Update app.py

app.py

@@ -50,16 +50,16 @@ iface = gr.Interface(
         "Text to Speech": text_to_speech,
         "Speech to Speech": speech_to_speech
     },
-    inputs={
-        "Speech to Text": gr.inputs.Audio(source="upload", type="file"),
-        "Text to Speech": gr.inputs.Textbox(label="Text"),
-        "Speech to Speech": [gr.inputs.Audio(source="upload", type="file"), gr.inputs.Textbox(label="Target Text")]
-    },
-    outputs={
-        "Speech to Text": gr.outputs.Textbox(label="Transcription"),
-        "Text to Speech": gr.outputs.Audio(type="file", label="Synthesized Speech"),
-        "Speech to Speech": gr.outputs.Audio(type="file", label="Synthesized Speech")
-    },
+    inputs=[
+        gr.Audio(source="upload", type="file", label="Speech to Text"),
+        gr.Textbox(label="Text to Speech"),
+        gr.Audio(source="upload", type="file", label="Speech to Speech Input") + gr.Textbox(label="Target Text for Speech to Speech")
+    ],
+    outputs=[
+        gr.Textbox(label="Transcription"),
+        gr.Audio(label="Synthesized Speech"),
+        gr.Audio(label="Speech to Speech Output")
+    ],
     title="Speech Processing Application",
     description="This app uses Facebook's Wav2Vec 2.0 for speech-to-text and VITS for text-to-speech.",
     layout="vertical"