Hugging Face's logo

Spaces:
ruslanmv
/
Text-to-Speech-Microsoft
Sleeping

App Files Community
Text-to-Speech-Microsoft
File size: 4,334 Bytes 
40e8287
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
import gradio as gr
import edge_tts
import asyncio
import tempfile
import os

# Custom CSS for clean, modern appearance
CUSTOM_CSS = """
body {
    background-color: #ffffff; /* White background */
    color: #333333; /* Dark text */
    font-family: 'Poppins', sans-serif;
}

.gradio-container {
    background-color: #ffffff;
    border-radius: 15px;
    padding: 20px;
    border: 1px solid #e0e0e0;
}

.gr-button {
    background-color: #FFA500 !important; /* Orange buttons */
    border: none !important;
    color: #ffffff !important; /* White text */
    font-size: 16px;
    font-weight: bold;
    border-radius: 8px;
    padding: 10px 20px;
    transition: all 0.3s ease-in-out;
}

.gr-button:hover {
    background-color: #ff8c00 !important; /* Darker orange on hover */
}

.gr-slider, .gr-dropdown, .gr-textbox {
    background-color: #f9f9f9 !important; /* Light input background */
    border-color: #d1d1d1 !important;
    color: #333333 !important;
}

.gr-slider .gr-label, .gr-dropdown .gr-label, .gr-textbox .gr-label {
    color: #333333 !important; /* Darker labels */
}

h1, h2, h3, p, label {
    color: #333333 !important;
}

a {
    color: #FFA500;
    text-decoration: none;
    font-weight: bold;
}

a:hover {
    color: #ff8c00;
}

footer {
    display: none; /* Hide default footer */
}
"""

async def get_voices():
    voices = await edge_tts.list_voices()
    voice_dict = {f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] for v in voices}
    return voice_dict

async def text_to_speech(text, voice, rate, pitch):
    if not text.strip():
        return None, "Please enter text to convert."
    if not voice:
        return None, "Please select a voice."
    
    voice_short_name = voice.split(" - ")[0]
    rate_str = f"{rate:+d}%"
    pitch_str = f"{pitch:+d}Hz"
    communicate = edge_tts.Communicate(text, voice_short_name, rate=rate_str, pitch=pitch_str)
    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
        tmp_path = tmp_file.name
        await communicate.save(tmp_path)
    return tmp_path, None

async def tts_interface(text, voice, rate, pitch):
    audio, warning = await text_to_speech(text, voice, rate, pitch)
    if warning:
        return audio, gr.Warning(warning)
    return audio, None

async def create_demo():
    voices = await get_voices()
    default_voice = "en-US-AvaNeural - en-US (Female)"

    description = """
    Convert text to speech using Microsoft Edge TTS. Adjust speech rate and pitch: 0 is default, positive values increase, negative values decrease.

    Take your content creation to the next level with our cutting-edge Text-to-Video Converter! 
    Transform your words into stunning, professional-quality videos in just a few clicks. 

    ✨ Features:
    • Convert text to engaging videos with customizable visuals
    • Perfect for creating audiobooks, storytelling, and language learning materials
    • Ideal for educators, content creators, and language enthusiasts

    For mor information [Click here to try our blog now!](https://ruslanmv.com/)
    """

    demo = gr.Interface(
        fn=tts_interface,
        inputs=[
            gr.Textbox(label="Input Text", lines=5, placeholder="Type your text here..."),
            gr.Dropdown(choices=["", default_voice] + list(voices.keys()), label="Select Voice", value=default_voice),
            gr.Slider(minimum=-50, maximum=50, value=0, label="Speech Rate Adjustment (%)", step=1),
            gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1)
        ],
        outputs=[
            gr.Audio(label="Generated Audio", type="filepath"),
            gr.Markdown(label="Warning", visible=False)
        ],
        title="🚀 Edge TTS Text-to-Speech Converter",
        description=description,
        article="Experience the power of Edge TTS for text-to-speech conversion, and explore our advanced Text-to-Video Converter for even more creative possibilities!",
        analytics_enabled=False,
        allow_flagging="manual",
        api_name=None,
        theme="default"
    )

    demo.css = CUSTOM_CSS
    return demo

async def main():
    demo = await create_demo()
    demo.queue(default_concurrency_limit=5)
    demo.launch(show_api=False)

if __name__ == "__main__":
    asyncio.run(main())