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

feat(audio): channel sample_rate caps Opus bandwidth (narrowband/wideband)
Some checks failed
Build Linux Binaries / linux/amd64 (push) Has been cancelled
Details
Build Linux Binaries / linux/arm64 (push) Has been cancelled
Details

Browse Source 
The per-channel sample_rate field was inert after pinning the codec to
48 kHz. Make it meaningful without changing the 48 kHz clock: carry it as
OpusParams::max_bandwidth_hz and apply OPUS_SET_MAX_BANDWIDTH in
OpusEncoder::init (8000->narrowband, 16000->wideband, 24000->super-wideband,
48000->full). A low-bitrate room can now shed out-of-band content while
every endpoint keeps a single 48 kHz clock.

Make sample_rate channel-authoritative on the server: conn_session no
longer overrides effective sample_rate with the client's always-48000
request (it now behaves like frame_ms/mode). vc_get_stream_audio_config
reports the channel's configured rate for own streams too.

New ctest channel_samplerate: a 7 kHz tone is attenuated ~1000x on an
8 kHz (narrowband) channel vs a 48 kHz (full-band) channel, proving the cap
is in effect. ctest --preset dev 26/26.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Talon
2026-06-22 16:56:49 +02:00
parent a460009a2f
commit e155e342f4
9 changed files with 379 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/CMakeLists.txt
View File

@@ -211,4 +211,13 @@ if(VOICECAT_USE_VCPKG_DEPS)
target_include_directories(test_frame_ms_reframe PRIVATE ${VC_TEST_INTERNAL_INCLUDES})
add_test(NAME frame_ms_reframe COMMAND test_frame_ms_reframe)
set_tests_properties(frame_ms_reframe PROPERTIES TIMEOUT 90)
# Per-channel sample_rate as an Opus bandwidth cap (OPUS_SET_MAX_BANDWIDTH): a 7 kHz tone is
# attenuated on an 8 kHz (narrowband) channel vs a 48 kHz (full-band) channel.
add_executable(test_channel_samplerate test_channel_samplerate.cpp)
target_link_libraries(test_channel_samplerate PRIVATE voicecat::server)
target_compile_features(test_channel_samplerate PRIVATE cxx_std_20)
target_include_directories(test_channel_samplerate PRIVATE ${VC_TEST_INTERNAL_INCLUDES})
add_test(NAME channel_samplerate COMMAND test_channel_samplerate)
set_tests_properties(channel_samplerate PROPERTIES TIMEOUT 90)
endif()

