Files
ESP32_ZACUS/box3_voice/main/main.c
T
clement 43dc1478b1
CI / platformio (pull_request) Failing after 3m44s
CI / platformio (push) Failing after 3m34s
box3: fix gamebook audio, accents, and crashes
The BOX-3 touch gamebook had several blocking bugs that made the
voiced+foley story packs unusable. This fixes them end to end.

- Stack overflow on story start: gb_play_task kept a 2 KB buffer on
  its 4 KB stack and rebooted the board. Buffers are now static (the
  task is a singleton) and the stack is 6 KB.
- No sound at all: the ES8311 codec was never initialised — main.c
  wrote raw I2S to a muted DAC. Output (and the mic) now go through
  the BSP esp_codec_dev (bsp_audio_codec_speaker/microphone_init,
  esp_codec_dev_write/read). The power amplifier (GPIO46) is also
  forced on and volume set to 100, as the es8311 pa_pin handling did
  not drive it in practice.
- First passage silent: gb_play re-mounted the SD that the gamebook
  had already mounted; the failed second bsp_sdcard_mount tore down
  the VFS so the first fopen failed. Now we open the file first and
  only mount if that fails. A short silence lead-in also primes the
  codec/PA ramp.
- No accents: the gamebook used ASCII-only lv_font_montserrat_14/24.
  Added custom Montserrat fonts (font_fr_14/24, Latin-1 + œŒŸ « » ’ …,
  uncompressed so they render without LV_USE_FONT_COMPRESSED).
- Mic/voice streaming gated behind CONFIG_BOX3_VOICE_STREAMING
  (default off): as a gamebook the BOX-3 needs no mic, and the
  constant codec reads + bridge reconnects interfered with playback
  and flooded the log.

plip_virtual + cmd_exec handle types switched from i2s_chan_handle_t
to esp_codec_dev_handle_t accordingly.
2026-06-21 11:07:34 +02:00

532 lines
20 KiB
C

/*
* Zacus BOX-3 Voice — ESP-IDF Application Entry Point
*
* ESP32-S3-BOX-3 voice pipeline for "Le Mystere du Professeur Zacus"
* escape room game. Handles wake-word detection, voice capture,
* WebSocket streaming to the mascarade voice bridge, and speaker output.
*/
#include <stdio.h>
#include <string.h>
#include <math.h>
#include "freertos/FreeRTOS.h"
#include "freertos/task.h"
#include "esp_log.h"
#include "esp_err.h"
#include "esp_system.h"
#include "esp_wifi.h"
#include "esp_event.h"
#include "nvs_flash.h"
#include "driver/i2s_std.h"
#include "driver/gpio.h"
#include "board_config.h"
#include "voice_ws_client.h"
#include "scenario_server.h"
#include "plip_virtual.h"
#include "plip_ui.h"
#include "gamebook.h"
#include "stimulus.h"
#include "scenario_mesh.h"
#include "cmd_exec.h"
/* BSP header — provided by espressif/esp-box component */
#include "bsp/esp-bsp.h"
static const char *TAG = "zacus-voice";
/* --------------- Shared state --------------- */
/* Audio now goes through the ES8311 (speaker) / ES7210 (mic) codecs via the
* BSP + esp_codec_dev. bsp_audio_init() owns the single shared I2S port; we
* must NOT create our own raw I2S channels (that left the ES8311 DAC unpowered
* and the speaker silent). */
static esp_codec_dev_handle_t s_spk_codec = NULL; /* ES8311 output (DAC) */
static esp_codec_dev_handle_t s_mic_codec = NULL; /* ES7210 input (ADC) */
static volatile bool s_wifi_connected = false;
static volatile bool s_voice_streaming = false;
/* --------------- Forward declarations --------------- */
static esp_err_t wifi_init_sta(void);
static void audio_test_tone(void);
static void mic_monitor_task(void *arg);
static void tts_audio_callback(const uint8_t *data, size_t len);
/* --------------- WiFi event handler --------------- */
static void wifi_event_handler(void *arg, esp_event_base_t event_base,
int32_t event_id, void *event_data)
{
