Add 5.1 surround output

The mixer folded the game's 5.1 device sink down to stereo and IAudioDevice told the game it had two channels.
audio_channels (auto, stereo, 5.1; Sound tab, Speakers) now opens the SDL stream with six channels in the device sink's
order (FL FR C LFE RL RR) and reports six to the game, which then mixes for 5.1. auto picks 5.1 when the default
playback device has six or more channels (a 5.1 or 7.1 speaker setup in Windows) and stereo otherwise; stereo keeps
the existing downmix.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

README.md

@@ -25,6 +25,7 @@ Report problems as issues, following [CONTRIBUTING.md](CONTRIBUTING.md).
 - In-game settings menu (F1) and performance overlay (F10)
 - Setup and in-game menu in English, Russian, Brazilian Portuguese and Simplified Chinese
 - Keyboard, mouse and gamepad with remapping, rumble and gyro
+- Stereo or 5.1 surround sound output
 - Xbox button prompts: LB, RB, LT, RT, Menu and View, and A, B, X and Y as labelled on the button to press, with either button layout
 - Shaders prepared at install instead of during play
 - Mods made for emulators: unpack a mod into the `mods` folder next to `totk.exe`; switch and order them in the menu. RomFS

runtime/audio_mixer.c

@@ -5,8 +5,9 @@
 //
 // Per 5 ms frame the render thread (audren.c, renderer lock held) decodes every started voice (PCM8/16/24/32, float,
 // DSP-ADPCM) along the sample path the voice clock consumes, resamples it linearly, runs the voice biquads, scales it
-// into its destination mix, folds the submixes, runs the mix effects and writes the device sink's stereo mix into a
-// single-producer single-consumer ring. The SDL audio thread drains that ring without taking any lock: an empty ring
+// into its destination mix, folds the submixes, runs the mix effects and writes the device sink's mix (stereo, or 5.1
+// with TOTK_AUDIO_CHANNELS, output_channels) into a single-producer single-consumer ring. The SDL audio thread drains
+// that ring without taking any lock: an empty ring
 // plays silence and never blocks the render thread or the guest. TOTK_AUDIO=none (or TOTK_AUDIO_OFF) mixes without a
 // device; TOTK_AUDIO_PREFILL_MS (0..500, default 20) is the queued audio the output waits for after start or underrun.
 // The device's clock paces the render thread, as the audio hardware paces the Switch's DSP (audio_mixer_pace_ns): a
@@ -32,7 +33,8 @@
 #include "ipc.h"
 
 #define MAX_FRAME 1024
-#define RING_FRAMES 16384            // stereo frames, about 340 ms at 48 kHz
+#define RING_FRAMES 16384            // output frames, about 340 ms at 48 kHz
+#define OUT_MAX 6                    // output channels at most: 5.1
 #define QUEUE_SLACK_MS 40            // queued audio above the target plus the device's request that ring_pull skips
 #define STALL_MS 50                  // the device took nothing this long (at least 4 periods): the timer paces
 #define SPLITTER_UNUSED 0xffffffffu
@@ -51,7 +53,8 @@ typedef struct Mixer {
     int *offset;                                   // first mix buffer of each mix id
     SplitInfo *split; int nsplit; SplitDest *dest; int ndest;
     SDL_AudioStream *stream; int device_ok, rate;
-    float ring[RING_FRAMES * 2];
+    int channels;                                  // output channels, 2 or 6 (output_channels)
+    float ring[RING_FRAMES * OUT_MAX];
     _Atomic uint64_t wr, rd, underruns, overruns, missing_frames, callback_frames, callback_nonzero, skipped_frames;
     _Atomic int playing; int ready;                // ready: the callback's own state
     int target, period;                            // output target and device period, frames (output_open)
@@ -61,7 +64,7 @@ typedef struct Mixer {
     EffectState *effect; int *effect_order; unsigned effect_reported;
     uint64_t *sink_address; uint32_t *sink_size, *sink_offset, *sink_old, *sink_written;
     unsigned reported;                             // one-time reports
-    float voice_scratch[6][MAX_FRAME], filter_scratch[MAX_FRAME], output_scratch[MAX_FRAME * 2];
+    float voice_scratch[6][MAX_FRAME], filter_scratch[MAX_FRAME], output_scratch[MAX_FRAME * OUT_MAX];
     double level_sum, level_peak; uint64_t level_count, level_frames; int first_sound_logged;
     int prefill;                                   // render blocks
 } Mixer;
@@ -98,8 +101,32 @@ static int prefill_blocks_for(const char *e) {
     return (int)ceil(ms / 5.0);
 }
 
