How to Build an ESP32 Bluetooth Speaker

#include <Arduino.h>
#include "BluetoothA2DPSink.h"
#include <Wire.h>
#include <Adafruit_GFX.h>
#include <Adafruit_SSD1306.h>
#include <math.h>

// ── Pins ──────────────────────────────────────────────────────────────────────
#define I2S_BCK_PIN  26
#define I2S_LCK_PIN  25
#define I2S_DIN_PIN  22
#define XSMT_PIN     27
#define OLED_SDA_PIN 21
#define OLED_SCL_PIN 23

// ── OLED ──────────────────────────────────────────────────────────────────────
#define SCREEN_WIDTH  128
#define SCREEN_HEIGHT  64
#define OLED_ADDR     0x3C

// ── Visualizer ────────────────────────────────────────────────────────────────
#define NUM_BARS      16
#define BAR_MAX_H     16
#define BUF_SAMPLES   512

// ── Globals ───────────────────────────────────────────────────────────────────
void audio_data_callback(const uint8_t *data, uint32_t len);
void connection_state_changed(esp_a2d_connection_state_t state, void *ptr);
void audio_state_changed(esp_a2d_audio_state_t state, void *ptr);
void drawCuteSmiley(int cx, int cy, int r, bool excited);
void drawArms(int cx, int cy, int r, float e, uint32_t t, int move);
void updateBars();
void drawVisualizer();
void displayTask(void *param);

static int16_t           audioBuf[BUF_SAMPLES];
static volatile uint16_t audioBufLen = 0;
static SemaphoreHandle_t bufMutex;

static float    bars[NUM_BARS];
static volatile float energy     = 0.0f;
static volatile float energyFast = 0.0f;
static volatile bool  isStreaming = false;

// Beat detection for triggering dance moves
static volatile float  beatAvg   = 0.0f;
static volatile bool   beatHit   = false;

Adafruit_SSD1306  display(SCREEN_WIDTH, SCREEN_HEIGHT, &Wire, -1);
BluetoothA2DPSink a2dp_sink;

// ── Audio tap — read-only post-processing hook.
//    with_post_call=true means the library STILL writes the data to I2S itself,
//    we only get a copy. This does NOT replace/disable the I2S output path. ──────
void audio_data_callback(const uint8_t *data, uint32_t len) {
    const int16_t *src = (const int16_t *)data;
    uint32_t stereo    = len / 4;
    uint32_t n         = stereo < BUF_SAMPLES ? stereo : BUF_SAMPLES;

    float sum = 0;
    for (uint32_t i = 0; i < n; i++) {
        float s = (((int32_t)src[i*2] + src[i*2+1]) / 2.0f) / 32768.0f;
        sum += s * s;
    }
    float rms = (n > 0) ? sqrtf(sum / n) : 0.0f;
    // Perceptual (sqrt) curve + higher gain: quiet passages get boosted much
    // more than loud ones, so the animation reacts well at low volume without
    // the loud parts clipping flat at 1.0.
    float e   = fminf(sqrtf(rms * 22.0f), 1.0f);

    // Instant attack, quick decay — strong beat response
    energyFast = (e > energyFast) ? e : energyFast * 0.82f;
    energy     = energy * 0.7f + e * 0.3f;

    // Simple beat detector: flag when energy spikes above a slow running average.
    // Slower average (0.98) makes transient kicks stand out; lower threshold and
    // floor so even quiet music reliably triggers move changes.
    beatAvg = beatAvg * 0.98f + e * 0.02f;
    if (e > beatAvg * 1.22f && e > 0.06f) beatHit = true;

    if (xSemaphoreTake(bufMutex, 0) == pdTRUE) {
        for (uint32_t i = 0; i < n; i++)
            audioBuf[i] = (int16_t)(((int32_t)src[i*2] + src[i*2+1]) >> 1);
        audioBufLen = (uint16_t)n;
        xSemaphoreGive(bufMutex);
    }
}

// ── BT callbacks ──────────────────────────────────────────────────────────────
void connection_state_changed(esp_a2d_connection_state_t state, void *ptr) {
    Serial.println(state == ESP_A2D_CONNECTION_STATE_CONNECTED
        ? "[BT] Connected" : "[BT] Disconnected");
}

void audio_state_changed(esp_a2d_audio_state_t state, void *ptr) {
    if (state == ESP_A2D_AUDIO_STATE_STARTED) {
        isStreaming = true;
        digitalWrite(XSMT_PIN, HIGH);
        Serial.println("[BT] Streaming started");
    } else {
        isStreaming = false;
        digitalWrite(XSMT_PIN, LOW);
        Serial.println("[BT] Streaming stopped");
        for (int i = 0; i < NUM_BARS; i++) bars[i] = 0;
        energy = 0; energyFast = 0;
    }
}

