Update app.py

app.py

@@ -8,7 +8,9 @@ zh_tts = TTS(model_name="tts_models/zh-CN/baker/tacotron2-DDC-GST", progress_bar
 # fr_tts = TTS(model_name = "tts_models/fr/css10/vits", gpu=False)
 # de_tts = TTS(model_name = "tts_models/de/thorsten/vits", gpu=False)
 
-def text_to_speech(text: str, speaker_wav, language: str):
+def text_to_speech(text: str, speaker_wav, speaker_wav_file, language: str):
+    if speaker_wav_file and not speaker_wav:
+        speaker_wav = speaker_wav_file
     file_path = "output.wav"
     if language == "zh-CN":
         # if speaker_wav is not None:
@@ -33,7 +35,8 @@ def text_to_speech(text: str, speaker_wav, language: str):
     return file_path
 
 inputs = [gr.Textbox(label="Input the text", value="", max_lines=3),
-          gr.Audio(label="Voice to clone", source="microphone", type="filepath"), 
+          gr.Audio(label="Voice to clone", source="microphone", type="filepath"),
+          gr.Audio(label="Voice to clone", type="filepath"), 
             gr.Radio(label="Language", choices=["en", "zh-CN", "fr-fr"], value="en")]
 outputs = gr.Audio(label="Output")