-// Fills `frames` stereo frames from the ring (zeros for what is missing). Lock-free; runs on SDL's audio thread.
+// TOTK_AUDIO_CHANNELS: the output channels of this run, decided once. stereo gives 2; 5.1 gives 6 (FL FR C LFE RL RR,
+// the device sink's order and SDL's); auto gives 6 when the default playback device has at least six channels (a 5.1
+// or 7.1 speaker setup in Windows; SDL places 5.1 on 7.1) and 2 otherwise. IAudioDevice reports the same count to the
+// game (GetActiveChannelCount), which picks its sink layout from it. TOTK_AUDIO=none: 2, without touching SDL.
+static int output_channels(void) {
+    static _Atomic int decided;
+    int n = atomic_load(&decided);
+    if (n) return n;
+    const char *want = cfg_value("TOTK_AUDIO_CHANNELS"), *mode = cfg_get("TOTK_AUDIO");
+    if ((mode && !strcmp(mode, "none")) || cfg_get("TOTK_AUDIO_OFF")) n = 2;
+    else if (!strcmp(want, "5.1")) n = 6;
+    else if (!strcmp(want, "stereo")) n = 2;
+    else {
+        SDL_AudioSpec dev = {0};
+        n = SDL_InitSubSystem(SDL_INIT_AUDIO) && SDL_GetAudioDeviceFormat(SDL_AUDIO_DEVICE_DEFAULT_PLAYBACK, &dev, NULL) &&
+            dev.channels >= 6 ? 6 : 2;
+        rt_log("audio: TOTK_AUDIO_CHANNELS=auto: the default device has %d channels, output %s", dev.channels,
+               n == 6 ? "5.1" : "stereo");
+    }
+    int expected = 0;
+    return atomic_compare_exchange_strong(&decided, &expected, n) ? n : expected;
+}
+
+// Fills `frames` output frames from the ring (zeros for what is missing). Lock-free; runs on SDL's audio thread.
 static void ring_pull(Mixer *m, float *out, uint32_t frames) {
+    const int oc = m->channels;
     atomic_fetch_add(&m->callback_frames, frames);
     unsigned epoch = atomic_load_explicit(&m->stop_epoch, memory_order_acquire);
     uint64_t rd = atomic_load(&m->rd), wr = atomic_load_explicit(&m->wr, memory_order_acquire), have = wr - rd;
@@ -114,7 +141,7 @@ static void ring_pull(Mixer *m, float *out, uint32_t frames) {
         m->ready = 0;
     }
     if (!atomic_load_explicit(&m->playing, memory_order_acquire)) {
-        memset(out, 0, (size_t)frames * 2 * sizeof(float));
+        memset(out, 0, (size_t)frames * oc * sizeof(float));
         m->ready = 0;
         atomic_store_explicit(&m->rd, wr, memory_order_release);
         return;
@@ -124,7 +151,7 @@ static void ring_pull(Mixer *m, float *out, uint32_t frames) {
     if (prefill > RING_FRAMES) prefill = RING_FRAMES;
     if (!m->ready) {
         if (have < prefill) {
-            memset(out, 0, (size_t)frames * 2 * sizeof(float));
+            memset(out, 0, (size_t)frames * oc * sizeof(float));
             return;
         }
         m->ready = 1;
@@ -140,13 +167,16 @@ static void ring_pull(Mixer *m, float *out, uint32_t frames) {
     uint64_t nonzero = 0;
     for (uint32_t i = 0; i < n; i++) {
         uint64_t k = (rd + i) % RING_FRAMES;
-        out[2 * i] = m->ring[2 * k];
-        out[2 * i + 1] = m->ring[2 * k + 1];
-        if (out[2 * i] != 0 || out[2 * i + 1] != 0) nonzero++;
+        int sound = 0;
+        for (int c = 0; c < oc; c++) {
+            out[oc * i + c] = m->ring[oc * k + c];
+            sound |= out[oc * i + c] != 0;
+        }
+        nonzero += sound;
     }
     atomic_fetch_add(&m->callback_nonzero, nonzero);
     if (n < frames) {
-        memset(out + 2 * n, 0, (size_t)(frames - n) * 2 * sizeof(float));
+        memset(out + (size_t)oc * n, 0, (size_t)(frames - n) * oc * sizeof(float));
         atomic_fetch_add(&m->underruns, 1);
         atomic_fetch_add(&m->missing_frames, frames - n);
         m->ready = 0;
@@ -157,15 +187,16 @@ static void ring_pull(Mixer *m, float *out, uint32_t frames) {
 static void SDLCALL sdl_pull(void *user, SDL_AudioStream *stream, int additional, int total) {
     (void)total;
     Mixer *m = user;
-    float tmp[2 * 1024];
+    float tmp[OUT_MAX * 1024];
+    const uint32_t frame_bytes = (uint32_t)m->channels * sizeof(float);
     atomic_store_explicit(&m->pulled_ns, kern_now_ns(), memory_order_release);
     while (additional > 0) {
-        uint32_t frames = (uint32_t)additional / (2 * sizeof(float));
+        uint32_t frames = (uint32_t)additional / frame_bytes;
         if (!frames) break;
         if (frames > 1024) frames = 1024;
         ring_pull(m, tmp, frames);
-        if (!SDL_PutAudioStreamData(stream, tmp, (int)(frames * 2 * sizeof(float)))) break;
-        additional -= (int)(frames * 2 * sizeof(float));
+        if (!SDL_PutAudioStreamData(stream, tmp, (int)(frames * frame_bytes))) break;
+        additional -= (int)(frames * frame_bytes);
     }
 }
 
