File size: 1,954 Bytes
32e218a
989f593
32e218a
989f593
32e218a
989f593
 
 
 
e30c131
989f593
 
 
 
 
e30c131
 
989f593
e30c131
 
2176d40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
989f593
 
 
e30c131
989f593
2176d40
989f593
 
 
 
2176d40
 
989f593
 
 
 
 
 
32e218a
2176d40
989f593
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
import gradio as gr
from TTS.api import TTS

tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False, gpu=False)

def predict(text):
    file_path = "output.wav"
    tts.tts_to_file(text, speaker=tts.speakers[0], language="en", file_path=file_path)
    return file_path

demo = gr.Interface(
    fn=predict,
    inputs='text',
    outputs='audio'
)


demo.launch()


# import requests
# import time
# import tempfile
# import os

# token = os.environ['apikey']
# #discord_id = os.environ['discord-id']
# API_HOST = "https://labs-proxy.voicemod.net/"

# def download_file(url):
#     response = requests.get(url)
#     if response.status_code == 200:
#         with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
#             tmp_file.write(response.content)
#             tmp_file.flush()
#             return tmp_file.name
#     else:
#         print("Error: Unable to download file")

# def tts(text):
#     url = API_HOST + "api/v1/tts/create"
#     payload = {
#         "text": text[:200] if len(text) > 200 else text,
#         "voiceId": "6926ecc5-ff5e-47c6-912b-3ffdb880bf56" # Narrator
#     }
#     headers = {
#         'x-api-key': token,
#     }
#     response = requests.request("POST", url, headers=headers, json=payload)
#     jsonResp = response.json()

#     return gr.make_waveform(download_file(jsonResp['audioUrl']))

# demo = gr.Interface(
#     fn=tts,
#     inputs="text",
#     outputs="audio"
# )

# demo.launch()

# import openai
# import os
# #from pymongo import MongoClient

# api_key = os.environ.get("OPENAI_API_KEY")

# def transcribe_audio(filepath):
#     audio = open(filepath, "rb")
#     transcript = openai.Audio.transcribe("whisper-1", audio)
#     return transcript['text']
    

# # Create a Gradio Tabbed Interface
# iface = gr.Interface(
#     fn=transcribe_audio,
#     inputs= gr.Audio(source="upload", type="filepath"),
#     outputs="text",
# )


# iface.launch()