go-tts-api / index.html
xidu's picture
fix(frontend): Simplify UI and fix API data handling
2042591
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>火山引擎语音合成</title>
<style>
:root {
--primary-color: #007bff;
--secondary-color: #6c757d;
--background-color: #f0f2f5;
--surface-color: #ffffff;
--text-color: #212529;
--border-color: #dee2e6;
--error-color: #dc3545;
}
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', Arial, sans-serif;
background-color: var(--background-color);
color: var(--text-color);
margin: 0;
padding: 2rem;
display: flex;
justify-content: center;
align-items: center;
min-height: 100vh;
box-sizing: border-box;
}
.container {
width: 100%;
max-width: 600px;
background: var(--surface-color);
padding: 2rem;
border-radius: 8px;
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.1);
}
h1 {
text-align: center;
color: var(--primary-color);
margin-bottom: 1.5rem;
}
.form-group {
margin-bottom: 1.5rem;
}
.form-group.inline-label {
display: flex;
align-items: center;
gap: 1rem;
}
.form-group .slider-container {
flex-grow: 1;
display: flex;
align-items: center;
gap: 10px;
}
label {
display: block;
margin-bottom: 0.5rem;
font-weight: bold;
}
input[type="text"], input[type="password"], textarea, select, input[type="number"] {
width: 100%;
padding: 0.75rem;
border: 1px solid var(--border-color);
border-radius: 4px;
font-size: 1rem;
box-sizing: border-box;
transition: border-color 0.2s;
}
input[type="range"] { flex-grow: 1; }
input:focus, textarea:focus, select:focus {
outline: none;
border-color: var(--primary-color);
box-shadow: 0 0 0 2px rgba(0, 123, 255, 0.25);
}
textarea { height: 120px; resize: vertical; }
.submit-btn {
width: 100%;
padding: 0.8rem;
background-color: var(--primary-color);
color: white;
border: none;
border-radius: 4px;
font-size: 1.1rem;
cursor: pointer;
transition: background-color 0.2s;
display: flex;
justify-content: center;
align-items: center;
}
.submit-btn:hover:not(:disabled) { background-color: #0056b3; }
.submit-btn:disabled {
background-color: var(--secondary-color);
cursor: not-allowed;
}
.spinner {
border: 4px solid rgba(255, 255, 255, 0.3);
border-radius: 50%;
border-top: 4px solid #fff;
width: 20px;
height: 20px;
animation: spin 1s linear infinite;
margin-right: 10px;
}
@keyframes spin {
0% { transform: rotate(0deg); }
100% { transform: rotate(360deg); }
}
.hidden { display: none; }
#audio-player-container { margin-top: 1.5rem; }
audio { width: 100%; }
#error-message {
margin-top: 1rem;
color: var(--error-color);
background-color: #f8d7da;
border: 1px solid #f5c6cb;
padding: 1rem;
border-radius: 4px;
text-align: center;
word-break: break-all;
}
</style>
</head>
<body>
<div class="container">
<h1>火山引擎语音合成</h1>
<form id="tts-form">
<div class="form-group">
<label for="token-input">Access Token:</label>
<input type="password" id="token-input" value="NYAUtOWZSO24yAVv9vN7RdaXc96eh7BH" required>
</div>
<div class="form-group">
<label for="appid-input">AppID:</label>
<input type="text" id="appid-input" value="6135904441" required>
</div>
<div class="form-group">
<label for="text-input">输入文本:</label>
<textarea id="text-input" placeholder="在这里输入想要转换为语音的文字..." required>字节跳动语音合成,让机器像人一样开口说话。</textarea>
</div>
<div class="form-group">
<label for="voice-select">选择音色:</label>
<select id="voice-select" required>
<option value="">正在加载音色列表...</option>
</select>
</div>
<div class="form-group inline-label">
<label for="speed-slider">语速:</label>
<div class="slider-container">
<input type="range" id="speed-slider" min="0.8" max="2" step="0.1" value="1.0">
<span id="speed-value">1.0</span>
</div>
</div>
<div class="form-group inline-label">
<label for="loudness-slider">音量:</label>
<div class="slider-container">
<input type="range" id="loudness-slider" min="0.5" max="2" step="0.1" value="1.0">
<span id="loudness-value">1.0</span>
</div>
</div>
<div class="form-group inline-label">
<label for="silence-input">句末停顿(ms):</label>
<input type="number" id="silence-input" min="0" max="30000" step="100" value="0">
</div>
<div id="emotion-controls" class="hidden">
<div class="form-group">
<label style="display: inline-block; margin-right: 10px;">开启情感:</label>
<input type="checkbox" id="enable-emotion-checkbox">
</div>
<div class="form-group">
<label for="emotion-select">选择情感:</label>
<select id="emotion-select" disabled></select>
</div>
<div class="form-group inline-label">
<label for="emotion-scale-slider">情绪强度:</label>
<div class="slider-container">
<input type="range" id="emotion-scale-slider" min="1" max="5" step="0.1" value="4.0" disabled>
<span id="emotion-scale-value">4.0</span>
</div>
</div>
</div>
<button type="submit" class="submit-btn" id="submit-button">
<span id="button-spinner" class="spinner hidden"></span>
<span id="button-text">开始合成</span>
</button>
</form>
<div id="audio-player-container" class="hidden">
<label>合成结果:</label>
<audio id="audio-player" controls></audio>
</div>
<div id="error-message" class="hidden"></div>
</div>
<script>
document.addEventListener('DOMContentLoaded', () => {
