v0.1: Robovoice — PTT re-voicing app
WinForms tray app that captures text (from file or direct input) and synthesizes speech via libpiper (Piper TTS), outputting to any audio device (VB-CABLE for virtual mic routing). Features: - Global PTT hotkey (configurable F1-F12) via WH_KEYBOARD_LL - Text file sequential reader (line-by-line on each PTT cycle) - Direct text input with Speak button - Voice manager: browse 147-voice Piper catalogue, download, remove - libpiper P/Invoke wrapper with UTF-8 marshaling, streaming chunks - BufferedWaveProvider streaming playback with trailing silence flush - Sentence terminator auto-append (fixes espeak-ng final-word drop) - Tray icon with minimize-to-tray Architecture: - Robovoice.Core: ITtsEngine, ISttSource interfaces, voice catalogue - Robovoice.Tts.LibPiper: P/Invoke wrapper for libpiper.dll - Robovoice.Stt.File: text file STT source (testing without mic server) - Robovoice.Stt.Udp: UDP client stub (for future Linux mic server) - Robovoice.App: WinForms UI, orchestrator, PTT hotkey, audio output
This commit is contained in:
@@ -0,0 +1,179 @@
|
||||
using System.Runtime.InteropServices;
|
||||
using Robovoice.Core;
|
||||
|
||||
namespace Robovoice.Tts.LibPiper;
|
||||
|
||||
public sealed class LibPiperTtsEngine : ITtsEngine
|
||||
{
|
||||
private readonly string _modelPath;
|
||||
private readonly string _espeakDataPath;
|
||||
private readonly float? _noiseScaleOverride;
|
||||
private readonly float? _lengthScaleOverride;
|
||||
private readonly float? _noiseWScaleOverride;
|
||||
private float _noiseScale;
|
||||
private float _lengthScale;
|
||||
private float _noiseWScale;
|
||||
|
||||
private IntPtr _synth;
|
||||
private int _sampleRate;
|
||||
private bool _initialized;
|
||||
private bool _disposed;
|
||||
|
||||
public string Name => "libpiper";
|
||||
|
||||
public int SampleRate => _sampleRate;
|
||||
|
||||
public LibPiperTtsEngine(
|
||||
string modelPath,
|
||||
string espeakDataPath,
|
||||
float? noiseScale = null,
|
||||
float? lengthScale = null,
|
||||
float? noiseWScale = null)
|
||||
{
|
||||
_modelPath = modelPath;
|
||||
_espeakDataPath = espeakDataPath;
|
||||
_noiseScaleOverride = noiseScale;
|
||||
_lengthScaleOverride = lengthScale;
|
||||
_noiseWScaleOverride = noiseWScale;
|
||||
_noiseScale = noiseScale ?? 0.667f;
|
||||
_lengthScale = lengthScale ?? 1.0f;
|
||||
_noiseWScale = noiseWScale ?? 0.8f;
|
||||
}
|
||||
|
||||
public Task InitializeAsync(CancellationToken ct = default)
|
||||
{
|
||||
ObjectDisposedException.ThrowIf(_disposed, this);
|
||||
if (_initialized)
|
||||
return Task.CompletedTask;
|
||||
|
||||
NativeDependencyLoader.EnsureLoaded();
|
||||
|
||||
_synth = PiperCreateUtf8(_modelPath, _modelPath + ".json", _espeakDataPath);
|
||||
if (_synth == IntPtr.Zero)
|
||||
throw new InvalidOperationException(
|
||||
$"piper_create failed for model: {_modelPath}");
|
||||
|
||||
var defaults = PiperNative.piper_default_synthesize_options(_synth);
|
||||
_noiseScale = _noiseScaleOverride ?? defaults.NoiseScale;
|
||||
_lengthScale = _lengthScaleOverride ?? defaults.LengthScale;
|
||||
_noiseWScale = _noiseWScaleOverride ?? defaults.NoiseWScale;
|
||||
|
||||
_sampleRate = 22050;
|
||||
_initialized = true;
|
||||
return Task.CompletedTask;
|
||||
}
|
||||
|
||||
public async IAsyncEnumerable<AudioChunk> SynthesizeAsync(
|
||||
string text,
|
||||
[System.Runtime.CompilerServices.EnumeratorCancellation] CancellationToken ct = default)
|
||||
{
|
||||
ObjectDisposedException.ThrowIf(_disposed, this);
|
||||
if (!_initialized)
|
||||
throw new InvalidOperationException("Engine not initialized.");
|
||||
|
||||
var options = new PiperSynthesizeOptions
|
||||
{
|
||||
SpeakerId = 0,
|
||||