if (event_base == WIFI_EVENT && event_id == WIFI_EVENT_STA_START) {
esp_wifi_connect();
} else if (event_base == WIFI_EVENT && event_id == WIFI_EVENT_STA_DISCONNECTED) {
ESP_LOGW(TAG, "WiFi disconnected, retrying...");
vTaskDelay(pdMS_TO_TICKS(2000));
esp_wifi_connect();
} else if (event_base == IP_EVENT && event_id == IP_EVENT_STA_GOT_IP) {
ip_event_got_ip_t *event = (ip_event_got_ip_t *)event_data;
ESP_LOGI(TAG, "Connected — IP: " IPSTR, IP2STR(&event->ip_info.ip));
s_wifi_connected = true;
}
}
/* --------------- WiFi station init --------------- */
static esp_err_t wifi_init_sta(void)
{
ESP_ERROR_CHECK(esp_netif_init());
ESP_ERROR_CHECK(esp_event_loop_create_default());
esp_netif_create_default_wifi_sta();
wifi_init_config_t cfg = WIFI_INIT_CONFIG_DEFAULT();
ESP_ERROR_CHECK(esp_wifi_init(&cfg));
ESP_ERROR_CHECK(esp_event_handler_instance_register(
WIFI_EVENT, ESP_EVENT_ANY_ID, &wifi_event_handler, NULL, NULL));
ESP_ERROR_CHECK(esp_event_handler_instance_register(
IP_EVENT, IP_EVENT_STA_GOT_IP, &wifi_event_handler, NULL, NULL));
wifi_config_t wifi_config = {
.sta = {
.ssid = CONFIG_ZACUS_WIFI_SSID,
.password = CONFIG_ZACUS_WIFI_PASSWORD,
.threshold.authmode = WIFI_AUTH_WPA2_PSK,
.channel = CONFIG_ZACUS_WIFI_CHANNEL, /* co-channel master for ESP-NOW relay (0 = auto) */
},
};
/* Allow open networks if no password configured */
if (strlen(CONFIG_ZACUS_WIFI_PASSWORD) == 0) {
wifi_config.sta.threshold.authmode = WIFI_AUTH_OPEN;
}
ESP_ERROR_CHECK(esp_wifi_set_mode(WIFI_MODE_STA));
ESP_ERROR_CHECK(esp_wifi_set_config(WIFI_IF_STA, &wifi_config));
ESP_ERROR_CHECK(esp_wifi_start());
ESP_LOGI(TAG, "WiFi STA started, connecting to '%s'...", CONFIG_ZACUS_WIFI_SSID);
return ESP_OK;
}
/* --------------- Test tone (440 Hz sine) --------------- */
// Play a single tone on the speaker (blocking). Public so the stimulus
// generator can sequence a melody for the master's microphone.
void audio_play_tone(float frequency, int duration_ms)
{
if (!s_spk_codec || duration_ms <= 0) return;
const int total_samples = AUDIO_SAMPLE_RATE * duration_ms / 1000;
const float amplitude = 16000.0f;
int16_t buffer[256];
int sample_idx = 0;
while (sample_idx < total_samples) {
int chunk = (total_samples - sample_idx < 256)
? (total_samples - sample_idx) : 256;
for (int i = 0; i < chunk; i++) {
float t = (float)(sample_idx + i) / (float)AUDIO_SAMPLE_RATE;
buffer[i] = (int16_t)(amplitude * sinf(2.0f * M_PI * frequency * t));
}
esp_codec_dev_write(s_spk_codec, buffer, chunk * sizeof(int16_t));
sample_idx += chunk;
}
}
static void audio_test_tone(void)
{
if (!s_spk_codec) {
ESP_LOGW(TAG, "Speaker not initialized, skipping test tone");
return;
}
ESP_LOGI(TAG, "Playing 440 Hz test tone (1 second)...");
/* Generate 1 second of 440 Hz sine wave through the ES8311 codec */
const int duration_ms = 1000;
const int total_samples = AUDIO_SAMPLE_RATE * duration_ms / 1000;
const float frequency = 440.0f;
const float amplitude = 16000.0f;
int16_t buffer[256];
int sample_idx = 0;
while (sample_idx < total_samples) {
int chunk = (total_samples - sample_idx < 256) ? (total_samples - sample_idx) : 256;
for (int i = 0; i < chunk; i++) {
float t = (float)(sample_idx + i) / (float)AUDIO_SAMPLE_RATE;
buffer[i] = (int16_t)(amplitude * sinf(2.0f * M_PI * frequency * t));
}
esp_codec_dev_write(s_spk_codec, buffer, chunk * sizeof(int16_t));
sample_idx += chunk;
}
vTaskDelay(pdMS_TO_TICKS(100)); /* Let buffer drain */
ESP_LOGI(TAG, "Test tone complete");
}
/* --------------- TTS audio callback --------------- */
static void tts_audio_callback(const uint8_t *data, size_t len)
{
/*
* Called from WebSocket event context with incoming TTS PCM16 data.