316
tests/test_channel_samplerate.cpp Normal file
View File

@@ -0,0 +1,316 @@
/*
* test_channel_samplerate — per-channel sample_rate as an Opus bandwidth cap.
*
* The codec always runs at 48 kHz internally (docs/voice.md §3); a channel's sample_rate is
* carried as OPUS_SET_MAX_BANDWIDTH so a low-bitrate / narrowband room can constrain the encoded
* audio bandwidth without changing the PCM clock. This verifies the cap is actually in effect:
*
* - A channel at sample_rate = 8000 (NARROWBAND, ~4 kHz audio) and a channel at 48000
* (FULLBAND) are each fed an identical 7 kHz tone (well above the narrowband edge).
* - The narrowband channel's decoded energy must be substantially lower — the only difference
* between the two runs is the channel's sample_rate, so a lower energy proves the bandwidth
* cap filtered the out-of-band tone.
* - vc_get_stream_audio_config reports the channel's configured sample_rate (not 48000).
*/
#include <cstdio>
#ifdef VOICECAT_HAS_NET
#include <atomic>
#include <chrono>
#include <cmath>
#include <condition_variable>
#include <cstring>
#include <filesystem>
#include <mutex>
#include <string>
#include <thread>
#include <vector>
#include "voicecat.h"
#include "server.h"
#include "db.h"
static int g_failures = 0;
#define CHECK(cond) \
do { if (!(cond)) { \
std::printf("FAIL [%s:%d]: %s\n", __FILE__, __LINE__, #cond); \
++g_failures; \
}} while (0)
struct EventStore {
std::mutex mu;
std::condition_variable cv;
bool auth_ok{false};
uint32_t self_user_id{0};
bool channel_list_received{false};
bool generic_result_received{false};
bool generic_ok{false};
std::vector<std::pair<uint32_t, uint32_t>> streams_started; // (user_id, stream_id)
vc_client* client{nullptr};
const char* label{nullptr};
};
static void on_event(void* user, const vc_event* ev) {
auto* s = static_cast<EventStore*>(user);
std::lock_guard lk(s->mu);
switch (ev->type) {
case VC_EVENT_SERVER_IDENTITY: vc_confirm_server_identity(s->client, 1); break;
case VC_EVENT_AUTH_RESULT:
s->auth_ok = (ev->result == VC_OK);
s->self_user_id = ev->user_id;
break;
case VC_EVENT_CHANNEL_LIST: s->channel_list_received = true; break;
case VC_EVENT_GENERIC_RESULT:
s->generic_result_received = true;
s->generic_ok = (ev->result == VC_OK);
break;
case VC_EVENT_STREAM_STARTED: s->streams_started.emplace_back(ev->user_id, ev->stream_id); break;
default: break;
}
s->cv.notify_all();
}
template <typename Pred>
static bool wait_for(EventStore& s, Pred pred, int timeout_ms) {
auto deadline = std::chrono::steady_clock::now() + std::chrono::milliseconds(timeout_ms);
std::unique_lock lk(s.mu);
return s.cv.wait_until(lk, deadline, [&] { return pred(s); });
}
static bool connect_guest(vc_client*& client, const char* name, const char* label,
uint16_t port, EventStore& ev) {
vc_callbacks cb{on_event, nullptr, &ev};
vc_config cfg{label, "0.1", VC_LOG_OFF};
client = vc_client_create(&cfg, cb);
if (!client) return false;
ev.client = client;
ev.label = label;
if (vc_connect(client, "127.0.0.1", port) != VC_OK) return false;
if (vc_authenticate_guest(client, name) != VC_OK) return false;
if (!wait_for(ev, [](EventStore& s) { return s.auth_ok; }, 8000)) return false;
if (!wait_for(ev, [](EventStore& s) { return s.channel_list_received; }, 3000)) return false;
return true;
}
// 7 kHz tone — above the NARROWBAND (~4 kHz) edge, within FULLBAND.
static std::vector<int16_t> make_tone(int n, float hz) {
std::vector<int16_t> pcm(static_cast<size_t>(n));
for (int i = 0; i < n; ++i) {
float t = static_cast<float>(i) / 48000.0f;
