Update openvoice_app.py

openvoice_app.py

@@ -52,7 +52,7 @@ def delete_voice(api_key, voice_id):
 
 # Predict function with rate limiting based on IP address
 #@limiter.limit("100 per minute")
-def predict(prompt, style, audio_file_pth):
+def predict(prompt, style, audio_file_pth, voice_name):
     text_hint = ''
     if len(prompt) < 2:
         text_hint += "[ERROR] Please provide a longer prompt text.\n"
@@ -63,7 +63,7 @@ def predict(prompt, style, audio_file_pth):
     
     print(audio_file_pth)
     voice = client.clone(
-        name="TrialVoice",
+        name=voice_name,
         description="A trial voice model for testing",
         files=[audio_file_pth],
     )
@@ -73,16 +73,16 @@ def predict(prompt, style, audio_file_pth):
     
     save_path = f'{output_dir}/output.wav'
     data = get_voices(api_key)
-    # Find all voice IDs with the name "TrialVoice"
-    trial_voice_ids = [voice.get("voice_id") for voice in data['voices'] if voice.get("name") == "TrialVoice"]
+    # Find all voice IDs with the name provided by the user
+    trial_voice_ids = [voice.get("voice_id") for voice in data['voices'] if voice.get("name") == voice_name]
 
-    # # Delete each voice with the name "TrialVoice"
+    # # Delete each voice with the name provided by the user
     # for voice_id in trial_voice_ids:
     #     status_code, response_text = delete_voice(api_key, voice_id)
     #     print(f"Deleted voice ID {voice_id}: Status Code {status_code}, Response {response_text}")
 
     # if not trial_voice_ids:
-    #     print("No voices with the name 'TrialVoice' found.")
+    #     print("No voices with the name provided by the user found.")
 
     return text_hint, save_path, audio_file_pth
 
@@ -108,6 +108,11 @@ with gr.Blocks(gr.themes.Glass()) as demo:
                 value="resources/demo_speaker2.mp3",
                 sources=["upload"],  # Allow only upload
             )
+            voice_name_gr = gr.Textbox(
+                label="Voice Name",
+                info="Name for the cloned voice model.",
+                value="TrialVoice"
+            )
             tts_button = gr.Button("Send", elem_id="send-btn", visible=True)
 
         with gr.Column():
@@ -115,7 +120,7 @@ with gr.Blocks(gr.themes.Glass()) as demo:
             audio_gr = gr.Audio(label="Synthesised Audio", autoplay=True)
             ref_audio_gr = gr.Audio(label="Reference Audio Used")
 
-            tts_button.click(predict, [input_text_gr, style_gr, ref_gr], outputs=[out_text_gr, audio_gr, ref_audio_gr])
+            tts_button.click(predict, [input_text_gr, style_gr, ref_gr, voice_name_gr], outputs=[out_text_gr, audio_gr, ref_audio_gr])
 
     demo.queue()
     demo.launch(debug=True, show_api=False, share=args.share)