions about kokoro-fastapi

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up a self-hosted text-to-speech API using FastAPI and Docker?▼

To set up a self-hosted text-to-speech API, you can integrate the Kokoro FastAPI service using Docker and a Python environment to manage TTS with ONNX and optional PyTorch GPU paths.

Can I run Kokoro TTS with ONNX on CPU and PyTorch on GPU?▼

Yes, Kokoro FastAPI supports running TTS using CPU ONNX paths and provides optional GPU PyTorch paths, allowing you to choose the execution environment that fits your hardware.

What is the best way to integrate an OpenAI compatible TTS service in my application?▼

The best way to integrate an OpenAI compatible TTS service is to deploy Kokoro FastAPI, a Docker-friendly wrapper that streamlines using self-hosted TTS APIs within your application environment.

Do I need Docker and Python to manage the Kokoro FastAPI TTS service?▼

Yes, managing the Kokoro FastAPI TTS service requires both Docker and a Python environment to run the FastAPI wrapper and handle the ONNX or PyTorch execution paths.

Are there limitations when using ONNX for text-to-speech instead of PyTorch?▼

Using ONNX for text-to-speech provides a CPU-optimized execution path, while PyTorch offers an optional GPU path, meaning your limitation is hardware dependency if you need GPU acceleration.

How does the Kokoro FastAPI skill help manage text-to-speech workflows?▼

The Kokoro FastAPI skill facilitates integration and provides management guidance for the TTS service, streamlining deployment and usage of OpenAI compatible self-hosted endpoints.

Related Skills

Explore More Software Engineering Skills→
bonitasoft-presalesbonitasoft-presales

bonita-deploy-local

Automate local Bonita server deployment with Docker Compose and Maven.

Official
Intermediate
michaelboedingmichaelboeding
24

voice-generation

Convert text into speech using Gemini, ElevenLabs, or OpenAI TTS backends.

Community
Intermediate
rish2jainrish2jain

nvidia-nim

Deploy and operate NVIDIA Inference Microservices for GPU-accelerated AI inference.

Community
Advanced
JOHNNYWHITEMIKEJOHNNYWHITEMIKE

sherpa-onnx-tts

Convert input text into offline speech audio using sherpa-onnx.

Community
Intermediate