* Write directly to the speaker I2S channel.
*/
if (!s_spk_codec || len == 0) {
return;
}
int ret = esp_codec_dev_write(s_spk_codec, (void *)data, (int)len);
if (ret != ESP_CODEC_DEV_OK) {
ESP_LOGW(TAG, "TTS write to speaker failed: %d", ret);
}
}
/* --------------- Speaker init --------------- */
static esp_err_t speaker_init(void)
{
/* Init the ES8311 output codec via the BSP. This also runs bsp_audio_init()
* (shared duplex I2S port) + bsp_i2c_init() and configures the power
* amplifier (BSP_POWER_AMP_IO = GPIO46). The ES8311 DAC is configured over
* I2C here — without this the speaker stays muted no matter what we push on
* I2S. */
s_spk_codec = bsp_audio_codec_speaker_init();
if (!s_spk_codec) {
ESP_LOGE(TAG, "bsp_audio_codec_speaker_init failed — speaker unavailable");
return ESP_FAIL;
}
/* All speaker audio in this app is 16 kHz / 16-bit / mono PCM. */
esp_codec_dev_sample_info_t fs = {
.bits_per_sample = AUDIO_BITS,
.channel = AUDIO_CHANNELS,
.channel_mask = 0,
.sample_rate = AUDIO_SAMPLE_RATE,
.mclk_multiple = 0,
};
int ret = esp_codec_dev_open(s_spk_codec, &fs);
if (ret != ESP_CODEC_DEV_OK) {
ESP_LOGE(TAG, "esp_codec_dev_open (speaker) failed: %d", ret);
return ESP_FAIL;
}
/* Output volume 0..100. */
esp_codec_dev_set_out_vol(s_spk_codec, 100);
/* Belt-and-suspenders: the es8311 driver is configured with pa_pin=GPIO46
* (pa_reverted=false) and should raise it on open, but the speaker stays
* silent in practice — force the power amplifier on explicitly. */
gpio_set_direction(BOX3_PA_ENABLE, GPIO_MODE_OUTPUT);
gpio_set_level(BOX3_PA_ENABLE, 1);
ESP_LOGI(TAG, "Speaker codec (ES8311) initialized @ %d Hz, vol=100, PA on",
AUDIO_SAMPLE_RATE);
return ESP_OK;
}
/* --------------- Microphone task --------------- */
static void mic_monitor_task(void *arg)
{
ESP_LOGI(TAG, "Starting mic capture task...");
/* Init the ES7210 input codec via the BSP. It shares the same I2S port
* (already created by speaker_init -> bsp_audio_init); creating a separate
* raw I2S channel here would conflict with that shared port. */
s_mic_codec = bsp_audio_codec_microphone_init();
if (!s_mic_codec) {
ESP_LOGE(TAG, "bsp_audio_codec_microphone_init failed — mic unavailable");
vTaskDelete(NULL);
return;
}
esp_codec_dev_sample_info_t fs = {
.bits_per_sample = AUDIO_BITS,
.channel = AUDIO_CHANNELS,
.channel_mask = 0,
.sample_rate = AUDIO_SAMPLE_RATE,
.mclk_multiple = 0,
};
int oret = esp_codec_dev_open(s_mic_codec, &fs);
if (oret != ESP_CODEC_DEV_OK) {
ESP_LOGE(TAG, "esp_codec_dev_open (mic) failed: %d", oret);
vTaskDelete(NULL);
return;
}