pcm[i] = static_cast<int16_t>(std::sin(2.0f * 3.14159265f * hz * t) * 16000.0f);
}
return pcm;
}
struct SinkData {
std::mutex mu;
std::condition_variable cv;
std::atomic<int> call_count{0};
int64_t total_energy = 0;
};
static void pcm_sink(void* user, uint32_t, uint32_t,
const int16_t* pcm, size_t n, uint32_t channels, uint32_t) {
auto* d = static_cast<SinkData*>(user);
std::lock_guard lk(d->mu);
for (size_t i = 0; i < n * channels; ++i)
d->total_energy += std::abs(static_cast<int>(pcm[i]));
d->call_count.fetch_add(1, std::memory_order_relaxed);
d->cv.notify_all();
}
static bool sink_wait(SinkData& d, int timeout_ms) {
auto deadline = std::chrono::steady_clock::now() + std::chrono::milliseconds(timeout_ms);
std::unique_lock lk(d.mu);
return d.cv.wait_until(lk, deadline, [&] { return d.call_count.load() > 0; });
}
static uint32_t make_channel(vc_client* admin, EventStore& evAdmin, const char* name,
uint32_t sample_rate) {
vc_channel_info ch{};
ch.name = name;
ch.audio.codec = 0; // OPUS
ch.audio.mode = 0; // mono
ch.audio.sample_rate = sample_rate;
ch.audio.bitrate_bps = 32000;
ch.audio.frame_ms = 20;
ch.audio.fec = 1;
ch.audio.complexity = 10;
{ std::lock_guard lk(evAdmin.mu); evAdmin.generic_result_received = false; }
if (vc_create_channel(admin, &ch) != VC_OK) return 0;
if (!wait_for(evAdmin, [](EventStore& s) { return s.generic_result_received; }, 5000)) return 0;
{ std::lock_guard lk(evAdmin.mu); if (!evAdmin.generic_ok) return 0; }
vc_channel_list cl{};
if (vc_list_channels(admin, &cl) != VC_OK) return 0;
uint32_t id = 0;
for (size_t i = 0; i < cl.count; ++i)
if (cl.items[i].name && std::string(cl.items[i].name) == name) { id = cl.items[i].id; break; }
vc_free_channel_list(&cl);
return id;
}
// Feed a 7 kHz tone through `channel_id` and return the decoded energy the sink observed.
// Also asserts vc_get_stream_audio_config reports `expect_sr`.
static int64_t run_case(uint16_t port, vc_client* admin, EventStore& evAdmin,
uint32_t channel_id, uint32_t expect_sr, const char* tag) {
EventStore evA, evB;
vc_client *clientA = nullptr, *clientB = nullptr;
CHECK(connect_guest(clientA, "SrA", "sr-a", port, evA));
CHECK(connect_guest(clientB, "SrB", "sr-b", port, evB));
int64_t energy = -1;
if (!clientA || !clientB) goto cleanup;
{
uint32_t a_uid = 0, b_uid = 0;
{ std::lock_guard lk(evA.mu); a_uid = evA.self_user_id; }
{ std::lock_guard lk(evB.mu); b_uid = evB.self_user_id; }
CHECK(vc_move_user(admin, a_uid, channel_id) == VC_OK);
CHECK(vc_move_user(admin, b_uid, channel_id) == VC_OK);
std::this_thread::sleep_for(std::chrono::milliseconds(500));
SinkData sink;
CHECK(vc_set_pcm_sink(clientB, pcm_sink, &sink) == VC_OK);
vc_stream_desc desc{};
desc.kind = VC_STREAM_MIC;
uint32_t a_sid = 0;
CHECK(vc_stream_start(clientA, &desc, &a_sid) == VC_OK);
bool b_saw_a = wait_for(evB, [&](EventStore& s) {
for (auto& [uid, sid] : s.streams_started)
if (uid == a_uid) return true;
return false;
}, 5000);
CHECK(b_saw_a);
std::this_thread::sleep_for(std::chrono::milliseconds(400));
vc_audio_config ac{};
CHECK(vc_get_stream_audio_config(clientA, a_uid, a_sid, &ac) == VC_OK);
CHECK(ac.sample_rate == expect_sr);
auto tone = make_tone(960, 7000.0f);
for (int i = 0; i < 300; ++i)
CHECK(vc_stream_feed_pcm(clientA, a_sid, tone.data(), 960, 1) == VC_OK);
CHECK(sink_wait(sink, 5000));
std::this_thread::sleep_for(std::chrono::milliseconds(1500));
energy = sink.total_energy;
std::printf("test_channel_samplerate[%s]: sr=%u calls=%d energy=%lld\n",
tag, expect_sr, sink.call_count.load(), static_cast<long long>(energy));
