File size: 2,182 Bytes
ce74a88 e695abb 303db20 ce74a88 9269376 e695abb 303db20 dd250a3 ce74a88 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 |
# 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() |