LengthScale = _lengthScale,
|
||||
NoiseScale = _noiseScale,
|
||||
NoiseWScale = _noiseWScale,
|
||||
};
|
||||
|
||||
byte[] textBytes = System.Text.Encoding.UTF8.GetBytes(EnsureTerminator(text) + "\0");
|
||||
GCHandle textPin = GCHandle.Alloc(textBytes, GCHandleType.Pinned);
|
||||
try
|
||||
{
|
||||
int startResult = PiperNative.piper_synthesize_start(
|
||||
_synth, textPin.AddrOfPinnedObject(), in options);
|
||||
if (startResult != PiperNative.PiperOk)
|
||||
throw new InvalidOperationException($"piper_synthesize_start failed: {startResult}");
|
||||
|
||||
while (true)
|
||||
{
|
||||
ct.ThrowIfCancellationRequested();
|
||||
|
||||
PiperAudioChunk chunk = default;
|
||||
int result = await Task.Run(() => PiperNative.piper_synthesize_next(_synth, out chunk), ct);
|
||||
|
||||
if (chunk.NumSamples > 0 && chunk.Samples != IntPtr.Zero)
|
||||
{
|
||||
int numSamples = (int)chunk.NumSamples;
|
||||
float[] samples = new float[numSamples];
|
||||
Marshal.Copy(chunk.Samples, samples, 0, numSamples);
|
||||
|
||||
if (chunk.SampleRate > 0)
|
||||
_sampleRate = chunk.SampleRate;
|
||||
|
||||
yield return new AudioChunk(samples, _sampleRate);
|
||||
}
|
||||
|
||||
if (result == PiperNative.PiperDone || chunk.IsLast)
|
||||
break;
|
||||
|
||||
if (result < 0)
|
||||
throw new InvalidOperationException($"piper_synthesize_next failed: {result}");
|
||||
}
|
||||
}
|
||||
finally
|
||||
{
|
||||
textPin.Free();
|
||||
}
|
||||
}
|
||||
|
||||
private static string EnsureTerminator(string text)
|
||||
{
|
||||
string trimmed = text.TrimEnd();
|
||||
if (trimmed.Length == 0)
|
||||
return text;
|
||||
char last = trimmed[^1];
|
||||
if (last is '.' or '!' or '?' or ',' or ';' or ':' or ')' or ']' or '}' or '"' or '\'' or '。' or '！' or '？')
|
||||
return text;
|
||||
return trimmed + ".";
|
||||
}
|
||||
|
||||
private static IntPtr PiperCreateUtf8(string modelPath, string? configPath, string espeakDataPath)
|
||||
{
|
||||
byte[] modelBytes = System.Text.Encoding.UTF8.GetBytes(modelPath + "\0");
|
||||
byte[] espeakBytes = System.Text.Encoding.UTF8.GetBytes(espeakDataPath + "\0");
|
||||
|
||||
GCHandle modelPin = GCHandle.Alloc(modelBytes, GCHandleType.Pinned);
|
||||
GCHandle espeakPin = GCHandle.Alloc(espeakBytes, GCHandleType.Pinned);
|
||||
GCHandle? configPin = null;
|
||||
byte[]? configBytes = null;
|
||||
|
||||
if (configPath is not null)
|
||||
{
|
||||
configBytes = System.Text.Encoding.UTF8.GetBytes(configPath + "\0");
|
||||
configPin = GCHandle.Alloc(configBytes, GCHandleType.Pinned);
|
||||
}
|
||||
|
||||
try
|
||||
{
|
||||
return PiperNative.piper_create(
|
||||
modelPin.AddrOfPinnedObject(),
|
||||
configPin?.AddrOfPinnedObject() ?? IntPtr.Zero,
|
||||
espeakPin.AddrOfPinnedObject());
|
||||
}
|
||||
finally
|
||||
{
|
||||
modelPin.Free();
|
||||
espeakPin.Free();
|
||||
configPin?.Free();
|
||||
}
|
||||
}
|
||||
|
||||
public ValueTask DisposeAsync()
|
||||
{
|
||||
if (_disposed)
|
||||
return ValueTask.CompletedTask;
|
||||
|
||||
if (_synth != IntPtr.Zero)
|
||||
{
|
||||
PiperNative.piper_free(_synth);
|
||||
_synth = IntPtr.Zero;
|
||||
}
|
||||
|
||||
_disposed = true;
|
||||
return ValueTask.CompletedTask;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,28 @@
|
||||
using System.Runtime.InteropServices;
|
||||
|
||||
namespace Robovoice.Tts.LibPiper;
|
||||
|
||||
internal static class NativeDependencyLoader
|
||||
{
|
||||
private static int _loaded;
|
||||
|
||||
public static void EnsureLoaded()
|
||||
{
|
||||
if (Interlocked.CompareExchange(ref _loaded, 1, 0) != 0)
|
||||
return;
|
||||
|
||||
string baseDir = AppContext.BaseDirectory;
|
||||
string nativeDir = Path.Combine(baseDir, "runtimes", "win-x64", "native");
|
||||
|
