Membuat Asisten Virtual dengan ESP8266 dan Speech Recognition

0 62 2 minutes read

Di era digital saat ini, teknologi Internet of Things (IoT) sudah semakin mudah diakses. Bahkan dengan budget terbatas, kita bisa membuat proyek menarik yang menggabungkan perangkat mikrokontroler dengan teknologi web modern. Pada artikel kali ini, saya akan berbagi pengalaman membuat asisten virtual sederhana menggunakan ESP8266 dan teknologi speech recognition (pengenalan suara) yang berjalan di browser.

Apa yang Bisa Dilakukan Alat Ini?

Proyek ini memungkinkan kita untuk:

Mengenali suara melalui browser smartphone/laptop
Menampilkan teks hasil pengenalan suara ke layar LCD 16×2
Bisa dikembangkan untuk terhubung dengan API AI seperti Groq

Yang menarik, kita tidak perlu modul pengenalan suara khusus karena memanfaatkan kemampuan browser modern yang sudah mendukung Web Speech API.

Komponen yang Dibutuhkan

NodeMCU ESP8266
LCD I2C 16×2
Kabel jumper secukupnya
Koneksi WiFi
Smartphone/laptop dengan browser yang mendukung Web Speech API (Chrome, Edge, Safari)

Rangkaian Hardware

Rangkaian hardware-nya sangat sederhana:

VCC LCD ke 3.3V ESP8266
GND LCD ke GND ESP8266
SDA LCD ke pin D2 (GPIO4) ESP8266
SCL LCD ke pin D1 (GPIO5) ESP8266

Cara Kerja

Sistem ini bekerja dengan prinsip sebagai berikut:

ESP8266 bertindak sebagai web server yang menampilkan halaman HTML dengan fitur speech recognition
Browser mengakses halaman tersebut dan mengaktifkan fitur pengenalan suara
Hasil pengenalan suara dikirim kembali ke ESP8266 melalui HTTP request
ESP8266 menampilkan teks yang diterima ke layar LCD

Yang membuat sistem ini menarik adalah kita memanfaatkan kemampuan browser untuk mengenali suara tanpa perlu menambahkan hardware khusus. Pengenalan suara terjadi di browser, bukan di ESP8266, sehingga kita bisa mengatasi keterbatasan memori dan daya komputasi mikrokontroler.

Kode Program

Berikut adalah kode lengkap untuk proyek ini:

#include <ESP8266WiFi.h>
#include <ESP8266WebServer.h>
#include <WiFiClientSecure.h>
#include <ArduinoJson.h>
#include <LiquidCrystal_I2C.h>
#include <Wire.h>

#define LCD_I2C_ADDR 0x27
#define LCD_COLS 16
#define LCD_ROWS 2
#define SDA_PIN 4  // D2 on NodeMCU
#define SCL_PIN 5  // D1 on NodeMCU

struct Config {
  const char* ssid = "YOUR_WIFI_SSID";
  const char* password = "YOUR_WIFI_PASSWORD";
  const char* openai_api_key = "YOUR_OPENAI_API_KEY";
  const char* openai_host = "api.openai.com";
  const int openai_port = 443;
};

Config config;
ESP8266WebServer server(80);
LiquidCrystal_I2C lcd(LCD_I2C_ADDR, LCD_COLS, LCD_ROWS);
WiFiClientSecure client;

String lastSpeechText = "";
String lastAiResponse = "";
bool processing = false;

const char* htmlPage = R"rawliteral(
<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1">
  <title>ESP8266 AI Speech Assistant</title>
  <style>
    :root {
      --primary: #3498db;
      --primary-dark: #2980b9;
      --secondary: #e74c3c;
      --background: #f9f9f9;
      --text: #333;
      --light-text: #666;
      --border: #ddd;
    }
    
    * {
      box-sizing: border-box;
      margin: 0;
      padding: 0;
    }
    
    body {
      font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
      background-color: var(--background);
      color: var(--text);
      line-height: 1.6;
      padding: 20px;
      max-width: 800px;
      margin: 0 auto;
    }
    
    h1 {
      text-align: center;
      margin-bottom: 20px;
      color: var(--primary-dark);
    }
    
    .container {
      background: white;
      border-radius: 10px;
      box-shadow: 0 2px 10px rgba(0, 0, 0, 0.1);
      padding: 20px;
      margin-bottom: 20px;
    }
    