@@ -179,7 +210,7 @@ static void output_open(Mixer *m, int rate) {
         rt_log("audio: SDL audio init failed (%s): mixing without sound", SDL_GetError());
         return;
     }
-    SDL_AudioSpec spec = {SDL_AUDIO_F32, 2, rate};
+    SDL_AudioSpec spec = {SDL_AUDIO_F32, m->channels, rate};
     m->stream = SDL_OpenAudioDeviceStream(SDL_AUDIO_DEVICE_DEFAULT_PLAYBACK, &spec, sdl_pull, m);
     if (!m->stream) {
         rt_log("audio: no output device (%s): mixing without sound", SDL_GetError());
@@ -192,7 +223,7 @@ static void output_open(Mixer *m, int rate) {
         return;
     }
     m->device_ok = 1;
-    SDL_AudioSpec dev;
+    SDL_AudioSpec dev = {0};
     int period = 0;
     if (!SDL_GetAudioDeviceFormat(SDL_GetAudioStreamDevice(m->stream), &dev, &period) || period <= 0) period = m->frame;
     m->period = period;
@@ -201,8 +232,9 @@ static void output_open(Mixer *m, int rate) {
     uint64_t period_ns = (uint64_t)period * 1000000000ull / (uint64_t)rate;
     m->stall_ns = 4 * period_ns > STALL_MS * 1000000ull ? 4 * period_ns : STALL_MS * 1000000ull;
     const char *name = SDL_GetAudioDeviceName(SDL_GetAudioStreamDevice(m->stream));
-    rt_log("audio: SDL device '%s' opened, %d Hz stereo float, prefill %d ms, device period %d frames; the device paces "
-           "rendering at %.1f ms queued", name ? name : "?", rate, m->prefill * 5, period, m->target * 1000.0 / rate);
+    rt_log("audio: SDL device '%s' opened, %d Hz %s float (device %d channels), prefill %d ms, device period %d frames; "
+           "the device paces rendering at %.1f ms queued", name ? name : "?", rate, m->channels == 6 ? "5.1" : "stereo",
+           dev.channels, m->prefill * 5, period, m->target * 1000.0 / rate);
 }
 
