Gemini-Powered Voice Assistant with ESP32 and Microphone Input

1#include <WiFi.h>
2#include <HTTPClient.h>
3#include <ArduinoJson.h>
4#include <Wire.h>
5#include <Adafruit_GFX.h>
6#include <Adafruit_SSD1306.h>
7
8// OLED config
9#define SCREEN_WIDTH 128
10#define SCREEN_HEIGHT 64
11#define OLED_RESET    -1
12#define I2C_SDA 21
13#define I2C_SCL 22
14Adafruit_SSD1306 display(SCREEN_WIDTH, SCREEN_HEIGHT, &Wire, OLED_RESET);
15
16// WiFi
17const char* ssid = "your wifi id";
18const char* password = "your wifi password";
19const String gemini_api_key = "your api key";
20
21// MAX9814 microphone input pin
22#define MIC_PIN 34
23
24void setup() {
25  Serial.begin(115200);
26  delay(1000);
27
28  Wire.begin(I2C_SDA, I2C_SCL);
29  if (!display.begin(SSD1306_SWITCHCAPVCC, 0x3C)) {
30    Serial.println("OLED init failed!");
31    while (1);
32  }
33
34  displayMessage("Connecting WiFi...");
35  WiFi.begin(ssid, password);
36  while (WiFi.status() != WL_CONNECTED) {
37    delay(500);
38    Serial.print(".");
39  }
40
41  displayMessage("WiFi connected!");
42  pinMode(MIC_PIN, INPUT);
43  delay(500);
44  displayMessage("Ready! Speak loud...");
45}
46
47void loop() {
48  static unsigned long lastTrigger = 0;
49
50  int micValue = analogRead(MIC_PIN);
51  Serial.println(micValue);
52
53  if (micValue > 1500 && millis() - lastTrigger > 5000) {
54    lastTrigger = millis();
55
56    displayMessage("Detecting...");
57
58    String response = askGemini("who are you.");
59    displayMultilineText(response);
60  }
61
62  delay(100);
63}
64
65void displayMessage(String msg) {
66  display.clearDisplay();
67  display.setTextSize(1);
68  display.setTextColor(SSD1306_WHITE);
69  display.setCursor(0, 0);
70  display.println(msg);
71  display.display();
72}
73
74void displayMultilineText(String text) {
75  display.clearDisplay();
76  display.setTextSize(1);
77  display.setTextColor(SSD1306_WHITE);
78  display.setCursor(0, 0);
79
80  int maxCharsPerLine = 21;
81  int lineHeight = 10;
82  int y = 0;
83
84  while (text.length() > 0 && y < SCREEN_HEIGHT) {
85    String line = text.substring(0, maxCharsPerLine);
86    text = text.substring(min((unsigned int)maxCharsPerLine, text.length()));
87    display.setCursor(0, y);
88    display.println(line);
89    y += lineHeight;
90  }
91
92  display.display();
93}
94
95// Gemini API call
96String askGemini(String prompt) {
97  HTTPClient http;
98  String endpoint = "https://generativelanguage.googleapis.com/v1/models/gemini-1.5-flash-002:generateContent?key=" + gemini_api_key;
99  http.begin(endpoint);
100  http.addHeader("Content-Type", "application/json");
101
102  prompt.replace("\"", "\\\"");
103
104  String requestBody = "{ \"contents\": [ { \"parts\": [ { \"text\": \"" + prompt + "\" } ] } ] }";
105  int code = http.POST(requestBody);
106  String reply = "";
107
108  if (code == 200) {
109    String payload = http.getString();
110    StaticJsonDocument<2048> doc;
111    DeserializationError error = deserializeJson(doc, payload);
112
113    if (!error) {
114      reply = doc["candidates"][0]["content"]["parts"][0]["text"].as<String>();
115      reply.replace("\\n", "\n");
116    } else {
117      Serial.println("JSON Error: " + String(error.c_str()));
118      reply = "I am Gemini, your AI assistant.";
119    }
120  } else {
121    Serial.println("Gemini API error: " + String(code));
122    // Fallback reply when API fails
123    reply = "I am Gemini, your AI assistant.";
124  }
125
126  http.end();
127  return reply;
128}