    .btn-group {
      display: flex;
      justify-content: center;
      margin-bottom: 20px;
    }
    
    button {
      background-color: var(--primary);
      color: white;
      border: none;
      padding: 12px 24px;
      font-size: 16px;
      border-radius: 50px;
      cursor: pointer;
      margin: 0 10px;
      transition: background-color 0.3s, transform 0.2s;
      display: flex;
      align-items: center;
    }
    
    button:hover {
      background-color: var(--primary-dark);
      transform: translateY(-2px);
    }
    
    button:disabled {
      background-color: var(--border);
      cursor: not-allowed;
      transform: none;
    }
    
    #stopBtn {
      background-color: var(--secondary);
    }
    
    .card {
      border: 1px solid var(--border);
      border-radius: 8px;
      padding: 15px;
      margin-bottom: 15px;
    }
    
    .card-header {
      font-weight: bold;
      margin-bottom: 10px;
      color: var(--primary-dark);
      border-bottom: 1px solid var(--border);
      padding-bottom: 5px;
    }
    
    #speechResult, #aiResponse {
      min-height: 80px;
      white-space: pre-wrap;
    }
    
    .listening {
      color: var(--secondary);
      font-weight: bold;
    }
    
    .status {
      text-align: center;
      font-size: 14px;
      margin-top: 20px;
      color: var(--light-text);
    }
    
    .icon {
      margin-right: 8px;
    }

    @media (max-width: 500px) {
      .btn-group {
        flex-direction: column;
      }
      
      button {
        margin: 5px 0;
      }
    }
  </style>
</head>
<body>
  <h1>ESP8266 AI Speech Assistant</h1>
  
  <div class="container">
    <div class="btn-group">
      <button id="startBtn">
        <span class="icon">🎤</span> Start Listening
      </button>
      <button id="stopBtn" disabled>
        <span class="icon">⏹️</span> Stop
      </button>
      <button id="askAiBtn" disabled>
        <span class="icon">🤖</span> Ask AI
      </button>
    </div>
    
    <div class="card">
      <div class="card-header">Your Speech</div>
      <div id="speechResult">Speak something to see your words here...</div>
    </div>
    
    <div class="card">
      <div class="card-header">AI Response</div>
      <div id="aiResponse">AI response will appear here...</div>
    </div>
    
    <div class="status" id="status"></div>
  </div>
  
  <script>
    const startBtn = document.getElementById('startBtn');
    const stopBtn = document.getElementById('stopBtn');
    const askAiBtn = document.getElementById('askAiBtn');
    const speechResult = document.getElementById('speechResult');
    const aiResponse = document.getElementById('aiResponse');
    const statusEl = document.getElementById('status');
    
    let recognition;
    let resultText = "";
    
    function setStatus(message, isError = false) {
      statusEl.textContent = message;
      statusEl.style.color = isError ? 'red' : 'var(--light-text)';
    }
    
    function resetButtons(listening = false) {
      startBtn.disabled = listening;
      stopBtn.disabled = !listening;
      askAiBtn.disabled = !resultText.trim();
    }
    
    function initSpeechRecognition() {
      if ('webkitSpeechRecognition' in window || 'SpeechRecognition' in window) {
        recognition = new (window.SpeechRecognition || window.webkitSpeechRecognition)();
        recognition.continuous = true;
        recognition.interimResults = true;
        recognition.lang = 'en-US';  // Set language - change as needed
        
        recognition.onstart = function() {
          resetButtons(true);
          speechResult.classList.add('listening');
          speechResult.textContent = "Listening...";
          setStatus("Listening for speech");
        };
        
        recognition.onresult = function(event) {
          resultText = "";
          for (let i = event.resultIndex; i < event.results.length; i++) {
            if (event.results[i].isFinal) {
              resultText += event.results[i][0].transcript;
            }
          }
          
          speechResult.textContent = resultText;
          askAiBtn.disabled = !resultText.trim();
          
          if (resultText.trim() !== "") {
            // Automatically send to ESP if needed
            // sendToESP(resultText);
          }
        };
        
        recognition.onerror = function(event) {
          console.error('Speech recognition error:', event.error);
          setStatus(`Error: ${event.error}`, true);
          speechResult.textContent = "Error: " + event.error;
          resetButtons();
        };
        
