LMSupply.Synthesizer

LMSupply.Synthesizer

Local text-to-speech synthesis using VITS/Piper models.

Known issue — the output is not yet intelligible speech. The synthesizer has no text-to-phoneme step: it maps letters to fixed ids instead of the phoneme ids the Piper voices were trained on, so what comes out is voice-like noise (a Whisper transcript of "The weather is beautiful today." read back "tube of warrior practitioner"), and text in non-Latin scripts comes out as near-silence.

Features

• Zero-config: Models download automatically from HuggingFace
• GPU Acceleration: CUDA, DirectML (Windows), CoreML (macOS)
• Licensing stated per voice: Piper's code is MIT; each voice's own license is in SynthesizerModelInfo.License (the default voice is public domain)
• Multiple Languages: English, Korean, Japanese, Chinese, and more

Quick Start

using LMSupply.Synthesizer;

#pragma warning disable LMSUPPLY001 // the output is not yet intelligible speech — see the repository README's known issue
// Load the default model
await using var synthesizer = await LocalSynthesizer.LoadAsync("default");

// Synthesize speech
var result = await synthesizer.SynthesizeAsync("Hello, welcome to LMSupply!");

Console.WriteLine($"Duration: {result.DurationSeconds:F2}s");
Console.WriteLine($"Real-time factor: {result.RealTimeFactor:F1}x");

// Save as WAV file
await synthesizer.SynthesizeToFileAsync("Hello world!", "output.wav");

Available Models

GPU Acceleration

# NVIDIA GPU
dotnet add package Microsoft.ML.OnnxRuntime.Gpu

# Windows (AMD/Intel/NVIDIA)
dotnet add package Microsoft.ML.OnnxRuntime.DirectML