Files
Talon 2baefddbe4 feat(windows): system-wide push-to-talk via Raw Input
PTT was focus-scoped (WinForms KeyDown/KeyUp) so it died the moment the
window lost focus. Add an optional system-wide path using the Raw Input
API (RegisterRawInputDevices + WM_INPUT with RIDEV_INPUTSINK) instead of
a WH_KEYBOARD_LL low-level hook -- the latter is the keylogger pattern AV
heuristics flag, which is worse for our unsigned MinGW binary. Raw Input
involves no DLL injection or global hook and passes keys through.

- New VoiceCat.App/Native/RawInput.cs: P/Invoke + structs; register the
  keyboard sink, decode WM_INPUT to vkey/up-down, GetAsyncKeyState helper.
- MainForm overrides OnHandleCreated/OnHandleDestroyed/WndProc to manage
  the sink and route WM_INPUT to PTT; gates the focus-scoped KeyDown/KeyUp
  off when system-wide is on; makes the Deactivate force-release
  conditional; adds a GetAsyncKeyState watchdog on the pump timer so a
  missed key-up (RDP/lock-screen) cannot leave PTT stuck.
- VoiceSettings.SystemWidePtt (default ON) + system-wide checkbox in the
  Audio settings PTT section.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-24 13:14:01 +02:00

89 lines
4.3 KiB
C#
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

using System.Text.Json;
namespace VoiceCat.App.Models;
/// <summary>
/// User's send-side voice input preferences — transmission mode, VAD sensitivity, mic input
/// gain, and the push-to-talk key. Persisted to %AppData%\VoiceCat\voice.json, same pattern as
/// <see cref="ServerListStore"/> and FeedbackSettings: a missing or corrupt file yields defaults
/// rather than throwing. Slider-position values are stored as-is so MainForm can restore the
/// TrackBars directly.
/// </summary>
public sealed class VoiceSettings
{
/// <summary>Transmission mode: 0 = voice activation, 1 = push-to-talk, 2 = always on
/// (matches Interop's VcInputMode).</summary>
public int InputMode { get; set; } = 0;
/// <summary>VAD sensitivity slider position, 1100 (default mirrors the designer's 76).</summary>
public int VadThresholdSlider { get; set; } = 76;
/// <summary>Microphone input gain slider position, 0400 percent (100 = unity).</summary>
public int MicGain { get; set; } = 100;
/// <summary>Send-side mic noise reduction (RNNoise) toggle. MIC stream only, mono only;
/// denoises captured mic PCM before input gain and VAD/PTT gate so everyone hears the
/// cleaned signal. Independent of the per-listener receive-side NR.</summary>
public bool MicNoiseReduction { get; set; } = false;
/// <summary>Capture the mic in stereo (interleaved L/R) instead of mono. Off by default. Real
/// stereo only reaches the wire on a stereo channel; on a mono channel the core folds the mic
/// to mono. Applied when the capture device next starts (Join Voice or an audio restart).</summary>
public bool StereoMic { get; set; } = false;
/// <summary>Push-to-talk key, stored as the integer value of System.Windows.Forms.Keys.</summary>
public int PttKey { get; set; } = (int)Keys.F8;
/// <summary>Make push-to-talk work system-wide — i.e. while another app is focused. When on,
/// MainForm registers a background Raw Input keyboard device (WM_INPUT + RIDEV_INPUTSINK) so the
/// PTT key is observed even when VoiceCat is not in the foreground; when off, PTT is focus-scoped
/// (only fires while the VoiceCat window has focus). Raw Input is used instead of a low-level
/// keyboard hook to avoid antivirus keylogger heuristics.</summary>
public bool SystemWidePtt { get; set; } = true;
/// <summary>Saved device ID from the last session; null means use the system default.</summary>
public string? InputDeviceId { get; set; } = null;
/// <summary>Whether the secondary "aux" outgoing stream is enabled. The aux stream is a
/// second hardware input device the client captures itself and feeds to the core via
/// vc_stream_feed_pcm (kind = AUX_DEVICE, external_feed). Lets a user transmit e.g. mic +
/// a line-in at once.</summary>
public bool AuxEnabled { get; set; } = false;
/// <summary>WASAPI endpoint id of the aux capture device; null = system default capture
/// device. NOTE: this is a WASAPI device id (from <see cref="Audio.InputDeviceEnumerator"/>),
/// NOT a core/miniaudio id — the aux device is opened client-side, so the two id spaces differ.</summary>
public string? AuxDeviceId { get; set; } = null;
/// <summary>Aux input volume slider position, 0400 percent (100 = unity). Applied client-side
/// to the captured PCM before feeding (the core's input gain is mic-only and global).</summary>
public int AuxGain { get; set; } = 100;
private static readonly JsonSerializerOptions JsonOptions = new() { WriteIndented = true };
private static string AppDataDir => Path.Combine(
Environment.GetFolderPath(Environment.SpecialFolder.ApplicationData), "VoiceCat");
private static string FilePath => Path.Combine(AppDataDir, "voice.json");
public static VoiceSettings Load()
{
try
{
if (!File.Exists(FilePath)) return new VoiceSettings();
string json = File.ReadAllText(FilePath);
return JsonSerializer.Deserialize<VoiceSettings>(json) ?? new VoiceSettings();
}
catch
{
return new VoiceSettings();
}
}
public void Save()
{
Directory.CreateDirectory(AppDataDir);
File.WriteAllText(FilePath, JsonSerializer.Serialize(this, JsonOptions));
}
}