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

fix(audio): stereo screen-audio loopback capture on Windows

Browse Source 
start_loopback_capture hardcoded channels=1, forcing miniaudio to downmix the system's stereo mix to mono before the encoder saw it -- on_capture_frame then upmixed L=R to produce fake stereo. Now the loopback device opens in the channel's mode (stereo when the channel is stereo), CaptureCallback carries an explicit channels param so the encoder gets real interleaved L/R, and a mono fallback covers unusual render endpoints. New test_loopback_stereo_capture asserts L!=R end-to-end; 18/18 ctest green.
This commit is contained in:
Talon
2026-06-17 23:27:59 +02:00
parent a88656f2fa
commit cccf085a87
7 changed files with 258 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

89
tests/test_vad_ptt_devices.cpp
View File

@@ -230,6 +230,90 @@ static void test_stereo_mix() {
std::printf("test_stereo_mix: ok (total_diff=%lld)\n", static_cast<long long>(total_diff));
}
// ── 4a-2. Stereo screen-audio loopback capture (white-box, no audio hardware needed) ──
// Regression for the mono-loopback bug: start_loopback_capture used to hardcode channels=1,
// downmixing the system's stereo mix to mono before the encoder ever saw it (and on_capture_frame
// then upmixed L=R to produce a fake-stereo bitstream). Now the loopback device opens in the
// channel's mode (stereo when the channel is stereo), so the encoder receives real interleaved
// L/R PCM and encodes it directly. This test drives feed_loopback_for_test with a loud-L /
// silent-R stereo signal, encodes it (as on_capture_frame now does for channels==2), decodes,
// and mixes — asserting L != R across the frame. A mono-downmixed-then-upmixed bitstream would
// have L == R. Mirrors test_stereo_mix but routes the encode side through the loopback
// accumulator path that the fix touches (feed_loopback_for_test → on_loopback's accumulator).
#if defined(VOICECAT_HAS_LOOPBACK) && defined(VOICECAT_HAS_OPUS)
static void test_loopback_stereo_capture() {
voicecat::audio::AudioEngine engine;
voicecat::audio::AudioParams p;
p.sample_rate = 48000;
p.capture_channels = 1; // mic path — irrelevant here; loopback has its own channel count
p.playback_channels = 2; // stereo mix output (for mix_for_test below)
p.frame_ms = 20;
CHECK(engine.start(p)); // no capture_cb — the real mic (if any) won't touch capture_accum_
voicecat::codec::OpusParams stereo_params;
stereo_params.stereo = true;
stereo_params.application = voicecat::codec::OpusApplication::Audio; // screen-audio channel
stereo_params.bitrate_bps = 128000; // music/screen-audio channel default
int frame_samples = voicecat::codec::opus_frame_samples(stereo_params);
voicecat::codec::OpusEncoder enc;
CHECK(enc.init(stereo_params));
// Loud left channel, silent right — a real mono downmix would average them into a single
// audible-but-quieter centered sample; true stereo keeps them distinct.
std::vector<int16_t> interleaved(static_cast<size_t>(frame_samples) * 2);
for (int i = 0; i < frame_samples; ++i) {
float t = static_cast<float>(i) / 48000.0f;
interleaved[i * 2] = static_cast<int16_t>(std::sin(2.0f * 3.14159265f * 440.0f * t) * 20000.0f);
interleaved[i * 2 + 1] = 0;
}
// Encode via the loopback accumulator path: feed_loopback_for_test drives on_loopback's
// accumulator and invokes the callback with channels=2 (the fix). The callback encodes
// exactly as on_capture_frame does for real-stereo SCREEN_AUDIO PCM — no upmix.
uint8_t opus_buf[1500];
int opus_len = 0;
int seen_channels = 0;
auto cb = [&](int /*kind*/, const int16_t* pcm, int /*samples*/, int channels) {
seen_channels = channels;
if (channels == 2) {
// The loopback accumulator must have preserved L/R distinctness pre-encode.
int64_t pre_diff = 0;
for (int i = 0; i < frame_samples; ++i)
pre_diff += std::abs(static_cast<int>(pcm[i * 2]) - static_cast<int>(pcm[i * 2 + 1]));
CHECK(pre_diff > static_cast<int64_t>(frame_samples) * 1000);
}
opus_len = enc.encode(pcm, frame_samples, opus_buf, sizeof(opus_buf));
};
engine.feed_loopback_for_test(interleaved.data(), frame_samples, 2, cb);
CHECK(seen_channels == 2); // the loopback path reported stereo, not downmixed mono
CHECK(opus_len > 0);
// Decode + mix — same recv path as test_stereo_mix. A real stereo bitstream should
// survive with L != R; a mono-downmixed-then-upmixed bitstream would have L == R.
engine.init_recv_stream(/*ssrc=*/3, stereo_params);
voicecat::audio::JitterBuffer::Frame f;
f.seq = 0;
f.timestamp = 0;
f.fec_present = false;
f.payload.assign(opus_buf, opus_buf + opus_len);
engine.push_recv_frame(3, std::move(f));
std::vector<int16_t> out(static_cast<size_t>(frame_samples) * 2, 0);
engine.mix_for_test(out.data(), static_cast<uint32_t>(frame_samples));
int64_t total_diff = 0;
for (int i = 0; i < frame_samples; ++i)
total_diff += std::abs(static_cast<int>(out[i * 2]) - static_cast<int>(out[i * 2 + 1]));
CHECK(total_diff > static_cast<int64_t>(frame_samples) * 1000);
engine.remove_stream(3);
engine.stop();
std::printf("test_loopback_stereo_capture: ok (total_diff=%lld, seen_channels=%d)\n",
static_cast<long long>(total_diff), seen_channels);
}
#endif
// ── 4b. Playout-clock re-sync after a late join / silence gap ────────────────────
// Regression for the "talk indicator lit, no audio" bug: the playout clock free-runs (it
// advances every callback via PLC), while the sender's frame timestamps only advance while it
@@ -316,7 +400,7 @@ static void test_capture_frame_accumulation() {
// and drives the same accumulator directly with the explicit `cb` below — no races.
CHECK(engine.start(p));
auto cb = [&](int /*kind*/, const int16_t* /*pcm*/, int samples) {
auto cb = [&](int /*kind*/, const int16_t* /*pcm*/, int samples, int /*channels*/) {
++call_count;
if (samples != kExpected) wrong_size.store(true);
};
@@ -501,6 +585,9 @@ int main() {
test_device_enumeration();
#if defined(VOICECAT_HAS_AUDIO) && defined(VOICECAT_HAS_OPUS)
test_stereo_mix();
#if defined(VOICECAT_HAS_LOOPBACK)
test_loopback_stereo_capture();
#endif
test_playout_resync();
#endif
#ifdef VOICECAT_HAS_AUDIO