 int64_t audio_mixer_pace_ns(AudioRenderer *r, uint64_t now) {
@@ -217,7 +249,8 @@ int64_t audio_mixer_pace_ns(AudioRenderer *r, uint64_t now) {
 }
 
 // Render thread only.
-static void output_push(Mixer *m, const float *lr, int frames) {
+static void output_push(Mixer *m, const float *out, int frames) {
+    const int oc = m->channels;
     uint64_t wr = atomic_load(&m->wr), rd = atomic_load_explicit(&m->rd, memory_order_acquire);
     if (m->device_ok && wr + (uint64_t)frames - rd > RING_FRAMES) {   // device stalled: drop this frame
         atomic_fetch_add(&m->overruns, 1);
@@ -225,24 +258,23 @@ static void output_push(Mixer *m, const float *lr, int frames) {
     }
     for (int i = 0; i < frames; i++) {
         uint64_t k = (wr + (uint64_t)i) % RING_FRAMES;
-        m->ring[2 * k] = lr[2 * i];
-        m->ring[2 * k + 1] = lr[2 * i + 1];
+        memcpy(&m->ring[oc * k], &out[oc * i], (size_t)oc * sizeof(float));
     }
     atomic_store_explicit(&m->wr, wr + (uint64_t)frames, memory_order_release);
     if (!m->device_ok) atomic_store(&m->rd, wr + (uint64_t)frames);   // no device: the ring only keeps the latest frames
 }
 
