Talon/voice-cat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(windows): real native exclude + self-echo removal for screen audio

Browse Source 
"All apps except selected" previously captured the complement of a frozen
app snapshot in INCLUDE mode (missed late-launched apps and system sounds,
wasted captures on silent windows). It now opens a single ProcessLoopbackCapture
in EXCLUDE mode (AUDIOCLIENT_PROCESS_LOOPBACK_MODE_EXCLUDE_TARGET_PROCESS_TREE)
of the one chosen app — true system-mix-minus-one, dynamic so apps launched
after sharing starts are included. The picker enforces single-selection in
exclude mode (the activation params take one target PID).

Adds an "Exclude VoiceCat's own audio (prevents echo)" checkbox (default on,
entire-desktop only) that routes the desktop capture through the same EXCLUDE
path targeting our own process id, killing the whole-device self-echo loop.

No C++/ABI changes. Updates voice.md and PROGRESS.md.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Talon
2026-06-22 12:28:53 +02:00
parent fb73b694d0
commit 5e18dfa1c9
6 changed files with 131 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
clients/windows/VoiceCat.App/Audio/AudioSessionEnumerator.cs
View File

@@ -6,7 +6,10 @@ namespace VoiceCat.App.Audio;
// ── Scope types (mirror macOS ScreenAudioScope / ScreenAudioSelection) ────────
public abstract record AppAudioScope;
public sealed record EntireDesktop : AppAudioScope;
// ExcludeSelf=true captures the whole system render mix minus VoiceCat's own process tree
// (kills the self-echo loop). Routed through the external-feed mixer as a single EXCLUDE
// capture; ExcludeSelf=false keeps the core's whole-device loopback path.
public sealed record EntireDesktop(bool ExcludeSelf = false) : AppAudioScope;
public sealed record OnlyApps(IReadOnlyList<int> Pids, IReadOnlyList<string> Names) : AppAudioScope;
public sealed record AllExceptApps(IReadOnlyList<int> Pids, IReadOnlyList<string> Names) : AppAudioScope;

35
clients/windows/VoiceCat.App/Audio/ProcessAudioMixer.cs
View File

@@ -22,15 +22,14 @@ public sealed class ProcessAudioMixer : IDisposable
private VoiceCatClient? _client;
private uint _streamId;
public void Start(AppAudioScope scope, VoiceCatClient client, uint streamId,
IReadOnlyList<AudioAppInfo> allApps)
public void Start(AppAudioScope scope, VoiceCatClient client, uint streamId)
{
if (_running) return;
_client = client;
_streamId = streamId;
var pids = ResolvePids(scope, allApps);
if (pids.Count == 0)
var specs = ResolveCaptures(scope);
if (specs.Count == 0)
{
// nothing to capture — scope resolved to empty set
return;
@@ -38,14 +37,15 @@ public sealed class ProcessAudioMixer : IDisposable
lock (_frameLock)
{
_latestFrames = new List<short[]>(new short[pids.Count][]);
_latestFrames = new List<short[]>(new short[specs.Count][]);
_activeChannels = Channels;
}
for (int i = 0; i < pids.Count; i++)
for (int i = 0; i < specs.Count; i++)
{
int captureIndex = i;
var cap = new ProcessLoopbackCapture(pids[i], ProcessLoopbackCapture.Mode.Include);
var (pid, mode) = specs[i];
var cap = new ProcessLoopbackCapture(pid, mode);
cap.PcmFrameReady += (pcm, spc, ch) => OnCaptureFrame(captureIndex, pcm, ch);
_captures.Add(cap);
}
@@ -117,18 +117,21 @@ public sealed class ProcessAudioMixer : IDisposable
// ── Helpers ───────────────────────────────────────────────────────────────
// For "AllExcept": enumerate all running audio apps and exclude the specified ones.
// For "OnlyApps": use their PIDs directly.
private static List<int> ResolvePids(AppAudioScope scope, IReadOnlyList<AudioAppInfo> allApps)
// Resolve the scope to the WASAPI captures to open:
// OnlyApps → one INCLUDE capture per selected process tree.
// AllExceptApps → one EXCLUDE capture of the single selected process tree, which
// natively captures the whole system render mix minus that tree
// (dynamic — apps launched later are included automatically).
private static List<(int pid, ProcessLoopbackCapture.Mode mode)> ResolveCaptures(AppAudioScope scope)
{
return scope switch
{
OnlyApps o => [.. o.Pids],
AllExceptApps a =>
allApps
.Where(app => !a.Pids.Contains(app.Pid))
.Select(app => app.Pid)
.ToList(),
OnlyApps o => o.Pids.Select(p => (p, ProcessLoopbackCapture.Mode.Include)).ToList(),
AllExceptApps a when a.Pids.Count > 0 =>
[(a.Pids[0], ProcessLoopbackCapture.Mode.Exclude)],
// Entire desktop minus VoiceCat itself: EXCLUDE our own process tree.
EntireDesktop { ExcludeSelf: true } =>
[(Environment.ProcessId, ProcessLoopbackCapture.Mode.Exclude)],
_ => [],
};
}

