Hugging Face's logo

Spaces:
99i
/
t2
Running

App Files Community
t2
File size: 8,596 Bytes 
c4d8226
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
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
 
<!DOCTYPE html>
<html lang="zh-CN">

<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>TTS 语音合成服务</title>
    <style>
        body {
            font-family: Arial, sans-serif;
            margin: 0;
            padding: 20px;
            background-color: #f5f5f5;
        }

        .container {
            max-width: 1200px;
            margin: 0 auto;
            background-color: white;
            padding: 20px;
            border-radius: 8px;
            box-shadow: 0 2px 10px rgba(0, 0, 0, 0.1);
        }

        h1 {
            color: #333;
            text-align: center;
        }

        .filter-section {
            margin-bottom: 20px;
            padding: 15px;
            background-color: #f0f8ff;
            border-radius: 5px;
        }

        .voice-list {
            display: grid;
            grid-template-columns: repeat(auto-fill, minmax(300px, 1fr));
            gap: 20px;
        }

        .voice-card {
            border: 1px solid #ddd;
            padding: 15px;
            border-radius: 5px;
            background-color: white;
        }

        .voice-card h3 {
            margin-top: 0;
            color: #2c3e50;
        }

        .voice-card p {
            margin: 5px 0;
        }

        .style-list {
            display: flex;
            flex-wrap: wrap;
            gap: 5px;
            margin-top: 10px;
        }

        .style-tag {
            background-color: #e0f7fa;
            padding: 3px 8px;
            border-radius: 10px;
            font-size: 12px;
        }

        select,
        button {
            padding: 8px 12px;
            margin-right: 10px;
            border-radius: 4px;
            border: 1px solid #ddd;
        }

        button {
            background-color: #4CAF50;
            color: white;
            border: none;
            cursor: pointer;
        }

        button:hover {
            background-color: #45a049;
        }
    </style>
</head>

<body>
    <div class="container">
        <h1>TTS 语音合成服务</h1>
        <div class="container" style="margin-top: 30px;">
            <h2>语音合成</h2>
            <div class="filter-section">
                <div style="margin-bottom: 15px;">
                    <label for="synthesis-text">输入文本:</label>
                    <textarea id="synthesis-text" rows="4"
                        style="width: 100%; padding: 8px; border-radius: 4px; border: 1px solid #ddd;"></textarea>
                </div>

                <div style="margin-bottom: 15px;">
                    <label for="synthesis-voice">选择音色:</label>
                    <select id="synthesis-voice" style="width: 200px;">
                        <!-- 音色选项将通过JavaScript动态加载 -->
                    </select>
                </div>

                <div style="margin-bottom: 15px;">
                    <label for="rate-slider">语速: <span id="rate-value">1.0</span></label>
                    <input type="range" id="rate-slider" min="0.5" max="2.0" step="0.1" value="1.0"
                        style="width: 200px;" oninput="document.getElementById('rate-value').textContent = this.value">
                </div>

                <div style="margin-bottom: 15px;">
                    <label for="pitch-slider">音调: <span id="pitch-value">0</span></label>
                    <input type="range" id="pitch-slider" min="-12" max="12" step="1" value="0" style="width: 200px;"
                        oninput="document.getElementById('pitch-value').textContent = this.value">
                </div>

                <button onclick="synthesizeSpeech()">合成语音</button>
                <audio id="audio-player" controls style="display: none; margin-top: 15px; width: 100%;"></audio>
            </div>
            <div class="filter-section">
                <label for="gender-filter">按性别筛选:</label>
                <select id="gender-filter">
                    <option value="all">全部</option>
                    <option value="Female">女声</option>
                    <option value="Male">男声</option>
                </select>
                <button id="apply-filter">应用筛选</button>
            </div>

            <div class="voice-list" id="voice-list">
                <!-- 语音列表将通过JavaScript动态加载 -->
            </div>
        </div>


    </div>

    <script>
        async function loadVoices(gender = 'all') {
            try {
                const response = await fetch('/voices?l=zh&d=true');
                let voices = await response.json();
                voices = voices['voices']
                const filteredVoices = gender === 'all'
                    ? voices
                    : voices.filter(voice => voice.Gender === gender);

                const voiceList = document.getElementById('voice-list');
                voiceList.innerHTML = '';

                filteredVoices.forEach(voice => {
                    const voiceCard = document.createElement('div');
                    voiceCard.className = 'voice-card';

                    voiceCard.innerHTML = `
                        <h3>${voice.LocalName} (${voice.DisplayName})</h3>
                        <p><strong>性别:</strong> ${voice.Gender === 'Female' ? '女' : '男'}</p>
                        <p><strong>语言:</strong> ${voice.LocaleName}</p>
                        <p><strong>短名称:</strong> ${voice.ShortName}</p>
                        
                        <div class="style-list">
                            ${voice.StyleList ? voice.StyleList.map(style =>
                        `<span class="style-tag">${style}</span>`).join('') : ''}
                        </div>
                    `;

                    voiceList.appendChild(voiceCard);
                });
            } catch (error) {
                console.error('加载音色列表失败:', error);
                document.getElementById('voice-list').innerHTML =
                    '<p style="color:red;">加载音色列表失败，请刷新页面重试</p>';
            }
        }

        async function synthesizeSpeech() {
            const text = document.getElementById('synthesis-text').value;
            const voice = document.getElementById('synthesis-voice').value;
            const rate = document.getElementById('rate-slider').value;
            const pitch = document.getElementById('pitch-slider').value;

            try {
                const response = await fetch('/tts', {
                    method: 'POST',
                    headers: {
                        'Content-Type': 'application/json',
                    },
                    body: JSON.stringify({
                        t: text,
                        v: voice,
                        r: rate,
                        p: pitch
                    })
                });

                if (response.ok) {
                    let audioUrl = await response.json();
                    audioUrl = audioUrl['audio_url']
                    const audioPlayer = document.getElementById('audio-player');
                    audioPlayer.src = audioUrl;
                    audioPlayer.style.display = 'block';
                } else {
                    alert('语音合成失败: ' + await response.text());
                }
            } catch (error) {
                console.error('语音合成错误:', error);
                alert('语音合成过程中发生错误');
            }
        }

        document.addEventListener('DOMContentLoaded', () => {
            loadVoices();

            // 加载音色选项
            fetch('/voices?l=zh&d=true')
                .then(response => response.json())
                .then(data => {
                    const voiceSelect = document.getElementById('synthesis-voice');
                    data.voices.forEach(voice => {
                        const option = document.createElement('option');
                        option.value = voice.ShortName;
                        option.textContent = `${voice.LocalName} (${voice.Gender === 'Female' ? '女' : '男'})`;
                        voiceSelect.appendChild(option);
                    });
                });

            document.getElementById('apply-filter').addEventListener('click', () => {
                const gender = document.getElementById('gender-filter').value;
                loadVoices(gender);
            });
        });
    </script>
</body>

</html>