        recognition.onend = function() {
          speechResult.classList.remove('listening');
          resetButtons();
          setStatus("Speech recognition ended");
        };
        
        return true;
      } else {
        alert("Your browser doesn't support speech recognition. Please try Chrome or Edge.");
        return false;
      }
    }
    
    function sendToESP(text, endpoint = '/process') {
      setStatus("Sending to ESP...");
      
      return fetch(`${endpoint}?text=${encodeURIComponent(text)}`)
        .then(response => {
          if (!response.ok) {
            throw new Error(`Server returned ${response.status}`);
          }
          return response.text();
        })
        .then(data => {
          setStatus("ESP processed successfully");
          return data;
        })
        .catch(error => {
          console.error('Error sending to ESP:', error);
          setStatus(`Error: ${error.message}`, true);
          throw error;
        });
    }
    
    function askAI() {
      if (!resultText.trim()) return;
      
      askAiBtn.disabled = true;
      aiResponse.textContent = "Processing request...";
      setStatus("Sending to AI...");
      
      sendToESP(resultText, '/ask')
        .then(data => {
          if (data) {
            // Poll for result
            checkAIResponse();
          }
        })
        .catch(() => {
          aiResponse.textContent = "Failed to process your request.";
          askAiBtn.disabled = false;
        });
    }
    
    function checkAIResponse() {
      fetch('/ai-response')
        .then(response => response.json())
        .then(data => {
          if (data.processing) {
            aiResponse.textContent = "AI is thinking...";
            setTimeout(checkAIResponse, 2000);
          } else if (data.response) {
            aiResponse.textContent = data.response;
            setStatus("Response received");
            askAiBtn.disabled = false;
          } else {
            aiResponse.textContent = "No response from AI.";
            setStatus("No response", true);
            askAiBtn.disabled = false;
          }
        })
        .catch(error => {
          console.error('Error checking AI response:', error);
          aiResponse.textContent = "Error checking response status.";
          setStatus("Error checking response", true);
          askAiBtn.disabled = false;
        });
    }
    
    // Initialize
    if (initSpeechRecognition()) {
      startBtn.addEventListener('click', function() {
        recognition.start();
      });
      
      stopBtn.addEventListener('click', function() {
        recognition.stop();
      });
      
      askAiBtn.addEventListener('click', askAI);
    }
    
    // Check for ongoing processes on page load
    fetch('/status')
      .then(response => response.json())
      .then(data => {
        if (data.lastSpeech) {
          resultText = data.lastSpeech;
          speechResult.textContent = resultText;
          askAiBtn.disabled = false;
        }
        
        if (data.lastResponse) {
          aiResponse.textContent = data.lastResponse;
        }
        
        if (data.processing) {
          askAiBtn.disabled = true;
          setStatus("AI request in progress...");
          checkAIResponse();
        }
      })
      .catch(error => {
        console.error('Error fetching status:', error);
      });
  </script>
</body>
</html>
)rawliteral";

void displayLcdMessage(String line1, String line2 = "") {
  lcd.clear();
  lcd.setCursor(0, 0);
  lcd.print(line1.substring(0, min(LCD_COLS, (int)line1.length())));
  
  if (line2.length() > 0) {
    lcd.setCursor(0, 1);
    lcd.print(line2.substring(0, min(LCD_COLS, (int)line2.length())));
  }
}

void setupWifi() {
  WiFi.mode(WIFI_STA);
  WiFi.begin(config.ssid, config.password);
  
  displayLcdMessage("Connecting WiFi");
  
  int attempts = 0;
  while (WiFi.status() != WL_CONNECTED && attempts < 20) {
    delay(500);
    Serial.print(".");
    attempts++;
  }
  
  if (WiFi.status() == WL_CONNECTED) {
    Serial.println("\nWiFi Connected");
    Serial.print("IP Address: ");
    Serial.println(WiFi.localIP());
    
    displayLcdMessage("WiFi Connected", WiFi.localIP().toString());
  } else {
    Serial.println("\nWiFi connection failed");
    displayLcdMessage("WiFi Failed", "Check settings");
  }
}

void setupServer() {
  server.on("/", HTTP_GET, []() {
    server.send(200, "text/html", htmlPage);
  });
  
  server.on("/process", HTTP_GET, handleSpeechText);
  server.on("/ask", HTTP_GET, handleAskAI);
  server.on("/ai-response", HTTP_GET, handleAIResponse);
  server.on("/status", HTTP_GET, handleStatus);
  
  server.onNotFound([]() {
    server.send(404, "text/plain", "Not Found");
  });
  
  server.begin();
  Serial.println("Web Server started");
}

void setup() {
  Serial.begin(115200);
  Serial.println("\nESP8266 AI Speech Assistant");
  
