Update app.py

app.py

@@ -3,6 +3,9 @@ import gradio as gr
 
 
 from huggingface_hub import snapshot_download
+import numpy as np
+from scipy.io import wavfile
+
 
 
 
@@ -34,6 +37,12 @@ def infer(prompt):
     # It assumes that you have a speaker file in `bark_voices/speaker_n/speaker.wav` or `bark_voices/speaker_n/speaker.npz`
     output_dict = model.synthesize(text, config, speaker_id="speaker", voice_dirs="bark_voices/")
     print(output_dict)
-    return "done"
 
-gr.Interface(fn=infer, inputs=[gr.Textbox()], outputs=[gr.Textbox()]).launch()
+    sample_rate = 44100  # Replace with the actual sample rate
+
+    wavfile.write('output.wav', sample_rate, output_dict['wav'])
+
+   
+    return "output.wav"
+
+gr.Interface(fn=infer, inputs=[gr.Textbox()], outputs=[gr.Audio()]).launch()