File size: 8,767 Bytes
bcc6ddf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
244
245
246
import os
import scipy
import nltk
import tempfile
import numpy as np
from bark.generation import preload_models, SAMPLE_RATE
from bark import generate_audio
from scipy.io import wavfile

import gradio as gr
nltk.download('punkt')
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
preload_models()



def generate_audio_from_text(text,language_prompt,speaker_prompt):
    if language_prompt == "english":
        if speaker_prompt=="speaker 1":
            history_prompt = "v2/en_speaker_0"
        elif speaker_prompt=="speaker 2":
          history_prompt = "v2/en_speaker_1"
        elif speaker_prompt=="speaker 3":
          history_prompt = "v2/en_speaker_2"
        elif speaker_prompt=="speaker 4":
          history_prompt = "v2/en_speaker_3"
        elif speaker_prompt=="speaker 5":
          history_prompt = "v2/en_speaker_4"
        elif speaker_prompt=="speaker 6":
          history_prompt = "v2/en_speaker_5"
        elif speaker_prompt=="speaker 7":
          history_prompt = "v2/en_speaker_6"
        elif speaker_prompt=="speaker 8":
          history_prompt = "v2/en_speaker_7"
        elif speaker_prompt=="speaker 9":
          history_prompt = "v2/en_speaker_8"
        elif speaker_prompt=="speaker 10":
          history_prompt = "v2/en_speaker_9"
        else:
            history_prompt = "v2/en_speaker_9"

    elif language_prompt == "french":
        if speaker_prompt=="speaker 1":
          history_prompt = "v2/fr_speaker_0"
        elif speaker_prompt=="speaker 2":
          history_prompt = "v2/fr_speaker_1"
        elif speaker_prompt=="speaker 3":
          history_prompt = "v2/fr_speaker_2"
        elif speaker_prompt=="speaker 4":
          history_prompt = "v2/fr_speaker_3"
        elif speaker_prompt=="speaker 5":
          history_prompt = "v2/fr_speaker_4"
        elif speaker_prompt=="speaker 6":
          history_prompt = "v2/fr_speaker_5"
        elif speaker_prompt=="speaker 7":
          history_prompt = "v2/fr_speaker_6"
        elif speaker_prompt=="speaker 8":
          history_prompt = "v2/fr_speaker_7"
        elif speaker_prompt=="speaker 9":
          history_prompt = "v2/fr_speaker_8"
        elif speaker_prompt=="speaker 10":
          history_prompt = "v2/fr_speaker_9"
        else:
            history_prompt = "v2/fr_speaker_9"

    elif language_prompt =="german":
        if speaker_prompt=="speaker 1":
          history_prompt = "v2/de_speaker_0"
        elif speaker_prompt=="speaker 2":
          history_prompt = "v2/de_speaker_1"
        elif speaker_prompt=="speaker 3":
          history_prompt = "v2/de_speaker_2"
        elif speaker_prompt=="speaker 4":
          history_prompt = "v2/de_speaker_3"
        elif speaker_prompt=="speaker 5":
          history_prompt = "v2/de_speaker_4"
        elif speaker_prompt=="speaker 6":
          history_prompt = "v2/de_speaker_5"
        elif speaker_prompt=="speaker 7":
          history_prompt = "v2/de_speaker_6"
        elif speaker_prompt=="speaker 8":
          history_prompt = "v2/de_speaker_7"
        elif speaker_prompt=="speaker 9":
          history_prompt = "v2/de_speaker_8"
        elif speaker_prompt=="speaker 10":
          history_prompt = "v2/de_speaker_9"
        else:
            history_prompt = "v2/de_speaker_9"

    elif language_prompt =="hindi":
        if speaker_prompt=="speaker 1":
          history_prompt = "v2/hi_speaker_0"
        elif speaker_prompt=="speaker 2":
          history_prompt = "v2/hi_speaker_1"
        elif speaker_prompt=="speaker 3":
          history_prompt = "v2/hi_speaker_2"
        elif speaker_prompt=="speaker 4":
          history_prompt = "v2/hi_speaker_3"
        elif speaker_prompt=="speaker 5":
          history_prompt = "v2/hi_speaker_4"
        elif speaker_prompt=="speaker 6":
          history_prompt = "v2/hi_speaker_5"
        elif speaker_prompt=="speaker 7":
          history_prompt = "v2/hi_speaker_6"
        elif speaker_prompt=="speaker 8":
          history_prompt = "v2/hi_speaker_7"
        elif speaker_prompt=="speaker 9":
          history_prompt = "v2/hi_speaker_8"
        elif speaker_prompt=="speaker 10":
          history_prompt = "v2/hi_speaker_9"
        else:
            history_prompt = "v2/hi_speaker_9"