  Wire.begin(SDA_PIN, SCL_PIN);
  lcd.begin(LCD_COLS, LCD_ROWS);
  lcd.backlight();
  
  displayLcdMessage("AI Speech", "Assistant v1.0");
  delay(2000);
  
  setupWifi();
  
  client.setInsecure(); // Note: For production, consider using proper certificate verification
  
  setupServer();
  
  Serial.println("Ready! Open browser at http://" + WiFi.localIP().toString());
}

void loop() {
  server.handleClient();
}

void handleSpeechText() {
  if (server.hasArg("text")) {
    String text = server.arg("text");
    text.trim();
    
    lastSpeechText = text;
    
    Serial.println("[Speech] " + text);
    
    displayLcdMessage("Speech:", text);
    
    server.send(200, "text/plain", "Speech received");
  } else {
    server.send(400, "text/plain", "No text parameter");
  }
}

String callOpenAI(String prompt) {
  if (!client.connect(config.openai_host, config.openai_port)) {
    Serial.println("Connection to OpenAI failed");
    return "Connection failed";
  }
  
  // Create JSON payload
  DynamicJsonDocument requestDoc(1024);
  requestDoc["model"] = "gpt-3.5-turbo";
  
  JsonArray messages = requestDoc.createNestedArray("messages");
  
  JsonObject systemMessage = messages.createNestedObject();
  systemMessage["role"] = "system";
  systemMessage["content"] = "You are a helpful assistant. Keep responses concise as they will be displayed on a small LCD screen.";
  
  JsonObject userMessage = messages.createNestedObject();
  userMessage["role"] = "user";
  userMessage["content"] = prompt;
  
  requestDoc["max_tokens"] = 150;
  requestDoc["temperature"] = 0.7;
  
  String jsonPayload;
  serializeJson(requestDoc, jsonPayload);
  
  // Prepare HTTP request
  String request = "POST /v1/chat/completions HTTP/1.1\r\n";
  request += "Host: " + String(config.openai_host) + "\r\n";
  request += "Content-Type: application/json\r\n";
  request += "Authorization: Bearer " + String(config.openai_api_key) + "\r\n";
  request += "Content-Length: " + String(jsonPayload.length()) + "\r\n";
  request += "Connection: close\r\n\r\n";
  request += jsonPayload;
  
  // Send request
  client.print(request);
  
  // Wait for response
  long timeout = millis() + 10000;
  while (client.available() == 0) {
    if (millis() > timeout) {
      Serial.println("OpenAI request timeout");
      client.stop();
      return "Request timeout";
    }
    delay(100);
  }
  
  // Read headers
  String line;
  while (client.available()) {
    line = client.readStringUntil('\n');
    if (line == "\r") {
      break;
    }
  }
  
  // Read body
  String response = "";
  while (client.available()) {
    response += client.readString();
  }
  
  // Parse JSON response
  DynamicJsonDocument responseDoc(2048);
  DeserializationError error = deserializeJson(responseDoc, response);
  
  if (error) {
    Serial.print("JSON parsing failed: ");
    Serial.println(error.c_str());
    return "JSON parsing failed";
  }
  
  // Extract content
  String content = "";
  if (responseDoc.containsKey("choices") && 
      responseDoc["choices"].size() > 0 && 
      responseDoc["choices"][0].containsKey("message") &&
      responseDoc["choices"][0]["message"].containsKey("content")) {
    content = responseDoc["choices"][0]["message"]["content"].as<String>();
  } else if (responseDoc.containsKey("error")) {
    content = "API Error: " + responseDoc["error"]["message"].as<String>();
  } else {
    content = "Unknown response format";
  }
  
  return content;
}

void handleAskAI() {
  if (!server.hasArg("text")) {
    server.send(400, "text/plain", "No text parameter");
    return;
  }
  
