audio_output

app.py

@@ -2,6 +2,8 @@ import os
 import gradio as gr
 from openai import OpenAI
 import json
+from transformers import pipeline
+import soundfile as sf
 
 
 OPEN_AI_KEY = os.getenv("OPEN_AI_KEY")
@@ -265,6 +267,24 @@ def paragraph_save(refine_paragraph):
     """
     return refine_paragraph
 
+def paragraph_save_and_tts(paragraph_text):
+    """
+    Saves the paragraph text and generates an audio file using Hugging Face's TTS.
+    """
+    # Instantiate the text-to-speech pipeline
+    tts = pipeline("text-to-speech", model="facebook/fastspeech2-en-ljspeech")
+
+    # Generate speech
+    speech = tts(paragraph_text)
+
+    # Define the path for the audio file
+    audio_path = "/mnt/data/generated_audio.wav"
+
+    # Save the audio file
+    sf.write(audio_path, speech["array"], speech["sampling_rate"])
+
+    # Return the path to the audio file along with the text
+    return paragraph_text, audio_path
 
 with gr.Blocks() as demo:
     with gr.Row():
@@ -462,7 +482,7 @@ with gr.Blocks() as demo:
             gr.Markdown("## 11. Save and Share")
             paragraph_save_button = gr.Button("Save and Share")
             paragraph_save_output = gr.Textbox(label="Save and Share")
-  
+            audio_output = gr.Audio(label="Generated Speech")
 
 
 
@@ -588,7 +608,10 @@ with gr.Blocks() as demo:
             correct_grammatical_spelling_errors_output,
             refine_output
         ],
-        output=paragraph_save_output
+        output=[
+            paragraph_save_output, 
+            audio_output
+        ]
     )
 
 demo.launch()

requirements.txt

@@ -1,3 +1,4 @@
 gradio
 openai>=1.0.0
-
+transformers
+soundfile