typo 2

app.py

@@ -104,7 +104,7 @@ def speaking(audio: np.ndarray, sampling_rate: int):
     audio_buffer = io.BytesIO()
     
     audio = AudioSegment(
-        data.tobytes(),
+        audio.tobytes(),
         frame_rate=sampling_rate,
         sample_width=data.dtype.itemsize,
         channels=(1 if len(data.shape) == 1 else data.shape[1]),
@@ -180,7 +180,7 @@ with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column():
             input_audio = gr.Audio(
-                label="Input Audio", sources="microphone", type="filepath"
+                label="Input Audio", sources="microphone", type="numpy"
             )
         with gr.Column():
             output_audio = gr.Audio(label="Output Audio", streaming=True, autoplay=True)