File size: 4,017 Bytes
ce74a88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b837136
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e695abb
303db20
ce74a88
 
 
9269376
b837136
 
 
 
 
 
 
 
 
 
 
 
e695abb
303db20
dd250a3
 
 
 
b837136
 
 
 
 
ce74a88
b837136
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c3ee49d
8ea6338
c3ee49d
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
# import gradio as gr
# import requests
# import os

# def function1(prompt):
#     response = requests.post("https://tommy24-testing3.hf.space/run/predict", json={
#       "data": [
#         prompt,
#     ]}).json()
#     message = response["data"][0]
#     url = 'https://api.elevenlabs.io/v1/text-to-speech/pNInz6obpgDQGcFmaJgB'

#     headers = {
#         'accept': 'audio/mpeg',
#         'xi-api-key': os.environ.get("test2"),
#         'Content-Type': 'application/json'
#     }

#     data = {
#         "text": message,
#         "voice_settings": {
#             "stability": 0,
#             "similarity_boost": 0
#         }
#     }

#     response = requests.post(url, headers=headers, json=data)
#     if response.status_code == 200:
#         file_path = 'test.mp3'
#         if os.path.isfile(file_path):
#             os.remove(file_path)
#         with open(file_path, 'wb') as f:
#             f.write(response.content)
#     return "test.mp3"

# iface = gr.Interface(fn=function1, inputs="text", outputs=[gr.Audio(label="Audio",type="numpy")])
# iface.launch()


# import gradio as gr
# import requests
# import urllib.request
# from pydub import AudioSegment
# import numpy as np
# import os

# def function1(prompt):
#     response = requests.post("https://tommy24-testing3.hf.space/run/predict", json={
#       "data": [
#         prompt,
#     ]}).json()
#     data = response["data"][0]
#     response = requests.post("https://matthijs-speecht5-tts-demo.hf.space/run/predict", json={
#         "data": [
#             data,
#             "KSP (male)",
#         ]
#     }).json()
#     data = response["data"][0]["name"]
#     data = "https://matthijs-speecht5-tts-demo.hf.space/file="+data
#     file_name, headers = urllib.request.urlretrieve(data, "speech.mp3")
#     # code = random.randint(1,1000)
#     # generated_file = f"output{code}"
#     filename = "output.mp3"
    
#     if os.path.exists(filename):
#         os.remove(filename)
#     else:
#         pass
#     command = f"ffmpeg -i {file_name} -vn -ar 44100 -ac 2 -b:a 192k output.mp3"
#     os.system(command)
#     return "output.mp3"

# iface = gr.Interface(fn=function1, inputs="text", outputs=[gr.Audio(label="Audio",type="numpy")])
# iface.launch()

import gradio as gr
import requests
import urllib.request
from pydub import AudioSegment
import numpy as np
import os
import sys
import wave
import io
import base64
import azure.cognitiveservices.speech as speechsdk

speech_key = os.environ.get("test3")
service_region = os.environ.get("test4")

speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
# Note: the voice setting will not overwrite the voice element in input SSML.
speech_config.speech_synthesis_voice_name = os.environ.get("test5")

def function1(prompt):
    response = requests.post("https://tommy24-testing3.hf.space/run/predict", json={
      "data": [
        prompt,
    ]}).json()
    message = response["data"][0]
    speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=speech_config)
    result = speech_synthesizer.speak_text_async(message).get()
    if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
        audio_stream = io.BytesIO(result.audio_data)
    
        # Create a wave file object and write the audio data to it
        with wave.open("audio.wav", 'wb') as wave_file:
            wave_file.setnchannels(1)
            wave_file.setsampwidth(2)
            wave_file.setframerate(16000)
            wave_file.writeframesraw(audio_stream.getvalue())
        
        # Use ffmpeg to convert the wave file to an mp3 file
        filename = "output.mp3"
        
        if os.path.exists(filename):
            os.remove(filename)
        else:
            pass
        command = f"ffmpeg -i audio.wav -y -codec:a libmp3lame -qscale:a 2 {filename}"
        os.system(command)
        return "output.mp3"

iface = gr.Interface(fn=function1, inputs="text", outputs=[gr.Audio(label="Audio",type="numpy")])
iface.launch()