  String text = server.arg("text");
  text.trim();
  
  if (text.isEmpty()) {
    server.send(400, "text/plain", "Empty text");
    return;
  }
  
  lastSpeechText = text;
  processing = true;
  
  server.send(200, "text/plain", "Processing");
  
  // Process OpenAI request in a non-blocking way
  displayLcdMessage("Processing...", "Please wait");
  
  // In a real implementation, you'd use AsyncTCP or similar
  // Since ESP8266 doesn't multitask well, we'll just do it here
  lastAiResponse = callOpenAI(text);
  processing = false;
  
  // Display result on LCD
  displayLcdMessage("AI Response:", lastAiResponse);
}

void handleAIResponse() {
  DynamicJsonDocument doc(512);
  doc["processing"] = processing;
  doc["response"] = lastAiResponse;
  
  String jsonResponse;
  serializeJson(doc, jsonResponse);
  
  server.send(200, "application/json", jsonResponse);
}

void handleStatus() {
  DynamicJsonDocument doc(512);
  doc["processing"] = processing;
  doc["lastSpeech"] = lastSpeechText;
  doc["lastResponse"] = lastAiResponse;
  
  String jsonResponse;
  serializeJson(doc, jsonResponse);
  
  server.send(200, "application/json", jsonResponse);
}

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

#include <ESP8266WiFi.h>

#include <ESP8266WebServer.h>

#include <WiFiClientSecure.h>

#include <ArduinoJson.h>

#include <LiquidCrystal_I2C.h>

#include <Wire.h>

#define LCD_I2C_ADDR 0x27

#define LCD_COLS 16

#define LCD_ROWS 2

#define SDA_PIN 4 // D2 on NodeMCU

#define SCL_PIN 5 // D1 on NodeMCU

struct Config {

const char* ssid = "YOUR_WIFI_SSID";

const char* password = "YOUR_WIFI_PASSWORD";

const char* openai_api_key = "YOUR_OPENAI_API_KEY";

const char* openai_host = "api.openai.com";

const int openai_port = 443;

};

Config config;

ESP8266WebServer server(80);

LiquidCrystal_I2C lcd(LCD_I2C_ADDR, LCD_COLS, LCD_ROWS);

WiFiClientSecure client;

String lastSpeechText = "";

String lastAiResponse = "";

bool processing = false;

const char* htmlPage = R"rawliteral(

<!DOCTYPE html>

<head>

<title>ESP8266 AI Speech Assistant</title>

<style>

:root {

--primary: #3498db;

--primary-dark: #2980b9;

--secondary: #e74c3c;

--background: #f9f9f9;

--text: #333;

--light-text: #666;

--border: #ddd;

}

* {

box-sizing: border-box;

margin: 0;

padding: 0;

}

body {

font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;

background-color: var(--background);

color: var(--text);

line-height: 1.6;

padding: 20px;

max-width: 800px;

margin: 0 auto;

}

h1 {

text-align: center;

margin-bottom: 20px;

color: var(--primary-dark);

}

.container {

background: white;

border-radius: 10px;

box-shadow: 0 2px 10px rgba(0, 0, 0, 0.1);

padding: 20px;

margin-bottom: 20px;

}

.btn-group {

display: flex;

justify-content: center;

margin-bottom: 20px;

}

button {

background-color: var(--primary);

color: white;

border: none;

padding: 12px 24px;

font-size: 16px;

border-radius: 50px;

cursor: pointer;

margin: 0 10px;

transition: background-color 0.3s, transform 0.2s;

display: flex;

align-items: center;

}

button:hover {

background-color: var(--primary-dark);

transform: translateY(-2px);

}

button:disabled {

background-color: var(--border);

cursor: not-allowed;

transform: none;

}

#stopBtn {

background-color: var(--secondary);

}

.card {

border: 1px solid var(--border);

border-radius: 8px;

padding: 15px;

margin-bottom: 15px;

}

.card-header {

font-weight: bold;

margin-bottom: 10px;

color: var(--primary-dark);

border-bottom: 1px solid var(--border);

padding-bottom: 5px;

}

#speechResult, #aiResponse {

min-height: 80px;

white-space: pre-wrap;

}

.listening {

color: var(--secondary);

font-weight: bold;

}

.status {

text-align: center;

font-size: 14px;

margin-top: 20px;

color: var(--light-text);

}

.icon {

margin-right: 8px;

}

@media (max-width: 500px) {

.btn-group {

flex-direction: column;