/* ES7210 input gain (dB). 30 dB is a sane default for the BOX-3 mic array. */
esp_codec_dev_set_in_gain(s_mic_codec, 30.0f);
int16_t buffer[AUDIO_FRAME_SAMPLES];
int rms_log_counter = 0;
while (1) {
int ret = esp_codec_dev_read(s_mic_codec, buffer,
AUDIO_FRAME_SAMPLES * sizeof(int16_t));
if (ret != ESP_CODEC_DEV_OK) {
ESP_LOGW(TAG, "Mic read error: %d", ret);
vTaskDelay(pdMS_TO_TICKS(20));
continue;
}
int samples = AUDIO_FRAME_SAMPLES;
/* If voice streaming is active, send PCM to bridge */
if (s_voice_streaming) {
voice_state_t st = voice_ws_get_state();
if (st == VOICE_STATE_LISTENING || st == VOICE_STATE_READY) {
voice_ws_send_audio(buffer, samples);
}
}
/* Log RMS periodically (every ~500ms = 25 frames at 20ms) */
rms_log_counter++;
if (rms_log_counter >= 25) {
rms_log_counter = 0;
double sum_sq = 0.0;
for (int i = 0; i < samples; i++) {
sum_sq += (double)buffer[i] * (double)buffer[i];
}
double rms = sqrt(sum_sq / samples);
float db = 20.0f * log10f((float)rms + 1.0f);
ESP_LOGI(TAG, "Mic RMS: %.1f (~%.1f dB) streaming=%s",
rms, db, s_voice_streaming ? "yes" : "no");
}
}
}
/* --------------- Voice bridge connection task --------------- */
static void voice_bridge_task(void *arg)
{
/* Wait for WiFi to be connected */
while (!s_wifi_connected) {
vTaskDelay(pdMS_TO_TICKS(500));
}
ESP_LOGI(TAG, "WiFi connected — initializing voice bridge...");
/* Small delay for network stack to settle */
vTaskDelay(pdMS_TO_TICKS(1000));
esp_err_t ret = voice_ws_init();
if (ret != ESP_OK) {
ESP_LOGE(TAG, "Voice WS init failed: %s", esp_err_to_name(ret));
vTaskDelete(NULL);
return;
}
/* Set TTS audio callback to play through speaker */
voice_ws_set_audio_callback(tts_audio_callback);
ret = voice_ws_connect();
if (ret == ESP_OK) {
ESP_LOGI(TAG, "Voice bridge connected and ready!");
/* Enable streaming — for now always on (wake-word stub).
* TODO: Gate this behind actual wake-word detection from ESP-SR.
* For prototype: use BOX-3 BOOT button (GPIO0) to toggle streaming. */
s_voice_streaming = true;
ESP_LOGI(TAG, "Voice streaming enabled (continuous mode)");
} else if (ret == ESP_ERR_TIMEOUT) {
ESP_LOGW(TAG, "Bridge handshake timed out — will keep retrying via reconnect");
/* Streaming will be enabled when hello_ack arrives */
s_voice_streaming = true;
} else {
ESP_LOGE(TAG, "Voice bridge connection failed: %s", esp_err_to_name(ret));
}
vTaskDelete(NULL);
}
/* --------------- Button handler (BOOT button = GPIO0) --------------- */
static void button_task(void *arg)
{
/* Use BOOT button (GPIO0) to toggle voice streaming on/off.
* This is a wake-word placeholder — press to start/stop listening.