79
clients/windows/VoiceCat.App/Forms/AppAudioPickerDialog.cs
View File

@@ -12,6 +12,7 @@ public sealed class AppAudioPickerDialog : Form
private readonly RadioButton _rdoAll;
private readonly RadioButton _rdoOnly;
private readonly RadioButton _rdoExcept;
private readonly CheckBox _chkExcludeSelf;
private readonly ListView _appList;
private readonly Label _lblApps;
@@ -50,26 +51,42 @@ public sealed class AppAudioPickerDialog : Form
_rdoOnly.CheckedChanged += OnModeChanged;
_rdoExcept.CheckedChanged += OnModeChanged;
// ── Self-exclude (echo prevention) ───────────────────────────────────
// Captures the whole desktop minus VoiceCat's own playback, so the channel
// doesn't echo back the voices you're already hearing. Only applies to the
// entire-desktop mode (the per-app modes already exclude this app's tree).
_chkExcludeSelf = new CheckBox
{
Text = "E&xclude VoiceCat's own audio (prevents echo)",
Checked = true,
Location = new Point(28, 84),
Size = new Size(344, 20),
TabIndex = 3,
};
// ── App list ────────────────────────────────────────────────────────
_lblApps = new Label
{
Text = "Apps with active audio sessions:",
AutoSize = true,
Location = new Point(12, 90),
Location = new Point(12, 112),
Visible = false,
TabIndex = 3,
TabIndex = 4,
};
_appList = new ListView
{
Location = new Point(12, 112),
Size = new Size(360, 180),
Location = new Point(12, 134),
Size = new Size(360, 158),
CheckBoxes = true,
View = View.List,
Visible = false,
TabIndex = 4,
TabIndex = 5,
FullRowSelect = true,
};
// Exclude mode supports only one target process tree (WASAPI EXCLUDE takes a single
// PID), so enforce a single check while "All apps except selected" is active.
_appList.ItemCheck += OnAppItemCheck;
// ── Buttons ─────────────────────────────────────────────────────────
var btnShare = new Button
@@ -78,7 +95,7 @@ public sealed class AppAudioPickerDialog : Form
DialogResult = DialogResult.OK,
Location = new Point(216, 308),
Size = new Size(75, 27),
TabIndex = 5,
TabIndex = 6,
};
var btnCancel = new Button
{
@@ -86,7 +103,7 @@ public sealed class AppAudioPickerDialog : Form
DialogResult = DialogResult.Cancel,
Location = new Point(297, 308),
Size = new Size(75, 27),
TabIndex = 6,
TabIndex = 7,
};
btnShare.Click += OnShareClick;
@@ -94,7 +111,8 @@ public sealed class AppAudioPickerDialog : Form
CancelButton = btnCancel;
AutoScaleMode = AutoScaleMode.Font;
ClientSize = new Size(384, 348);
Controls.AddRange([_rdoAll, _rdoOnly, _rdoExcept, _lblApps, _appList, btnShare, btnCancel]);
Controls.AddRange([_rdoAll, _rdoOnly, _rdoExcept, _chkExcludeSelf, _lblApps, _appList,
btnShare, btnCancel]);
FormBorderStyle = FormBorderStyle.FixedDialog;
MaximizeBox = false;
MinimizeBox = false;
@@ -121,16 +139,56 @@ public sealed class AppAudioPickerDialog : Form
bool showList = _rdoOnly.Checked || _rdoExcept.Checked;
_lblApps.Visible = showList;
_appList.Visible = showList;
_lblApps.Text = _rdoExcept.Checked
? "App to exclude (everything else is shared):"
: "Apps with active audio sessions:";
// Self-exclude only applies to entire-desktop; the per-app modes already exclude
// this app's own tree (Include) or spend the single EXCLUDE slot on the chosen app.
_chkExcludeSelf.Enabled = _rdoAll.Checked;
if (showList && _appList.Items.Count == 0)
RefreshAppList();
// Switching into exclude mode: collapse any multi-selection down to a single item.
if (_rdoExcept.Checked)
KeepSingleCheck(firstCheckedOnly: true);
}
// In exclude mode the list behaves like radio buttons: checking one item clears the rest.
private bool _suppressItemCheck;
private void OnAppItemCheck(object? sender, ItemCheckEventArgs e)
{
if (_suppressItemCheck || !_rdoExcept.Checked || e.NewValue != CheckState.Checked)
return;
_suppressItemCheck = true;
foreach (ListViewItem item in _appList.Items)
if (item.Index != e.Index && item.Checked)
item.Checked = false;
_suppressItemCheck = false;
}
// Leave at most one item checked (the first), unchecking the rest.
private void KeepSingleCheck(bool firstCheckedOnly)
{
_suppressItemCheck = true;
bool kept = false;
foreach (ListViewItem item in _appList.Items)
{
if (!item.Checked) continue;
if (firstCheckedOnly && !kept) { kept = true; continue; }
item.Checked = false;
}
_suppressItemCheck = false;
}
private void OnShareClick(object? sender, EventArgs e)
{
if (_rdoAll.Checked)
{
ChosenScope = new EntireDesktop();
ChosenScope = new EntireDesktop(_chkExcludeSelf.Checked);
return;
}
@@ -160,7 +218,4 @@ public sealed class AppAudioPickerDialog : Form
? new OnlyApps(checkedPids, checkedNames)
: new AllExceptApps(checkedPids, checkedNames);
}
/// <summary>All apps that were visible in the list when the user clicked Share.</summary>
public IReadOnlyList<AudioAppInfo> VisibleApps => _apps;
}