||||
if (RuntimeInformation.IsOSPlatform(OSPlatform.Windows) && Directory.Exists(nativeDir))
|
||||
{
|
||||
if (!SetDllDirectory(nativeDir))
|
||||
throw new InvalidOperationException(
|
||||
$"SetDllDirectory failed for: {nativeDir}");
|
||||
}
|
||||
}
|
||||
|
||||
[DllImport("kernel32.dll", SetLastError = true, CharSet = CharSet.Unicode)]
|
||||
[return: MarshalAs(UnmanagedType.Bool)]
|
||||
private static extern bool SetDllDirectory(string lpPathName);
|
||||
}
|
||||
@@ -0,0 +1,65 @@
|
||||
using System.Runtime.InteropServices;
|
||||
|
||||
namespace Robovoice.Tts.LibPiper;
|
||||
|
||||
[StructLayout(LayoutKind.Sequential)]
|
||||
internal struct PiperSynthesizeOptions
|
||||
{
|
||||
public int SpeakerId;
|
||||
public float LengthScale;
|
||||
public float NoiseScale;
|
||||
public float NoiseWScale;
|
||||
}
|
||||
|
||||
[StructLayout(LayoutKind.Sequential)]
|
||||
internal struct PiperAudioChunk
|
||||
{
|
||||
public IntPtr Samples;
|
||||
public nuint NumSamples;
|
||||
public int SampleRate;
|
||||
|
||||
[MarshalAs(UnmanagedType.U1)]
|
||||
public bool IsLast;
|
||||
|
||||
public IntPtr Phonemes;
|
||||
public nuint NumPhonemes;
|
||||
public IntPtr PhonemeIds;
|
||||
public nuint NumPhonemeIds;
|
||||
public IntPtr Alignments;
|
||||
public nuint NumAlignments;
|
||||
}
|
||||
|
||||
internal static class PiperNative
|
||||
{
|
||||
private const string LibName = "piper";
|
||||
|
||||
public const int PiperOk = 0;
|
||||
public const int PiperDone = 1;
|
||||
public const int PiperErrGeneric = -1;
|
||||
|
||||
[DllImport(LibName, CallingConvention = CallingConvention.Cdecl)]
|
||||
public static extern IntPtr piper_create(
|
||||
IntPtr modelPath,
|
||||
IntPtr configPath,
|
||||
IntPtr espeakDataPath);
|
||||
|
||||
[DllImport(LibName, CallingConvention = CallingConvention.Cdecl)]
|
||||
public static extern void piper_free(IntPtr synth);
|
||||
|
||||
[DllImport(LibName, CallingConvention = CallingConvention.Cdecl)]
|
||||
public static extern PiperSynthesizeOptions piper_default_synthesize_options(IntPtr synth);
|
||||
|
||||
[DllImport(LibName, CallingConvention = CallingConvention.Cdecl)]
|
||||
public static extern int piper_synthesize_start(
|
||||
IntPtr synth,
|
||||
IntPtr text,
|
||||
in PiperSynthesizeOptions options);
|
||||
|
||||
[DllImport(LibName, CallingConvention = CallingConvention.Cdecl)]
|
||||
public static extern int piper_synthesize_next(
|
||||
IntPtr synth,
|
||||
out PiperAudioChunk chunk);
|
||||
|
||||
[DllImport(LibName, CallingConvention = CallingConvention.Cdecl)]
|
||||
public static extern IntPtr piper_version();
|
||||
}
|
||||
@@ -0,0 +1,21 @@
|
||||
<Project Sdk="Microsoft.NET.Sdk">
|
||||
|
||||
<ItemGroup>
|
||||
<ProjectReference Include="..\Robovoice.Core\Robovoice.Core.csproj" />
|
||||
</ItemGroup>
|
||||
|
||||
<PropertyGroup>
|
||||
<TargetFramework>net10.0</TargetFramework>
|
||||
<ImplicitUsings>enable</ImplicitUsings>
|
||||
<Nullable>enable</Nullable>
|
||||
<PlatformTarget>x64</PlatformTarget>
|
||||
</PropertyGroup>
|
||||
|
||||
<ItemGroup>
|
||||
<None Include="runtimes\win-x64\native\piper.dll" CopyToOutputDirectory="PreserveNewest" Link="piper.dll" />
|
||||
<None Include="runtimes\win-x64\native\onnxruntime.dll" CopyToOutputDirectory="PreserveNewest" Link="onnxruntime.dll" />
|
||||
<None Include="runtimes\win-x64\native\onnxruntime_providers_shared.dll" CopyToOutputDirectory="PreserveNewest" Link="onnxruntime_providers_shared.dll" />
|
||||
<None Include="runtimes\win-x64\native\espeak-ng-data\**\*" CopyToOutputDirectory="PreserveNewest" Link="espeak-ng-data\%(RecursiveDir)%(Filename)%(Extension)" />
|
||||
</ItemGroup>
|
||||
|
||||
</Project>
|
||||
Reference in New Issue
Block a user