Create app.py

app.py

@@ -0,0 +1,53 @@
+import gradio as gr
+import tempfile
+import azure.cognitiveservices.speech as speechsdk
+first_alert = "first.wav"
+next_alert = "next.wav"
+
+def Txt_To_Speech(SpeechRegion, SpeechKey, statements):
+    if (SpeechRegion == '' or SpeechKey == '' or statements == ''):
+        output= first_alert
+    else:
+        try:
+           speech_config = speechsdk.SpeechConfig(subscription= SpeechKey, region=SpeechRegion)
+           audio_config = speechsdk.audio.AudioOutputConfig(use_default_speaker=True)
+
+           speech_config.speech_synthesis_voice_name='en-US-JennyNeural'
+
+           speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=speech_config, audio_config=audio_config)
+
+           text = tuple(statements)
+           
+           with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as temp_file:
+            temp_file.write(speech_synthesizer.speak_text_async(text).get())
+
+            temp_file_path = temp_file.name
+           output = temp_file_path 
+        except :
+           output = next_alert
+    return output
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# TTS Text To Speech using OpenAI ")
+
+    text1 = gr.Textbox(type = 'password',label="Enter your Speech Region", placeholder="Speech Region", lines=1)
+    
+    text2 = gr.Textbox(label="SpeechKey",placeholder="Enter your Speech Key")
+    text3 = gr.Textbox(label="Inputs",placeholder="Enter your Inputs")
+
+
+    
+        
+    
+    gr.Interface(
+        Txt_To_Speech,
+        [
+            text1,text2,text3
+        ],
+        outputs=gr.Audio(label="Speech Output")
+    )
+
+    
+
+demo.launch()