*/
gpio_set_direction(GPIO_NUM_0, GPIO_MODE_INPUT);
gpio_set_pull_mode(GPIO_NUM_0, GPIO_PULLUP_ONLY);
bool last_state = true; /* Pull-up: idle = high */
while (1) {
bool current = gpio_get_level(GPIO_NUM_0);
/* Detect falling edge (button press) */
if (last_state && !current) {
/* Virtual PLIP hook first: while ringing or off-hook the BOOT
* button is the hook switch (pickup/hangup), not the streaming
* toggle. */
if (plip_virtual_button_press()) {
vTaskDelay(pdMS_TO_TICKS(300));
last_state = current;
continue;
}
s_voice_streaming = !s_voice_streaming;
ESP_LOGI(TAG, "BOOT button pressed — streaming %s",
s_voice_streaming ? "ON" : "OFF");
if (!s_voice_streaming) {
voice_ws_send_listen_stop();
}
/* Simple debounce */
vTaskDelay(pdMS_TO_TICKS(300));
}
last_state = current;
vTaskDelay(pdMS_TO_TICKS(50));
}
}
/* --------------- ESP-NOW CMD text callback --------------- */
// Called from the scenario_mesh text worker task for every CMD/EVT frame
// received via ESP-NOW. On the BOX-3 we only care about CMD (master→us).
static void on_mesh_text(uint8_t kind, const uint8_t src_mac[6], const char *text)
{
if (kind == SCENARIO_MESH_TEXT_CMD) {
ESP_LOGI(TAG, "ESP-NOW CMD from %02x:%02x:%02x:%02x:%02x:%02x: %.80s",
src_mac[0], src_mac[1], src_mac[2],
src_mac[3], src_mac[4], src_mac[5], text);
esp_err_t err = cmd_exec_handle(text, strlen(text));
if (err != ESP_OK && err != ESP_ERR_NOT_SUPPORTED) {
ESP_LOGW(TAG, "cmd_exec_handle: %s", esp_err_to_name(err));
}
} else {
// EVT arriving at the BOX-3 (unusual — master echoing back).
ESP_LOGI(TAG, "ESP-NOW EVT from %02x:%02x:%02x:%02x:%02x:%02x: %.80s",
src_mac[0], src_mac[1], src_mac[2],
src_mac[3], src_mac[4], src_mac[5], text);
}
}
/* --------------- Application entry point --------------- */
void app_main(void)
{
ESP_LOGI(TAG, "============================================");
ESP_LOGI(TAG, " Zacus BOX-3 Voice Pipeline");
ESP_LOGI(TAG, " Board: ESP32-S3-BOX-3");
ESP_LOGI(TAG, " IDF: %s", esp_get_idf_version());
ESP_LOGI(TAG, " Free heap: %lu bytes", esp_get_free_heap_size());
ESP_LOGI(TAG, "============================================");
/* Initialize NVS (required for WiFi) */
esp_err_t ret = nvs_flash_init();
if (ret == ESP_ERR_NVS_NO_FREE_PAGES || ret == ESP_ERR_NVS_NEW_VERSION_FOUND) {
ESP_ERROR_CHECK(nvs_flash_erase());
ret = nvs_flash_init();
}
ESP_ERROR_CHECK(ret);
/* Initialize BSP (display, codec, buttons) */
ESP_LOGI(TAG, "Initializing BSP...");
bsp_display_start();
ESP_LOGI(TAG, "Display initialized (%dx%d)", BOX3_LCD_WIDTH, BOX3_LCD_HEIGHT);
/* Initialize persistent speaker output (used for test tone + TTS playback) */
speaker_init();
/* Pass speaker codec handle to CMD executor for real WAV playback */
cmd_exec_set_spk_handle(s_spk_codec);
/* Play test tone to verify audio output */
audio_test_tone();
#if CONFIG_BOX3_VOICE_STREAMING
/* Start mic capture task (reads I2S mic, streams to bridge when active).