}

button {

margin: 5px 0;

}

</style>

</head>

<body>

<h1>ESP8266 AI Speech Assistant</h1>

<span class="icon">🎤</span> Start Listening

</button>

<span class="icon">⏹️</span> Stop

</button>

<span class="icon">🤖</span> Ask AI

</button>

</div>

<div class="card-header">Your Speech</div>

<div id="speechResult">Speak something to see your words here...</div>

</div>

<div class="card-header">AI Response</div>

<div id="aiResponse">AI response will appear here...</div>

</div>

</div>

const startBtn = document.getElementById('startBtn');

const stopBtn = document.getElementById('stopBtn');

const askAiBtn = document.getElementById('askAiBtn');

const speechResult = document.getElementById('speechResult');

const aiResponse = document.getElementById('aiResponse');

const statusEl = document.getElementById('status');

let recognition;

let resultText = "";

function setStatus(message, isError = false) {

statusEl.textContent = message;

statusEl.style.color = isError ? 'red' : 'var(--light-text)';

}

function resetButtons(listening = false) {

startBtn.disabled = listening;

stopBtn.disabled = !listening;

askAiBtn.disabled = !resultText.trim();

}

function initSpeechRecognition() {

if ('webkitSpeechRecognition' in window || 'SpeechRecognition' in window) {

recognition = new (window.SpeechRecognition || window.webkitSpeechRecognition)();

recognition.continuous = true;

recognition.interimResults = true;

recognition.lang = 'en-US'; // Set language - change as needed

recognition.onstart = function() {

resetButtons(true);

speechResult.classList.add('listening');

speechResult.textContent = "Listening...";

setStatus("Listening for speech");

};

recognition.onresult = function(event) {

resultText = "";

for (let i = event.resultIndex; i < event.results.length; i++) {

if (event.results[i].isFinal) {

resultText += event.results[i][0].transcript;

}

speechResult.textContent = resultText;

askAiBtn.disabled = !resultText.trim();

if (resultText.trim() !== "") {

// Automatically send to ESP if needed

// sendToESP(resultText);

}

};

recognition.onerror = function(event) {

console.error('Speech recognition error:', event.error);

setStatus(`Error: ${event.error}`, true);

speechResult.textContent = "Error: " + event.error;

resetButtons();

};

recognition.onend = function() {

speechResult.classList.remove('listening');

resetButtons();

setStatus("Speech recognition ended");

};

return true;

} else {

alert("Your browser doesn't support speech recognition. Please try Chrome or Edge.");

return false;

}

function sendToESP(text, endpoint = '/process') {

setStatus("Sending to ESP...");

return fetch(`${endpoint}?text=${encodeURIComponent(text)}`)

.then(response => {

if (!response.ok) {

throw new Error(`Server returned ${response.status}`);

}

return response.text();

})

.then(data => {

setStatus("ESP processed successfully");

return data;

})

.catch(error => {

console.error('Error sending to ESP:', error);

setStatus(`Error: ${error.message}`, true);

throw error;

});

}

function askAI() {

if (!resultText.trim()) return;

askAiBtn.disabled = true;

aiResponse.textContent = "Processing request...";

setStatus("Sending to AI...");

sendToESP(resultText, '/ask')

.then(data => {

if (data) {

// Poll for result

checkAIResponse();

}

})

.catch(() => {

aiResponse.textContent = "Failed to process your request.";

askAiBtn.disabled = false;

});

}

function checkAIResponse() {

fetch('/ai-response')

.then(response => response.json())

.then(data => {

if (data.processing) {

aiResponse.textContent = "AI is thinking...";

setTimeout(checkAIResponse, 2000);

} else if (data.response) {

aiResponse.textContent = data.response;

setStatus("Response received");

askAiBtn.disabled = false;

} else {

aiResponse.textContent = "No response from AI.";

setStatus("No response", true);

askAiBtn.disabled = false;

}

})

.catch(error => {

console.error('Error checking AI response:', error);

aiResponse.textContent = "Error checking response status.";

setStatus("Error checking response", true);

askAiBtn.disabled = false;

});

}

// Initialize

if (initSpeechRecognition()) {

startBtn.addEventListener('click', function() {

recognition.start();

});

stopBtn.addEventListener('click', function() {

recognition.stop();

});

askAiBtn.addEventListener('click', askAI);