 // Level meter (TOTK_TRACE=audio): one line per 5 s of output, and the first nonzero frame.
-static void level_note(AudioRenderer *r, Mixer *m, const float *lr, int frames) {
+static void level_note(AudioRenderer *r, Mixer *m, const float *out, int frames) {
     if (!(rt_trace & RT_TRACE_AUDIO)) return;
     int sound = 0;
-    for (int k = 0; k < 2 * frames; k++) {
-        double x = lr[k];
+    for (int k = 0; k < m->channels * frames; k++) {
+        double x = out[k];
         m->level_sum += x * x;
         if (fabs(x) > m->level_peak) m->level_peak = fabs(x);
         if (x != 0) sound = 1;
     }
-    m->level_count += 2 * (uint64_t)frames;
+    m->level_count += (uint64_t)m->channels * (uint64_t)frames;
     m->level_frames += (uint64_t)frames;
     if (sound && !m->first_sound_logged) {
         m->first_sound_logged = 1;
@@ -293,6 +325,7 @@ void audio_mixer_open(AudioRenderer *r) {
         rt_log("audio: TOTK_AUDIO_PREFILL_MS=%s is not 0..500 ms: using 20", pe);
         m->prefill = 4;
     }
+    m->channels = output_channels();
     r->mixer = m;
     atomic_store(&m->playing, r->state == 0);
     output_open(m, r->param.sample_rate);
@@ -793,30 +826,39 @@ void audio_mixer_render(AudioRenderer *r, double seconds) {
         if (r->sinks[i].type == SINK_DEVICE && !sink) sink = &r->sinks[i];
         else if (r->sinks[i].type == SINK_CIRCULAR){mix_circular_sink(r,i);circular=1;}
     } else {m->sink_address[i]=0;m->sink_size[i]=m->sink_offset[i]=m->sink_old[i]=m->sink_written[i]=0;}
-    float *lr=m->output_scratch;
-    memset(lr, 0, sizeof(float) * 2 * (size_t)frames);
+    const int oc = m->channels;
+    float *out=m->output_scratch;
+    memset(out, 0, sizeof(float) * (size_t)oc * (size_t)frames);
     if (sink && sink->input_count >= 1 && sink->input_count <= 6) {
+        if (!(m->reported & (1u << 6))) {
+            m->reported |= 1u << 6;
+            rt_log("audio: device sink has %u inputs, output %s", sink->input_count, oc == 6 ? "5.1" : "stereo");
+        }
         const float gain = host_volume() * atomic_load(&device_volume) * (r->mixes[0].in_use ? r->mixes[0].volume : 1.0f);
         const float *ch[6] = {0};
         for (uint32_t c = 0; c < sink->input_count; c++) if (sink->inputs[c] >= 0 && sink->inputs[c] < m->nbuf) ch[c] = mixbuf(m, sink->inputs[c]);
         for (int k = 0; k < frames; k++) {
-            float l, rr;
-            if (sink->input_count >= 6) {   /* FL FR C LFE RL RR -> stereo */
+            float s[OUT_MAX] = {0};   /* FL FR C LFE RL RR */
+            if (sink->input_count >= 6 && oc == 6) {
+                for (int c = 0; c < 6; c++) s[c] = ch[c] ? ch[c][k] : 0;
+            } else if (sink->input_count >= 6) {   /* 5.1 -> stereo; the LFE is left out, as the Switch's downmix does */
                 float ff = sink->downmix_enabled ? sink->downmix[0] : 1.0f, cf = sink->downmix_enabled ? sink->downmix[1] : 0.7071f, sf = sink->downmix_enabled ? sink->downmix[2] : 0.7071f;
                 float C = ch[2] ? ch[2][k] : 0;
-                l = ff * (ch[0] ? ch[0][k] : 0) + cf * C + sf * (ch[4] ? ch[4][k] : 0);
-                rr = ff * (ch[1] ? ch[1][k] : 0) + cf * C + sf * (ch[5] ? ch[5][k] : 0);
-            } else if (sink->input_count >= 2) { l = ch[0] ? ch[0][k] : 0; rr = ch[1] ? ch[1][k] : 0; }
-            else l = rr = ch[0] ? ch[0][k] : 0;
-            l *= gain; rr *= gain;
-            lr[2 * k] = l > 1 ? 1 : l < -1 ? -1 : l; lr[2 * k + 1] = rr > 1 ? 1 : rr < -1 ? -1 : rr;
+                s[0] = ff * (ch[0] ? ch[0][k] : 0) + cf * C + sf * (ch[4] ? ch[4][k] : 0);
+                s[1] = ff * (ch[1] ? ch[1][k] : 0) + cf * C + sf * (ch[5] ? ch[5][k] : 0);
+            } else if (sink->input_count >= 2) { s[0] = ch[0] ? ch[0][k] : 0; s[1] = ch[1] ? ch[1][k] : 0; }
+            else s[0] = s[1] = ch[0] ? ch[0][k] : 0;
+            for (int c = 0; c < oc; c++) {
+                float x = s[c] * gain;
+                out[oc * k + c] = x > 1 ? 1 : x < -1 ? -1 : x;
+            }
         }
     } else if (!sink && !circular) report_once(m, 5, "no device sink in use", r->param.sink_count);
-    level_note(r, m, lr, frames);
-    output_push(m, lr, frames);
+    level_note(r, m, out, frames);
+    output_push(m, out, frames);
 }
 
-// ---- IAudioDevice: one stereo output device
+// ---- IAudioDevice: one output device, stereo or 5.1 (output_channels)
 static const char device_name[] = "AudioTvOutput";
 
 static void put_name(const IpcBuffer *b, IpcResponse *rs, int pointer) {
@@ -855,7 +897,7 @@ void audio_device_handler(IpcSession *s, const IpcRequest *rq, IpcResponse *rs)
         put_name(&b, rs, pointer);
         return;
     }
-    case 5: { int32_t n = 2; IPC_OUT(rs, n); return; }   // GetActiveChannelCount
+    case 5: { int32_t n = output_channels(); IPC_OUT(rs, n); return; }   // GetActiveChannelCount
     case 4: case 11: case 12: {   // QueryAudioDeviceSystemEvent, ...InputEvent, ...OutputEvent
         uint32_t ev = __atomic_load_n(&change_event, __ATOMIC_ACQUIRE);
         if (!ev) {

