KokoroOnnx 7.0.0

KokoroOnnx .NET

A .NET port of the Kokoro TTS (Text-to-Speech) system using ONNX Runtime. This library provides a simple interface for synthesizing speech from text using pre-trained ONNX models.

Features

• Cross-platform support (.NET 8.0, .NET 9.0)
• Support for multiple voices
• GPU acceleration support (via ONNX Runtime GPU)

Prerequisites

• .NET 8.0 SDK or later
• ONNX model files (compatible with the original Kokoro TTS)
• Voice files (phoneme dictionaries, etc.)

Installation

Add the KokoroOnnx NuGet package to your project:

dotnet add package KokoroOnnx

Usage

Basic Usage

using KokoroOnnx;

 try
 {
 Console.WriteLine("Synthesizing...");
 
 // Synthesize speech
 Kokoro.Create(
 model: "models/kokoro_model.onnx",
 text: text,
 filename: "output.wav",
 voice: "jf_gongitsune",
 isPhonemes: true);
 
 Console.WriteLine($"Audio saved to: output.wav");
 
 // Play the audio
 Kokoro.PlayAudio("output.wav");
 }
 catch (Exception ex)
 {
 Console.WriteLine($"Error: {ex}");
 }

GPU Acceleration

To enable GPU acceleration, make sure you have the appropriate CUDA/cuDNN versions installed.

License

This project is licensed under the MIT License - see the file for details.

Acknowledgments

• Original Kokoro TTS project: kokoro-onnx
• ONNX Runtime: microsoft/onnxruntime