mute
8585972a1e
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
66 lines
1.8 KiB
C#
66 lines
1.8 KiB
C#
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();
|
|
}
|