10
clients/windows/VoiceCat.App/Forms/MainForm.cs
View File

@@ -640,7 +640,7 @@ public partial class MainForm : Form
var scope = picker.ChosenScope;
if (scope is EntireDesktop)
if (scope is EntireDesktop { ExcludeSelf: false })
{
// Existing whole-device WASAPI loopback path — core handles it.
var (result, streamId) = _client.StartStream(VcStreamKind.ScreenAudio, "Desktop audio");
@@ -654,7 +654,8 @@ public partial class MainForm : Form
}
else
{
// Per-app path: suppress core loopback, C# mixer feeds PCM.
// External-feed path: suppress core loopback, C# mixer feeds PCM. Covers the
// per-app modes and "entire desktop except VoiceCat" (single EXCLUDE of self).
var (result, streamId) = _client.StartStreamExternalFeed(VcStreamKind.ScreenAudio, "App audio");
if (result != VcResult.Ok)
{
@@ -664,12 +665,13 @@ public partial class MainForm : Form
_screenStreamId = streamId;
_screenMixer = new ProcessAudioMixer();
_screenMixer.Start(scope, _client, streamId, picker.VisibleApps);
_screenMixer.Start(scope, _client, streamId);
string desc = scope switch
{
EntireDesktop => "entire desktop (excluding VoiceCat)",
OnlyApps o => $"only {o.Pids.Count} app(s)",
AllExceptApps a => $"all except {a.Pids.Count} app(s)",
AllExceptApps a => $"all except {a.Names[0]}",
_ => "apps",
};
AddActivity($"Sharing screen audio: {desc}");