adjustments

app.py

@@ -628,24 +628,34 @@ def vevo_tts(text, ref_wav, timbre_ref_wav=None, src_language="en", ref_language
 # 创建Gradio界面
 with gr.Blocks(title="VEVO DEMO") as demo:
     gr.Markdown("# VEVO DEMO")
-    gr.Markdown("## Controllable Zero-Shot Voice Conversion and Style Transfer")
     
     with gr.Tab("Vevo-Timbre"):
         gr.Markdown("### Vevo-Timbre: Maintain style but transfer timbre")
         with gr.Row():
             with gr.Column():
-                timbre_content = gr.Audio(label="Content Audio", type="numpy")
+                timbre_content = gr.Audio(label="Source Audio", type="numpy")
                 timbre_reference = gr.Audio(label="Timbre Reference", type="numpy")
                 timbre_button = gr.Button("Generate")
             with gr.Column():
                 timbre_output = gr.Audio(label="Result")
         timbre_button.click(vevo_timbre, inputs=[timbre_content, timbre_reference], outputs=timbre_output)
-    
+
+    with gr.Tab("Vevo-Style"):
+        gr.Markdown("### Vevo-Style: Maintain timbre but transfer style (accent, emotion, etc.)")
+        with gr.Row():
+            with gr.Column():
+                style_content = gr.Audio(label="Source Audio", type="numpy")
+                style_reference = gr.Audio(label="Style Reference", type="numpy")
+                style_button = gr.Button("Generate")
+            with gr.Column():
+                style_output = gr.Audio(label="Result")
+        style_button.click(vevo_style, inputs=[style_content, style_reference], outputs=style_output)
+
     with gr.Tab("Vevo-Voice"):
         gr.Markdown("### Vevo-Voice: Transfers both style and timbre with separate references")
         with gr.Row():
             with gr.Column():
-                voice_content = gr.Audio(label="Content Audio", type="numpy")
+                voice_content = gr.Audio(label="Source Audio", type="numpy")
                 voice_style_reference = gr.Audio(label="Style Reference", type="numpy")
                 voice_timbre_reference = gr.Audio(label="Timbre Reference", type="numpy")
                 voice_button = gr.Button("Generate")
@@ -653,16 +663,7 @@ with gr.Blocks(title="VEVO DEMO") as demo:
                 voice_output = gr.Audio(label="Result")
         voice_button.click(vevo_voice, inputs=[voice_content, voice_style_reference, voice_timbre_reference], outputs=voice_output)
     
-    with gr.Tab("Vevo-Style"):
-        gr.Markdown("### Vevo-Style: Maintain timbre but transfer style (accent, emotion, etc.)")
-        with gr.Row():
-            with gr.Column():
-                style_content = gr.Audio(label="Content Audio", type="numpy")
-                style_reference = gr.Audio(label="Style Reference", type="numpy")
-                style_button = gr.Button("Generate")
-            with gr.Column():
-                style_output = gr.Audio(label="Result")
-        style_button.click(vevo_style, inputs=[style_content, style_reference], outputs=style_output)
+    
     
     with gr.Tab("Vevo-TTS"):
         gr.Markdown("### Vevo-TTS: Text-to-speech with separate style and timbre references")