}

// Check for ongoing processes on page load

fetch('/status')

.then(response => response.json())

.then(data => {

if (data.lastSpeech) {

resultText = data.lastSpeech;

speechResult.textContent = resultText;

askAiBtn.disabled = false;

}

if (data.lastResponse) {

aiResponse.textContent = data.lastResponse;

}

if (data.processing) {

askAiBtn.disabled = true;

setStatus("AI request in progress...");

checkAIResponse();

}

})

.catch(error => {

console.error('Error fetching status:', error);

});

</script>

</body>

</html>

)rawliteral";

void displayLcdMessage(String line1, String line2 = "") {

lcd.clear();

lcd.setCursor(0, 0);

lcd.print(line1.substring(0, min(LCD_COLS, (int)line1.length())));

if (line2.length() > 0) {

lcd.setCursor(0, 1);

lcd.print(line2.substring(0, min(LCD_COLS, (int)line2.length())));

}

void setupWifi() {

WiFi.mode(WIFI_STA);

WiFi.begin(config.ssid, config.password);

displayLcdMessage("Connecting WiFi");

int attempts = 0;

while (WiFi.status() != WL_CONNECTED && attempts < 20) {

delay(500);

Serial.print(".");

attempts++;

}

if (WiFi.status() == WL_CONNECTED) {

Serial.println("\nWiFi Connected");

Serial.print("IP Address: ");

Serial.println(WiFi.localIP());

displayLcdMessage("WiFi Connected", WiFi.localIP().toString());

} else {

Serial.println("\nWiFi connection failed");

displayLcdMessage("WiFi Failed", "Check settings");

}

void setupServer() {

server.on("/", HTTP_GET, []() {

server.send(200, "text/html", htmlPage);

});

server.on("/process", HTTP_GET, handleSpeechText);

server.on("/ask", HTTP_GET, handleAskAI);

server.on("/ai-response", HTTP_GET, handleAIResponse);

server.on("/status", HTTP_GET, handleStatus);

server.onNotFound([]() {

server.send(404, "text/plain", "Not Found");

});

server.begin();

Serial.println("Web Server started");

}

void setup() {

Serial.begin(115200);

Serial.println("\nESP8266 AI Speech Assistant");

Wire.begin(SDA_PIN, SCL_PIN);

lcd.begin(LCD_COLS, LCD_ROWS);

lcd.backlight();

displayLcdMessage("AI Speech", "Assistant v1.0");

delay(2000);

setupWifi();

client.setInsecure(); // Note: For production, consider using proper certificate verification

setupServer();

Serial.println("Ready! Open browser at http://" + WiFi.localIP().toString());

}

void loop() {

server.handleClient();

}

void handleSpeechText() {

if (server.hasArg("text")) {

String text = server.arg("text");

text.trim();

lastSpeechText = text;

Serial.println("[Speech] " + text);

displayLcdMessage("Speech:", text);

server.send(200, "text/plain", "Speech received");

} else {

server.send(400, "text/plain", "No text parameter");

}

String callOpenAI(String prompt) {

if (!client.connect(config.openai_host, config.openai_port)) {

Serial.println("Connection to OpenAI failed");

return "Connection failed";

}

// Create JSON payload

DynamicJsonDocument requestDoc(1024);

requestDoc["model"] = "gpt-3.5-turbo";

JsonArray messages = requestDoc.createNestedArray("messages");

JsonObject systemMessage = messages.createNestedObject();

systemMessage["role"] = "system";

systemMessage["content"] = "You are a helpful assistant. Keep responses concise as they will be displayed on a small LCD screen.";

JsonObject userMessage = messages.createNestedObject();

userMessage["role"] = "user";

userMessage["content"] = prompt;

requestDoc["max_tokens"] = 150;

requestDoc["temperature"] = 0.7;

String jsonPayload;

serializeJson(requestDoc, jsonPayload);

// Prepare HTTP request

String request = "POST /v1/chat/completions HTTP/1.1\r\n";

request += "Host: " + String(config.openai_host) + "\r\n";

request += "Content-Type: application/json\r\n";

request += "Authorization: Bearer " + String(config.openai_api_key) + "\r\n";

request += "Content-Length: " + String(jsonPayload.length()) + "\r\n";

request += "Connection: close\r\n\r\n";

request += jsonPayload;

// Send request

client.print(request);

