Update app.py

app.py

@@ -3,9 +3,16 @@ from PIL import Image
 from groq import Groq
 import os
 
-st.image('endesa.jpeg', caption="", use_column_width=False)
 st.image('calamo.png', caption="", use_column_width=False)
 
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+import scipy.io.wavfile
+
+synthesizer = pipeline("text-to-speech", "suno/bark")
+
+
+
 client = Groq(
     api_key=os.environ.get("GROQ_API_KEY"),
 )
@@ -13,10 +20,8 @@ client = Groq(
 st.write("# Inicio")
 
 # Other content of your app
-st.title("plAIn")
+st.title("plAIn Voice")
 # Add more components here
-# Create a text input widget
-user_input = st.text_input('Pega tu texto:', '')
 
 # Define a function to process the input
 def process_text(input_text):
@@ -41,9 +46,25 @@ def process_text(input_text):
     model="mixtral-8x7b-32768",
 )
     return (chat_completion.choices[0].message.content)
+def generate_audio(input_text):
+    tts = process_text(input_text)
+    speech = synthesizer(tts, forward_params={"do_sample": True})
+    scipy.io.wavfile.write("bark_out.wav", rate=speech["sampling_rate"], data=speech["audio"])
+    return "bark_out.wav"
+    
+user_input = st.text_input("Pega un texto para aclararlo y escuchar una lectura.")
+
+if st.button('Convert'):
+    if user_input == "":
+        st.write("Please enter some text")
+    else:
+        speech_file = text_to_speech(user_input)
+        st.audio(speech_file, format='audio/wav')    
+    
+    
 
-# Call the function with the user input
+'''# Call the function with the user input
 processed_output = process_text(user_input)
 
 # Display the processed output
-st.write('Texto procesado:', processed_output)
+st.write('Texto procesado:', processed_output)'''