Update app.py

app.py

@@ -1,17 +1,18 @@
 import gradio as gr
 import openai
+import winsound
 from elevenlabslib import *
 from pydub import AudioSegment
-from elevenlabs import play
+from pydub.playback import play
 import io
-#import winsound
+import config
 
-openai.api_key = "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"
-api_key = "929b67c6e533e94018a438d70c960b60"
+openai.api_key = config.OPENAI_API_KEY
+api_key = config.ELEVENLABS_API_KEY
 from elevenlabslib import ElevenLabsUser
 user = ElevenLabsUser(api_key)
 
-messages = ["Respond with voice"]
+messages = ["Respond in less than 60 words"]
 
 def transcribe(audio):
     global messages
@@ -33,24 +34,23 @@ def transcribe(audio):
     system_message = response["choices"][0]["text"]
     messages.append(f"{system_message}")
 
-    voice = user.get_voices_by_name("Bella")[0]
+    voice = user.get_voices_by_name("Antoni")[0]
     audio = voice.generate_audio_bytes(system_message)
 
     audio = AudioSegment.from_file(io.BytesIO(audio), format="mp3")
     audio.export("output.wav", format="wav")
 
-    #winsound.PlaySound("output.wav", winsound.SND_FILENAME)
-    audio = generate(text = system_message, voice = voice)
-    play(audio)
+    winsound.PlaySound("output.wav", winsound.SND_FILENAME)
 
     chat_transcript = "\n".join(messages)
     return chat_transcript
 
 iface = gr.Interface(
     fn=transcribe,
-    inputs=gr.Audio(source="microphone", type="filepath"),
+    inputs=gr.Audio(source="microphone", type="filepath", placeholder="Please start speaking..."),
     outputs="text",
-    title="Voice Assistant",
+    title="Voice Assistant ",
+    description="Please ask me your question",
 )
 
 iface.launch()