fudii0921 commited on
Commit
34977d1
·
verified ·
1 Parent(s): e33c369

Create app.py

Browse files
Files changed (1) hide show
  1. app.py +70 -0
app.py ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+ import edge_tts
3
+ import asyncio
4
+ import tempfile
5
+ import os
6
+
7
+ # Get all available voices
8
+ async def get_voices():
9
+ voices = await edge_tts.list_voices()
10
+ return {f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] for v in voices}
11
+
12
+ # Text-to-speech function
13
+ async def text_to_speech(text, voice, rate, pitch):
14
+ if not text.strip():
15
+ return None, gr.Warning("Please enter text to convert.")
16
+ if not voice:
17
+ return None, gr.Warning("Please select a voice.")
18
+
19
+ voice_short_name = voice.split(" - ")[0]
20
+ rate_str = f"{rate:+d}%"
21
+ pitch_str = f"{pitch:+d}Hz"
22
+ communicate = edge_tts.Communicate(text, voice_short_name, rate=rate_str, pitch=pitch_str)
23
+ with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
24
+ tmp_path = tmp_file.name
25
+ await communicate.save(tmp_path)
26
+ return tmp_path, None
27
+
28
+ # Gradio interface function
29
+ def tts_interface(text, voice, rate, pitch):
30
+ audio, warning = asyncio.run(text_to_speech(text, voice, rate, pitch))
31
+ return audio, warning
32
+
33
+ # Create Gradio application
34
+ import gradio as gr
35
+
36
+ async def create_demo():
37
+ voices = await get_voices()
38
+
39
+ description = """
40
+ Convert text to speech using Microsoft Edge TTS. Adjust speech rate and pitch: 0 is default, positive values increase, negative values decrease.
41
+
42
+
43
+
44
+
45
+ """
46
+
47
+ demo = gr.Interface(
48
+ fn=tts_interface,
49
+ inputs=[
50
+ gr.Textbox(label="Input Text", lines=5),
51
+ gr.Dropdown(choices=[""] + list(voices.keys()), label="Select Voice", value=""),
52
+ gr.Slider(minimum=-50, maximum=50, value=0, label="Speech Rate Adjustment (%)", step=1),
53
+ gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1)
54
+ ],
55
+ outputs=[
56
+ gr.Audio(label="Generated Audio", type="filepath"),
57
+ gr.Markdown(label="Warning", visible=False)
58
+ ],
59
+ title="Edge TTS Text-to-Speech",
60
+ description=description,
61
+
62
+ analytics_enabled=False,
63
+ allow_flagging="manual"
64
+ )
65
+ return demo
66
+
67
+ # Run the application
68
+ if __name__ == "__main__":
69
+ demo = asyncio.run(create_demo())
70
+ demo.launch()