    elif language_prompt =="chinese":
        if speaker_prompt=="speaker 1":
          history_prompt = "v2/zh_speaker_0"
        elif speaker_prompt=="speaker 2":
          history_prompt = "v2/zh_speaker_1"
        elif speaker_prompt=="speaker 3":
          history_prompt = "v2/zh_speaker_2"
        elif speaker_prompt=="speaker 4":
          history_prompt = "v2/zh_speaker_3"
        elif speaker_prompt=="speaker 5":
          history_prompt = "v2/zh_speaker_4"
        elif speaker_prompt=="speaker 6":
          history_prompt = "v2/zh_speaker_5"
        elif speaker_prompt=="speaker 7":
          history_prompt = "v2/zh_speaker_6"
        elif speaker_prompt=="speaker 8":
          history_prompt = "v2/zh_speaker_7"
        elif speaker_prompt=="speaker 9":
          history_prompt = "v2/zh_speaker_8"
        elif speaker_prompt=="speaker 10":
          history_prompt = "v2/zh_speaker_9"
        else:
            history_prompt = "v2/zh_speaker_9"

    elif language_prompt =="italian":
        if speaker_prompt=="speaker 1":
          history_prompt = "v2/it_speaker_0"
        elif speaker_prompt=="speaker 2":
          history_prompt = "v2/it_speaker_1"
        elif speaker_prompt=="speaker 3":
          history_prompt = "v2/it_speaker_2"
        elif speaker_prompt=="speaker 4":
          history_prompt = "v2/it_speaker_3"
        elif speaker_prompt=="speaker 5":
          history_prompt = "v2/it_speaker_4"
        elif speaker_prompt=="speaker 6":
          history_prompt = "v2/it_speaker_5"
        elif speaker_prompt=="speaker 7":
          history_prompt = "v2/it_speaker_6"
        elif speaker_prompt=="speaker 8":
          history_prompt = "v2/it_speaker_7"
        elif speaker_prompt=="speaker 9":
          history_prompt = "v2/it_speaker_8"
        elif speaker_prompt=="speaker 10":
          history_prompt = "v2/it_speaker_9"
        else:
            history_prompt = "v2/it_speaker_9"
            
    elif language_prompt =="japanese":
        if speaker_prompt=="speaker 1":
          history_prompt = "v2/ja_speaker_0"
        elif speaker_prompt=="speaker 2":
          history_prompt = "v2/ja_speaker_1"
        elif speaker_prompt=="speaker 3":
          history_prompt = "v2/ja_speaker_2"
        elif speaker_prompt=="speaker 4":
          history_prompt = "v2/ja_speaker_3"
        elif speaker_prompt=="speaker 5":
          history_prompt = "v2/ja_speaker_4"
        elif speaker_prompt=="speaker 6":
          history_prompt = "v2/ja_speaker_5"
        elif speaker_prompt=="speaker 7":
          history_prompt = "v2/ja_speaker_6"
        elif speaker_prompt=="speaker 8":
          history_prompt = "v2/ja_speaker_7"
        elif speaker_prompt=="speaker 9":
          history_prompt = "v2/ja_speaker_8"
        elif speaker_prompt=="speaker 10":
          history_prompt = "v2/ja_speaker_9"
        else:
            history_prompt = "v2/ja_speaker_9"
    else:
        raise ValueError("Invalid language or gender selection")

    sentences = nltk.sent_tokenize(text)
    silence = np.zeros(int(0.25 * SAMPLE_RATE))  # quarter second of silence

    pieces = []
    for sentence in sentences:
        audio_array = generate_audio(sentence, history_prompt=history_prompt)
        pieces += [audio_array]

    # Concatenate the audio pieces
    final_audio = np.concatenate(pieces)

    # Save the audio to a WAV file
    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_wav:
        wavfile.write(temp_wav.name, SAMPLE_RATE, final_audio)

    # Return the saved audio file
    return temp_wav.name

# Define lists of language and gender options
language_options = [
    "english",
    "french",
    "german",
    "hindi",
    "chinese",
    "italian",
    "japanese",


]

speaker_options=[
    "speaker 1",
    "speaker 2",
    "speaker 3",
    "speaker 4",
    "speaker 5",
    "speaker 6",
    "speaker 7",
    "speaker 8",
    "speaker 9",
    "speaker 10",
]
# Create a Gradio interface with text input and dropdown menus for language and gender
iface = gr.Interface(
    fn=generate_audio_from_text,
    inputs=[
        gr.Textbox(text="Enter text to convert to speech:"),
        gr.Dropdown(choices=language_options, label="Select language:"),
        gr.Dropdown(choices=speaker_options, label="Select speaker:"),
    ],
    outputs=gr.outputs.File(label="Download WAV File"),
    title="Text-to-Speech App Vertical Solution",
    timeout=300,
)

# Launch the Gradio app with sharing enabled
iface.launch(debug=True, enable_queue=True)