runtime/cfg.c

@@ -30,7 +30,7 @@ static int save_ok = 1;                         // the last cfg_save_to wrote (o
 // Every name the runtime reads (and the patch sets in generated/), without the prefix. A file key outside this list is
 // logged as unknown. A new variable goes here too, or its ini key logs a harmless "unknown key" line.
 static const char *const known[] = {
-    "AB", "AMIIBO_DIR", "ANISO", "APP_POOL", "ASPECT", "ASPECT_PATCH", "ASSUME_FOCUS", "ASTC", "ASTC_BC", "ASTC_TIME", "ASYNC_PREEMPT", "AUDIO", "AUDIO_OFF", "AUDIO_PREFILL_MS",
+    "AB", "AMIIBO_DIR", "ANISO", "APP_POOL", "ASPECT", "ASPECT_PATCH", "ASSUME_FOCUS", "ASTC", "ASTC_BC", "ASTC_TIME", "ASYNC_PREEMPT", "AUDIO", "AUDIO_CHANNELS", "AUDIO_OFF", "AUDIO_PREFILL_MS",
     "BACKGROUND_WINDOW", "BIND_A", "BIND_B", "BIND_DOWN", "BIND_L", "BIND_LCLICK", "BIND_LEFT", "BIND_LSTICK_DOWN", "BIND_LSTICK_LEFT",
     "BIND_LSTICK_RIGHT", "BIND_LSTICK_UP", "BIND_MINUS",
     "BIND_PLUS", "BIND_R", "BIND_RCLICK", "BIND_RIGHT", "BIND_RSTICK_DOWN", "BIND_RSTICK_LEFT", "BIND_RSTICK_RIGHT", "BIND_RSTICK_UP",
@@ -76,7 +76,7 @@ static const struct { const char *key, *section; } sections[] = {
     {"PCSS", "display"},
     {"MODS_DIR", "mods"}, {"MODS_ORDER", "mods"}, {"MODS_DISABLED", "mods"}, {"MODS_REBUILD", "mods"},
     {"MENU_LANG", "language"}, {"LANG", "language"}, {"OPERATION_MODE", "language"},
-    {"VOLUME", "audio"},
+    {"VOLUME", "audio"}, {"AUDIO_CHANNELS", "audio"},
     {"MOTION", "input"}, {"RUMBLE_STRENGTH", "input"}, {"RUMBLE_CURVE", "input"}, {"RUMBLE_TRIGGERS", "input"},
     {"PAD_LAYOUT", "input"}, {"PROMPTS", "input"}, {"STICK_DEADZONE", "input"}, {"LSTICK_DEADZONE", "input"}, {"RSTICK_DEADZONE", "input"},
     {"STICK_SENS", "input"},
@@ -135,7 +135,7 @@ static const CfgMeta metas[] = {
     {"OPERATION_MODE", "docked", "docked|handheld", RESTART},
     {"ASSUME_FOCUS", "1", "0|1", LIVE},   // read on every focus change (ov_system.c)
     // Sound, Controls, Menu
-    {"VOLUME", "100", "0..100", LIVE},
+    {"VOLUME", "100", "0..100", LIVE}, {"AUDIO_CHANNELS", "auto", "auto|stereo|5.1", RESTART},
     {"MOTION", "1", "0|1", LIVE}, {"RUMBLE_STRENGTH", "130", "0..300", LIVE}, {"RUMBLE_CURVE", "0.6", "0.2..1.5", LIVE},
     {"RUMBLE_TRIGGERS", "0", "0|1", LIVE}, {"PAD_LAYOUT", "auto", "auto|nintendo|xbox", LIVE},
     {"PROMPTS", "nintendo", "nintendo|xbox", RESTART},