* Off by default: as a touch gamebook the BOX-3 needs no mic, and the
* continuous codec reads + bridge reconnects interfered with the speaker
* (the first narration clip came out silent) and spammed the log. */
xTaskCreatePinnedToCore(mic_monitor_task, "mic_capture", 4096, NULL, 5, NULL, 1);
#endif
/* Start button handler (BOOT button toggles voice streaming) */
xTaskCreate(button_task, "button", 2048, NULL, 4, NULL);
/* Connect to WiFi */
ESP_LOGI(TAG, "Connecting to WiFi...");
wifi_init_sta();
#if CONFIG_BOX3_VOICE_STREAMING
/* Start voice bridge connection task (waits for WiFi, then connects WS) */
xTaskCreate(voice_bridge_task, "voice_bridge", 6144, NULL, 5, NULL);
#endif
/* Start the scenario hot-load HTTP server (POST /game/scenario).
* httpd_start binds to all netifs — works as soon as the WiFi STA has an IP. */
if (scenario_server_start() != ESP_OK) {
ESP_LOGW(TAG, "scenario_server_start failed — IR hot-load unavailable");
} else {
/* Phone-less PLIP annex: same REST contract as PLIP_FIRMWARE
* (POST /ring /stop /play, GET /status), ring on the speaker,
* BOOT button as the virtual hook switch. */
if (plip_virtual_init(scenario_server_handle(), s_spk_codec) != ESP_OK) {
ESP_LOGW(TAG, "plip_virtual_init failed — virtual phone unavailable");
} else if (plip_ui_init() != ESP_OK) {
/* REST/ESP-NOW phone still works headless if the UI fails. */
ESP_LOGW(TAG, "plip_ui_init failed — on-screen phone unavailable");
}
/* Stimulus generator: BOX-3 shows QR / plays melody for the Freenove
* master's camera + mic (POST /stim/qr, POST /stim/melody). */
if (stimulus_init() == ESP_OK) {
stimulus_register_routes(scenario_server_handle());
} else {
ESP_LOGW(TAG, "stimulus_init failed — QR/melody generator off");
}
/* Touch gamebook: if a story pack is on the SD (/sdcard/gamebook/),
* take over the screen with a tap-to-choose "livre dont tu es le
* héros". No-op (and the phone UI stays) when no pack is present. */
gamebook_init();
}
/* Start the ESP-NOW receiver so the master can relay scenarios to us even
* when WiFi is unreachable (battery / RF-noise fallback per the spec). The
* reassembled IR is funnelled through the exact same scenario_apply_buffer()
* path the HTTP handler uses. esp_wifi_start() already ran in
* wifi_init_sta(), so esp_now_init() inside has its prerequisite. */
esp_err_t mesh_err = scenario_mesh_init(scenario_apply_buffer);
if (mesh_err != ESP_OK) {
ESP_LOGW(TAG, "scenario_mesh_init failed: %s — ESP-NOW IR relay unavailable",
esp_err_to_name(mesh_err));
} else {
ESP_LOGI(TAG, "ESP-NOW scenario receiver active");
/* Register CMD text callback so the master can drive screen / audio / leds
* via POST /game/espnow/cmd {peer, command:<json>} (D5 contract). */
esp_err_t tcb_err = scenario_mesh_set_text_cb(on_mesh_text);
if (tcb_err != ESP_OK) {
ESP_LOGW(TAG, "scenario_mesh_set_text_cb: %s — CMD executor unavailable",
esp_err_to_name(tcb_err));
} else {
ESP_LOGI(TAG, "ESP-NOW CMD executor registered (op: screen/play/evt/led)");
}
}
/* TODO: Initialize ESP-SR WakeNet for wake-word detection
* - Load WakeNet9 model ("hi esp" or custom)
* - Feed audio frames from mic to WakeNet
* - On wake-word detection, set s_voice_streaming = true
* - Replace BOOT button toggle with wake-word trigger
*/
/* TODO: Game logic integration
* - Subscribe to game state events (puzzle solved, time updates)
* - Display status on ILI9341 (puzzle progress, timer)
* - LED ring feedback for voice activity
*/
/* TODO: OTA update support
* - Check for firmware updates on boot
* - Use ota_0 partition for rollback safety
*/
ESP_LOGI(TAG, "Initialization complete. Press BOOT button to toggle voice streaming.");
}