CHECK(sink.call_count.load() > 0);
vc_stream_stop(clientA, a_sid);
}
cleanup:
if (clientA) { vc_disconnect(clientA); vc_client_destroy(clientA); }
if (clientB) { vc_disconnect(clientB); vc_client_destroy(clientB); }
return energy;
}
int main() {
auto tmp = std::filesystem::temp_directory_path() /
("vctest_chansr_" + std::to_string(
std::chrono::steady_clock::now().time_since_epoch().count()));
std::filesystem::create_directories(tmp);
std::string data_dir = tmp.string();
{
voicecat::server::Database db(data_dir + "/voicecat.db");
std::string err;
if (!db.open(err) || !db.create_account("admin", "pass", true, err)) {
std::printf("FAIL: provision admin: %s\n", err.c_str());
std::filesystem::remove_all(tmp);
return 1;
}
}
std::atomic<uint16_t> bound_port{0};
std::mutex ready_mu;
std::condition_variable ready_cv;
bool ready{false};
voicecat::server::Config cfg;
cfg.data_dir = data_dir;
cfg.bind_port = 0;
cfg.media_port = 0;
cfg.server_name = "VoiceCat-ChanSrTest";
cfg.allow_guests = true;
cfg.on_ready = [&](uint16_t p) {
bound_port.store(p);
{ std::lock_guard lk(ready_mu); ready = true; }
ready_cv.notify_all();
};
voicecat::server::Server server(cfg);
std::thread server_thread([&] { server.run(); });
{
std::unique_lock lk(ready_mu);
if (!ready_cv.wait_for(lk, std::chrono::seconds(10), [&] { return ready; })) {
std::printf("FAIL: server did not start\n");
server.stop(); server_thread.join();
std::filesystem::remove_all(tmp);
return 1;
}
}
uint16_t port = bound_port.load();
std::printf("channel_samplerate: server ready on :%u\n", port);
EventStore evAdmin;
evAdmin.label = "admin";
vc_callbacks cbAdmin{on_event, nullptr, &evAdmin};
vc_config cfgAdmin{"chansr-admin", "0.1", VC_LOG_OFF};
vc_client* admin = vc_client_create(&cfgAdmin, cbAdmin);
CHECK(admin != nullptr);
evAdmin.client = admin;
CHECK(vc_connect(admin, "127.0.0.1", port) == VC_OK);
CHECK(vc_authenticate_user(admin, "admin", "pass") == VC_OK);
CHECK(wait_for(evAdmin, [](EventStore& s) { return s.auth_ok; }, 8000));
CHECK(wait_for(evAdmin, [](EventStore& s) { return s.channel_list_received; }, 3000));
uint32_t ch_full = make_channel(admin, evAdmin, "FullBand", 48000);
uint32_t ch_narrow = make_channel(admin, evAdmin, "NarrowBand", 8000);
CHECK(ch_full != 0);
CHECK(ch_narrow != 0);
int64_t full_energy = (ch_full ? run_case(port, admin, evAdmin, ch_full, 48000, "full") : -1);
int64_t narrow_energy = (ch_narrow ? run_case(port, admin, evAdmin, ch_narrow, 8000, "narrow") : -1);
// The 7 kHz tone is above the narrowband (~4 kHz) cutoff: the narrowband channel must filter
// most of it out, so its decoded energy is far below the full-band channel's. Generous margin
// (< 50%) to stay robust across Opus versions while still proving the cap is in effect.
CHECK(full_energy > 0);
CHECK(narrow_energy >= 0);
std::printf("channel_samplerate: full=%lld narrow=%lld ratio=%.3f\n",
static_cast<long long>(full_energy), static_cast<long long>(narrow_energy),
full_energy > 0 ? static_cast<double>(narrow_energy) / static_cast<double>(full_energy)
: 0.0);
CHECK(narrow_energy < full_energy / 2);
vc_disconnect(admin);
vc_client_destroy(admin);
server.stop();
server_thread.join();
std::filesystem::remove_all(tmp);
if (g_failures == 0) {
std::printf("channel_samplerate: all checks passed\n");
return 0;
}
std::printf("channel_samplerate: %d failure(s)\n", g_failures);
return 1;
}
#else // !VOICECAT_HAS_NET
int main() {
std::printf("channel_samplerate: SKIP (VOICECAT_HAS_NET not defined)\n");
return 0;
}
#endif // VOICECAT_HAS_NET