// Wait for response

long timeout = millis() + 10000;

while (client.available() == 0) {

if (millis() > timeout) {

Serial.println("OpenAI request timeout");

client.stop();

return "Request timeout";

}

delay(100);

}

// Read headers

String line;

while (client.available()) {

line = client.readStringUntil('\n');

if (line == "\r") {

break;

}

// Read body

String response = "";

while (client.available()) {

response += client.readString();

}

// Parse JSON response

DynamicJsonDocument responseDoc(2048);

DeserializationError error = deserializeJson(responseDoc, response);

if (error) {

Serial.print("JSON parsing failed: ");

Serial.println(error.c_str());

return "JSON parsing failed";

}

// Extract content

String content = "";

if (responseDoc.containsKey("choices") &&

responseDoc["choices"].size() > 0 &&

responseDoc["choices"][0].containsKey("message") &&

responseDoc["choices"][0]["message"].containsKey("content")) {

content = responseDoc["choices"][0]["message"]["content"].as<String>();

} else if (responseDoc.containsKey("error")) {

content = "API Error: " + responseDoc["error"]["message"].as<String>();

} else {

content = "Unknown response format";

}

return content;

}

void handleAskAI() {

if (!server.hasArg("text")) {

server.send(400, "text/plain", "No text parameter");

return;

}

String text = server.arg("text");

text.trim();

if (text.isEmpty()) {

server.send(400, "text/plain", "Empty text");

return;

}

lastSpeechText = text;

processing = true;

server.send(200, "text/plain", "Processing");

// Process OpenAI request in a non-blocking way

displayLcdMessage("Processing...", "Please wait");

// In a real implementation, you'd use AsyncTCP or similar

// Since ESP8266 doesn't multitask well, we'll just do it here

lastAiResponse = callOpenAI(text);

processing = false;

// Display result on LCD

displayLcdMessage("AI Response:", lastAiResponse);

}

void handleAIResponse() {

DynamicJsonDocument doc(512);

doc["processing"] = processing;

doc["response"] = lastAiResponse;

String jsonResponse;

serializeJson(doc, jsonResponse);

server.send(200, "application/json", jsonResponse);

}

void handleStatus() {

DynamicJsonDocument doc(512);

doc["processing"] = processing;

doc["lastSpeech"] = lastSpeechText;

doc["lastResponse"] = lastAiResponse;

String jsonResponse;

serializeJson(doc, jsonResponse);

server.send(200, "application/json", jsonResponse);

}

Jangan lupa ganti NAMA_WIFI_ANDA dan PASSWORD_WIFI_ANDA dengan kredensial WiFi Anda.

Penggunaan

Upload kode program ke ESP8266 melalui Arduino IDE
Buka Serial Monitor untuk melihat IP address ESP8266
Dari smartphone atau laptop, buka browser dan akses IP address tersebut
Tekan tombol “Mulai Mendengarkan” dan ucapkan sesuatu
Teks hasil pengenalan suara akan muncul di layar browser dan LCD

Pengembangan Lebih Lanjut

Sistem ini masih sangat dasar, tapi bisa dikembangkan lebih jauh. Beberapa ide pengembangan:

Integrasi dengan API AI: Mengirim teks hasil pengenalan suara ke Groq, OpenAI, atau layanan AI lainnya untuk mendapatkan respons cerdas
Kontrol Perangkat: Menambahkan kemampuan untuk mengontrol relay atau perangkat lain berdasarkan perintah suara
Penyimpanan Data: Menyimpan riwayat percakapan ke database atau file
Dukungan Bahasa: Menambahkan dukungan untuk bahasa lain selain bahasa default

Kesimpulan

Dengan kombinasi ESP8266 dan teknologi web modern, kita bisa membuat sistem pengenalan suara sederhana tanpa perlu komponen mahal. Meskipun ESP8266 memiliki keterbatasan RAM, pendekatan ini mengatasinya dengan memanfaatkan kemampuan browser untuk pemrosesan yang berat.

Semoga artikel ini bermanfaat dan bisa menjadi inspirasi untuk proyek-proyek IoT lainnya. Jangan ragu untuk bereksperimen dan mengembangkan ide ini lebih jauh sesuai kebutuhan Anda.

Selamat mencoba dan berkreasi!

fdciabdul3 weeks ago

0 62 2 minutes read