runtime/ui/menu.cpp

@@ -697,6 +697,8 @@ static void tab_game(float scale) {
 static void tab_sound(float scale) {
     opt_begin("##sound", scale);
     opt_slider("TOTK_VOLUME", UI_MENU_VOLUME, 0, 100, UI_MENU_VOLUME_DESC, 5, "%.0f %%");
+    static const UiTextId channels[] = {UI_MENU_CHANNELS_AUTO, UI_MENU_CHANNELS_STEREO, UI_MENU_CHANNELS_51};
+    opt_choice("TOTK_AUDIO_CHANNELS", UI_MENU_AUDIO_CHANNELS, channels, 3, UI_MENU_AUDIO_CHANNELS_DESC);
     opt_end();
 }
 

runtime/ui_text.c

@@ -190,6 +190,10 @@ static const char *const text_en[UI_TEXT_COUNT] = {
                                     "at 60 FPS.",
 
     [UI_MENU_VOLUME] = "Volume", [UI_MENU_VOLUME_DESC] = "Master volume of the game.",
+    [UI_MENU_AUDIO_CHANNELS] = "Speakers",
+    [UI_MENU_AUDIO_CHANNELS_DESC] = "Stereo or 5.1 surround output. Automatic picks 5.1 when the Windows speaker setup "
+                                    "has six or more channels. Applies after a restart.",
+    [UI_MENU_CHANNELS_AUTO] = "Automatic", [UI_MENU_CHANNELS_STEREO] = "Stereo", [UI_MENU_CHANNELS_51] = "5.1 surround",
 
     [UI_MENU_MOTION] = "Motion controls", [UI_MENU_MOTION_DESC] = "Aiming with the controller's gyroscope.",
     [UI_MENU_RUMBLE_STRENGTH] = "Vibration strength",
@@ -612,6 +616,10 @@ static const char *const text_ru[UI_TEXT_COUNT] = {
     [UI_MENU_MODS_QUICKMENU_DESC] = "Исправление порта: чёрный фон меню оружия, щитов и материалов при 60 FPS.",
 
     [UI_MENU_VOLUME] = "Громкость", [UI_MENU_VOLUME_DESC] = "Общая громкость игры.",
+    [UI_MENU_AUDIO_CHANNELS] = "Динамики",
+    [UI_MENU_AUDIO_CHANNELS_DESC] = "Стерео или объёмный звук 5.1. Автоматически выбирается 5.1, если в Windows "
+                                    "настроено шесть каналов или больше. Применяется после перезапуска.",
+    [UI_MENU_CHANNELS_AUTO] = "Автоматически", [UI_MENU_CHANNELS_STEREO] = "Стерео", [UI_MENU_CHANNELS_51] = "Объёмный 5.1",
 
     [UI_MENU_MOTION] = "Управление движением", [UI_MENU_MOTION_DESC] = "Прицеливание гироскопом контроллера.",
     [UI_MENU_RUMBLE_STRENGTH] = "Сила вибрации",

runtime/ui_text.h

@@ -88,6 +88,7 @@ typedef enum {
 
     // Sound
     UI_MENU_VOLUME, UI_MENU_VOLUME_DESC,
+    UI_MENU_AUDIO_CHANNELS, UI_MENU_AUDIO_CHANNELS_DESC, UI_MENU_CHANNELS_AUTO, UI_MENU_CHANNELS_STEREO, UI_MENU_CHANNELS_51,
 
     // Controls
     UI_MENU_MOTION, UI_MENU_MOTION_DESC,

totk.ini.example

@@ -218,6 +218,9 @@
 # audio_prefill_ms = 20
 # Volume in percent (0 to 100), on top of the game's own. Changes while the game runs take effect at once.
 # volume = 100
+# Speakers: auto (5.1 when the Windows speaker setup has six or more channels, stereo otherwise), stereo or 5.1. The
+# game is told the same channel count and mixes for it. Takes effect at the next start.
+# audio_channels = auto
 
 [input]
 # Gamepad motion controls (0 = off) and vibration (0 = off).