const voiceSelect = document.getElementById('voice-select');
const ttsForm = document.getElementById('tts-form');
const submitButton = document.getElementById('submit-button');
const buttonSpinner = document.getElementById('button-spinner');
const buttonText = document.getElementById('button-text');
const audioPlayerContainer = document.getElementById('audio-player-container');
const audioPlayer = document.getElementById('audio-player');
const errorMessageDiv = document.getElementById('error-message');
const speedSlider = document.getElementById('speed-slider');
const speedValue = document.getElementById('speed-value');
const loudnessSlider = document.getElementById('loudness-slider');
const loudnessValue = document.getElementById('loudness-value');
const emotionControls = document.getElementById('emotion-controls');
const enableEmotionCheckbox = document.getElementById('enable-emotion-checkbox');
const emotionSelect = document.getElementById('emotion-select');
const emotionScaleSlider = document.getElementById('emotion-scale-slider');
const emotionScaleValue = document.getElementById('emotion-scale-value');
speedSlider.oninput = () => { speedValue.textContent = speedSlider.value; };
loudnessSlider.oninput = () => { loudnessValue.textContent = loudnessSlider.value; };
emotionScaleSlider.oninput = () => { emotionScaleValue.textContent = emotionScaleSlider.value; };
let allVoiceData = {};
fetch('/api/voices')
.then(response => {
if (!response.ok) throw new Error('网络响应错误');
return response.json();
})
.then(voices => {
// 后端返回的是一个有序数组,我们需要先转成map方便查找
voices.forEach(v => { allVoiceData[v.code] = v; });
populateVoiceSelector(voices);
voiceSelect.dispatchEvent(new Event('change'));
})
.catch(error => {
showError('获取音色列表失败: ' + error.message);
});
function populateVoiceSelector(voiceList) {
voiceSelect.innerHTML = '';
const categories = {};
voiceList.forEach(voice => {
if (!categories[voice.category]) {
categories[voice.category] = [];
}
categories[voice.category].push({ code: voice.code, name: voice.displayName });
});
for (const categoryName in categories) {
const optgroup = document.createElement('optgroup');
optgroup.label = categoryName;
categories[categoryName].forEach(voice => {
const option = document.createElement('option');
option.value = voice.code;
option.textContent = voice.name;
optgroup.appendChild(option);
});
voiceSelect.appendChild(optgroup);
}
}
voiceSelect.addEventListener('change', () => {
const selectedVoiceCode = voiceSelect.value;
if (!allVoiceData || !selectedVoiceCode) return;
const voiceInfo = allVoiceData[selectedVoiceCode];
if (voiceInfo && voiceInfo.emotions && voiceInfo.emotions.length > 0) {
emotionControls.classList.remove('hidden');
emotionSelect.innerHTML = '';
voiceInfo.emotions.forEach(emo => {
const option = document.createElement('option');
option.value = emo;
option.textContent = emo;
emotionSelect.appendChild(option);
});
enableEmotionCheckbox.dispatchEvent(new Event('change'));
} else {
emotionControls.classList.add('hidden');
enableEmotionCheckbox.checked = false;
emotionSelect.disabled = true;
emotionScaleSlider.disabled = true;
}
});
enableEmotionCheckbox.addEventListener('change', () => {
const isEnabled = enableEmotionCheckbox.checked;
emotionSelect.disabled = !isEnabled;
emotionScaleSlider.disabled = !isEnabled;
});
ttsForm.addEventListener('submit', async (event) => {
event.preventDefault();
setLoading(true);
hideError();
audioPlayerContainer.classList.add('hidden');
const requestBody = {
token: document.getElementById('token-input').value,
app_id: document.getElementById('appid-input').value,
text: document.getElementById('text-input').value,
voice: voiceSelect.value,
speed_ratio: parseFloat(speedSlider.value),
loudness_ratio: parseFloat(loudnessSlider.value),
silence_duration: parseInt(document.getElementById('silence-input').value, 10),
enable_emotion: enableEmotionCheckbox.checked,
emotion: enableEmotionCheckbox.checked ? emotionSelect.value : "",
emotion_scale: enableEmotionCheckbox.checked ? parseFloat(emotionScaleSlider.value) : 0,
};
try {
const response = await fetch('/api/synthesize', {
method: 'POST',
headers: {'Content-Type': 'application/json'},
body: JSON.stringify(requestBody),
});
if (!response.ok) {
const errorText = await response.text();
throw new Error(errorText || `合成失败,服务器状态码: ${response.status}`);
}
const audioBlob = await response.blob();
const audioUrl = URL.createObjectURL(audioBlob);
audioPlayer.src = audioUrl;
audioPlayerContainer.classList.remove('hidden');
audioPlayer.play();
} catch (error) {
showError(error.message);
} finally {
setLoading(false);
}
});
function setLoading(isLoading) {
submitButton.disabled = isLoading;
buttonSpinner.classList.toggle('hidden', !isLoading);
buttonText.textContent = isLoading ? '正在合成...' : '开始合成';
}
function showError(message) {
errorMessageDiv.textContent = message;
errorMessageDiv.classList.remove('hidden');
}
function hideError() {
errorMessageDiv.classList.add('hidden');
}
});
</script>
</body>
</html>