Update app.py

app.py

@@ -8,8 +8,6 @@ import PIL.Image
 import mss
 from google import genai
 from google.genai import types
-from pydub import AudioSegment
-from pydub.playback import play
 import soundfile as sf
 
 # Configuration
@@ -78,12 +76,9 @@ class GeminiTTS:
                 turn = session.receive()
                 async for response in turn:
                     if data := response.data:
-                        # Convert to playable audio format
+                        # Convert to numpy array for Gradio Audio component
                         audio_array = np.frombuffer(data, dtype=np.float32)
-                        with io.BytesIO() as wav_buffer:
-                            sf.write(wav_buffer, audio_array, SAMPLE_RATE, format='WAV')
-                            wav_bytes = wav_buffer.getvalue()
-                        return (SAMPLE_RATE, wav_bytes)
+                        return (SAMPLE_RATE, audio_array)
                     if text := response.text:
                         return text