// ── Cute happy smiley ────────────────────────────────────────────────────────
//   Big round head, large shiny eyes, rosy cheeks, real upward grin.
void drawCuteSmiley(int cx, int cy, int r, bool excited) {
    // Head — double-stroke for a bold look
    display.drawCircle(cx, cy, r,     SSD1306_WHITE);
    display.drawCircle(cx, cy, r - 1, SSD1306_WHITE);

    int eo = r / 3 + 2;          // eye spacing
    int ey = cy - r / 5;         // eyes in upper half
    int er = max(r / 4, 3);      // eye radius

    if (excited) {
        // Happy "^ ^" closed eyes on a strong beat — curve opens DOWN (cute squint)
        for (int dx = -er; dx <= er; dx++) {
            int dy = (int)(sqrtf((float)(er*er - dx*dx)) * 0.7f);
            display.drawPixel(cx - eo + dx, ey + dy, SSD1306_WHITE);
            display.drawPixel(cx - eo + dx, ey + dy - 1, SSD1306_WHITE);
            display.drawPixel(cx + eo + dx, ey + dy, SSD1306_WHITE);
            display.drawPixel(cx + eo + dx, ey + dy - 1, SSD1306_WHITE);
        }
    } else {
        // Big shiny round eyes
        display.fillCircle(cx - eo, ey, er, SSD1306_WHITE);
        display.fillCircle(cx + eo, ey, er, SSD1306_WHITE);
        display.fillCircle(cx - eo + 1, ey - 1, 1, SSD1306_BLACK); // shine
        display.fillCircle(cx + eo + 1, ey - 1, 1, SSD1306_BLACK);
    }

    // Rosy cheeks
    int ck  = r * 3 / 4;
    int cky = cy + r / 5;
    display.drawCircle(cx - ck, cky, 2, SSD1306_WHITE);
    display.drawCircle(cx + ck, cky, 2, SSD1306_WHITE);

    // ── Upward grin ── on screen +Y is DOWN, so a smile dips in the MIDDLE
    int mw    = r * 3 / 5;            // mouth half-width
    int my    = cy + r / 5;           // mouth corners baseline
    int depth = excited ? (r * 3 / 5) : (r * 2 / 5);
    for (int dx = -mw; dx <= mw; dx++) {
        float t  = (float)dx / mw;            // -1..1
        int   dy = (int)((1.0f - t * t) * depth);   // center dips DOWN = smile
        display.drawPixel(cx + dx, my + dy,     SSD1306_WHITE);
        display.drawPixel(cx + dx, my + dy + 1, SSD1306_WHITE);
    }
}

// ── Dancing arms — move = current dance move (0 wave, 1 raise-the-roof, 2 sway) ─
void drawArms(int cx, int cy, int r, float e, uint32_t t, int move) {
    int sx = r;
    int sy = cy + r / 3;
    float osc  = sinf((float)t / 220.0f);
    float beat = fminf(e * 26.0f, 22.0f);

    int lx2, ly2, rx2, ry2;
    if (move == 1) {
        // "Raise the roof" — both hands punch straight up on the beat
        int lift = (int)(8 + beat);
        lx2 = cx - sx - 4; ly2 = sy - lift;
        rx2 = cx + sx + 4; ry2 = sy - lift;
    } else if (move == 2) {
        // Side sway — both arms swing the same way, flipping with the oscillator
        int swing = (int)(osc * (10 + beat * 0.5f));
        lx2 = cx - sx - 12 + swing; ly2 = sy + 2;
        rx2 = cx + sx + 12 + swing; ry2 = sy + 2;
    } else {
        // Wave — arms alternate up/down (classic dance)
        lx2 = cx - sx - 12; ly2 = (int)(sy - beat + osc * 5.0f);
        rx2 = cx + sx + 12; ry2 = (int)(sy - beat - osc * 5.0f);
    }

    display.drawLine(cx - sx, sy, lx2, ly2, SSD1306_WHITE);
    display.fillCircle(lx2, ly2, 2, SSD1306_WHITE);
    display.drawLine(cx + sx, sy, rx2, ry2, SSD1306_WHITE);
    display.fillCircle(rx2, ry2, 2, SSD1306_WHITE);
}

// ── Bars ──────────────────────────────────────────────────────────────────────
void updateBars() {
    static int16_t snap[BUF_SAMPLES];
    uint16_t snapLen = 0;
    if (xSemaphoreTake(bufMutex, pdMS_TO_TICKS(4)) == pdTRUE) {
        snapLen = audioBufLen;
        memcpy(snap, audioBuf, snapLen * sizeof(int16_t));
        xSemaphoreGive(bufMutex);
    }
    if (snapLen == 0) return;

    int spb = max(1, (int)snapLen / NUM_BARS);
    for (int b = 0; b < NUM_BARS; b++) {
        int start = b * spb;
        int end   = min(start + spb, (int)snapLen);
        float sum = 0; int cnt = 0;
        for (int i = start; i < end; i++) {
            float s = snap[i] / 32768.0f;
            sum += s * s; cnt++;
        }
        float rms    = (cnt > 0) ? sqrtf(sum / cnt) : 0.0f;
        // Same perceptual sqrt curve as the energy meter so quiet bars still
        // rise to a visible height instead of sitting flat at the bottom.
        float target = fminf(sqrtf(rms * 22.0f), 1.0f);
        bars[b] = (target > bars[b]) ? target : bars[b] * 0.78f;
    }
}

