Update app.py

app.py

@@ -6,6 +6,7 @@ tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_
 zh_tts = TTS(model_name="tts_models/zh-CN/baker/tacotron2-DDC-GST", progress_bar=False, gpu=False)
 # de_tts = TTS(model_name = "tts_models/de/thorsten/vits", gpu=False)
 de_tts = TTS(model_name = "tts_models/de/thorsten/tacotron2-DCA", gpu=False)
+es_tts = TTS(model_name = "tts_models/es/mai/tacotron2-DCA", progress_bar=False, gpu=False)
 
 def text_to_speech(text: str, speaker_wav, speaker_wav_file, language: str):
     if speaker_wav_file and not speaker_wav:
@@ -17,10 +18,15 @@ def text_to_speech(text: str, speaker_wav, speaker_wav_file, language: str):
         # else:
         zh_tts.tts_to_file(text, file_path=file_path)
     elif language == "de":
-        if speaker_wav is not None:
-            de_tts.tts_to_file(text, speaker_wav=speaker_wav, file_path=file_path)
-        else:
-            de_tts.tts_to_file(text, file_path=file_path)
+        # if speaker_wav is not None:
+        #     de_tts.tts_to_file(text, speaker_wav=speaker_wav, file_path=file_path)
+        # else:
+        de_tts.tts_to_file(text, file_path=file_path)
+    elif language == "es":
+        # if speaker_wav is not None:
+        #     es_tts.tts_to_file(text, speaker_wav=speaker_wav, file_path=file_path)
+        # else:
+        es_tts.tts_to_file(text, file_path=file_path)
     else:
         if speaker_wav is not None:
             tts.tts_to_file(text, speaker_wav=speaker_wav, language=language, file_path=file_path)
@@ -31,7 +37,7 @@ def text_to_speech(text: str, speaker_wav, speaker_wav_file, language: str):
 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", type="filepath"), 
-            gr.Radio(label="Language", choices=["en", "zh-CN", "fr-fr", "de"], value="en")]
+            gr.Radio(label="Language", choices=["en", "zh-CN", "fr-fr", "de", "es"], value="en")]
 outputs = gr.Audio(label="Output")
 
 demo = gr.Interface(fn=text_to_speech, inputs=inputs, outputs=outputs)