Sandbox MCP Server

test
test/index.html
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Windows Speech MCP Test</title>
    <style>
        body {
            font-family: Arial, sans-serif;
            max-width: 800px;
            margin: 0 auto;
            padding: 20px;
            background-color: #f5f5f5;
        }
        .container {
            background-color: white;
            padding: 20px;
            border-radius: 8px;
            box-shadow: 0 2px 4px rgba(0,0,0,0.1);
        }
        .section {
            margin-bottom: 20px;
            padding: 20px;
            border: 1px solid #ddd;
            border-radius: 4px;
        }
        h1 {
            color: #333;
            text-align: center;
        }
        textarea {
            width: 100%;
            height: 100px;
            margin: 10px 0;
            padding: 8px;
            border: 1px solid #ddd;
            border-radius: 4px;
            resize: vertical;
        }
        button {
            background-color: #007bff;
            color: white;
            border: none;
            padding: 10px 20px;
            border-radius: 4px;
            cursor: pointer;
            margin: 5px;
        }
        button:hover {
            background-color: #0056b3;
        }
        select {
            padding: 8px;
            margin: 5px;
            border-radius: 4px;
            border: 1px solid #ddd;
        }
        .status {
            margin-top: 10px;
            padding: 10px;
            border-radius: 4px;
        }
        .success {
            background-color: #d4edda;
            color: #155724;
        }
        .error {
            background-color: #f8d7da;
            color: #721c24;
        }
    </style>
</head>
<body>
    <div class="container">
        <h1>Windows Speech MCP Test</h1>
        
        <div class="section">
            <h2>Text to Speech</h2>
            <textarea id="ttsText" placeholder="Enter text to speak...">Hello, this is a test of Windows speech synthesis.</textarea>
            <div>
                <select id="ttsVoice">
                    <option value="Microsoft David Desktop">David</option>
                    <option value="Microsoft Zira Desktop">Zira</option>
                </select>
                <select id="ttsSpeed">
                    <option value="0.5">0.5x Speed</option>
                    <option value="1.0" selected>1.0x Speed</option>
                    <option value="1.5">1.5x Speed</option>
                    <option value="2.0">2.0x Speed</option>
                </select>
                <button onclick="speak()">Speak</button>
            </div>
            <div id="ttsStatus" class="status"></div>
        </div>

        <div class="section">
            <h2>Speech to Text</h2>
            <div>
                <select id="sttDuration">
                    <option value="5">5 seconds</option>
                    <option value="10">10 seconds</option>
                    <option value="15">15 seconds</option>
                    <option value="30">30 seconds</option>
                </select>
                <button onclick="startRecording()">Start Recording</button>
            </div>
            <textarea id="sttText" placeholder="Transcribed text will appear here..." readonly></textarea>
            <div id="sttStatus" class="status"></div>
        </div>
    </div>

    <script>
        async function speak() {
            const text = document.getElementById('ttsText').value;
            const voice = document.getElementById('ttsVoice').value;
            const speed = parseFloat(document.getElementById('ttsSpeed').value);
            const statusDiv = document.getElementById('ttsStatus');

            try {
                const response = await fetch('http://localhost:3000/tts', {
                    method: 'POST',
                    headers: {
                        'Content-Type': 'application/json'
                    },
                    body: JSON.stringify({ text, voice, speed })
                });

                if (!response.ok) throw new Error('Failed to synthesize speech');
                
                statusDiv.textContent = 'Speech synthesis successful!';
                statusDiv.className = 'status success';
            } catch (error) {
                statusDiv.textContent = `Error: ${error.message}`;
                statusDiv.className = 'status error';
            }
        }

        async function startRecording() {
            const duration = parseInt(document.getElementById('sttDuration').value);
            const statusDiv = document.getElementById('sttStatus');
            const textArea = document.getElementById('sttText');

            try {
                statusDiv.textContent = `Recording for ${duration} seconds...`;
                statusDiv.className = 'status';

                const response = await fetch('http://localhost:3000/stt', {
                    method: 'POST',
                    headers: {
                        'Content-Type': 'application/json'
                    },
                    body: JSON.stringify({ duration })
                });

                if (!response.ok) throw new Error('Failed to transcribe speech');
                
                const result = await response.json();
                textArea.value = result.text;
                statusDiv.textContent = 'Transcription successful!';
                statusDiv.className = 'status success';
            } catch (error) {
                statusDiv.textContent = `Error: ${error.message}`;
                statusDiv.className = 'status error';
                textArea.value = '';
            }
        }

        // Fetch available voices when the page loads
        async function loadVoices() {
            try {
                const response = await fetch('http://localhost:3000/voices');
                if (!response.ok) throw new Error('Failed to fetch voices');
                
                const voices = await response.json();
                const voiceSelect = document.getElementById('ttsVoice');
                voiceSelect.innerHTML = '';
                
                voices.forEach(voice => {
                    const option = document.createElement('option');
                    option.value = voice;
                    option.textContent = voice.replace('Microsoft ', '').replace(' Desktop', '');
                    voiceSelect.appendChild(option);
                });
            } catch (error) {
                console.error('Failed to load voices:', error);
            }
        }

        window.onload = loadVoices;
    </script>
</body>
</html>