// ── Main draw (core 0) ───────────────────────────────────────────────────────
void drawVisualizer() {
    static int      danceMove   = 0;
    static uint32_t lastSwitch  = 0;

    display.clearDisplay();
    uint32_t now = millis();

    if (!isStreaming) {
        drawCuteSmiley(64, 26, 16, false);
        display.setTextSize(1);
        display.setTextColor(SSD1306_WHITE);
        display.setCursor(16, 52);
        display.print("Waiting for BT...");
        display.display();
        return;
    }

    updateBars();

    // Cycle through the dance moves:
    //  - advance on a detected beat (min 700ms apart so a move is visible), OR
    //  - advance on a 2.5s timeout so it ALWAYS keeps alternating even when the
    //    beat detector is quiet. Each move gets at least one full bar to show.
    bool beat = beatHit;
    beatHit = false;
    if ((beat && now - lastSwitch > 700) || (now - lastSwitch > 2500)) {
        danceMove  = (danceMove + 1) % 3;
        lastSwitch = now;
    }

    float ef  = energyFast;
    bool  exc = ef > 0.35f;                  // big excited face on strong beats
    int   r   = 16 + (int)(ef * 8.0f);       // 16..24 — clearly grows
    int   bcy = 24 - (int)(ef * 6.0f);       // bounces up on beat

    drawArms(64, bcy, r, ef, now, danceMove);
    drawCuteSmiley(64, bcy, r, exc);

    // Full-width spectrum bars across the bottom
    int barW = SCREEN_WIDTH / NUM_BARS;
    for (int b = 0; b < NUM_BARS; b++) {
        int x = b * barW;
        int h = (int)(bars[b] * BAR_MAX_H);
        if (h > 0) display.fillRect(x, SCREEN_HEIGHT - h, barW - 1, h, SSD1306_WHITE);
    }

    display.display();
}

// ── Display task pinned to core 0 (keeps I2C off the BT/I2S core) ────────────
void displayTask(void *param) {
    for (;;) {
        drawVisualizer();
        vTaskDelay(pdMS_TO_TICKS(33));
    }
}

// ── Setup ─────────────────────────────────────────────────────────────────────
void setup() {
    Serial.begin(115200);
    Serial.println("SCHEMATIK SPEAKER starting...");

    pinMode(XSMT_PIN, OUTPUT);
    digitalWrite(XSMT_PIN, LOW);

    // I2C bus recovery before Wire.begin (clears a stuck SSD1306)
    pinMode(OLED_SCL_PIN, OUTPUT);
    pinMode(OLED_SDA_PIN, OUTPUT);
    digitalWrite(OLED_SDA_PIN, HIGH);
    for (int i = 0; i < 9; i++) {
        digitalWrite(OLED_SCL_PIN, HIGH); delayMicroseconds(5);
        digitalWrite(OLED_SCL_PIN, LOW);  delayMicroseconds(5);
    }
    digitalWrite(OLED_SDA_PIN, LOW);
    digitalWrite(OLED_SCL_PIN, HIGH); delayMicroseconds(5);
    digitalWrite(OLED_SDA_PIN, HIGH); delayMicroseconds(5);
    delay(50);

    Wire.begin(OLED_SDA_PIN, OLED_SCL_PIN);
    Wire.setClock(100000);
    if (!display.begin(SSD1306_SWITCHCAPVCC, OLED_ADDR)) {
        Serial.println("[OLED] Init failed — check wiring/address");
    } else {
        display.clearDisplay();
        drawCuteSmiley(64, 26, 16, false);
        display.display();
        Serial.println("[OLED] Ready");
    }

    bufMutex = xSemaphoreCreateMutex();

    // Tell the library which I2S pins to drive (legacy I2S API).
    i2s_pin_config_t pin_config = {
        .bck_io_num   = I2S_BCK_PIN,
        .ws_io_num    = I2S_LCK_PIN,
        .data_out_num = I2S_DIN_PIN,
        .data_in_num  = I2S_PIN_NO_CHANGE
    };
    a2dp_sink.set_pin_config(pin_config);

    a2dp_sink.set_on_connection_state_changed(connection_state_changed);
    a2dp_sink.set_on_audio_state_changed(audio_state_changed);

    // IMPORTANT: register the tap with post_write_callback semantics — the
    // library still installs+writes I2S itself; we only receive a copy.
    a2dp_sink.set_stream_reader(audio_data_callback, true);

    a2dp_sink.start("SCHEMATIK SPEAKER");
    Serial.println("Bluetooth ready — pair with \"SCHEMATIK SPEAKER\"");

    xTaskCreatePinnedToCore(displayTask, "display", 4096, NULL, 1, NULL, 0);
}

void loop() {
    vTaskDelay(pdMS_TO_TICKS(1000));
}

// Run this and build other cool things at schematik.io