Upload 2 files

app.py

@@ -99,7 +99,8 @@ with gr.Blocks() as demo:
     with gr.Tab("Speech to Speech"):
         with gr.Row():
             with gr.Column():
-                audio_input = gr.Audio(label="Input Audio", source="microphone", type="filepath")
+                # Updated Audio component initialization
+                audio_input = gr.Audio(label="Input Audio", sources=["microphone", "upload"])
                 voice_dropdown_s2s = gr.Dropdown(choices=list(VOICE_LIST.keys()), label="Select Voice")
                 
                 with gr.Row():
@@ -119,4 +120,4 @@ with gr.Blocks() as demo:
             outputs=[audio_output_s2s, text_output]
         )
 
-demo.launch()
+demo.launch()

requirements.txt

@@ -2,3 +2,5 @@ gradio==4.19.2
 elevenlabs==0.2.27
 SpeechRecognition==3.10.1
 pydub==0.25.1
+ffmpeg-python==0.2.0
+python-multipart==0.0.9