import gradio as gr
from docx import Document # For .docx handling
from gtts import gTTS
import os
import pdfkit
# Path to the wkhtmltopdf executable (update this path based on the Dockerfile output)
WKHTMLTOPDF_PATH = "/usr/local/bin/wkhtmltopdf" # You will get this from the Dockerfile output
# Configure pdfkit to use the correct wkhtmltopdf path
config = pdfkit.configuration(wkhtmltopdf=WKHTMLTOPDF_PATH)
# Function to extract text from a .docx file and convert to PDF
def docx_to_pdf(docx_file):
try:
# Extract text from the .docx file
doc = Document(docx_file.name)
full_text = []
for para in doc.paragraphs:
full_text.append(para.text)
extracted_text = '\n'.join(full_text)
# Convert the extracted text into an HTML format for pdfkit
html_content = f"""
{extracted_text}
"""
# Generate the PDF using pdfkit with the custom wkhtmltopdf path
pdf_output_path = "document_output.pdf"
pdfkit.from_string(html_content, pdf_output_path, configuration=config)
# Convert the text to audio using gTTS
tts = gTTS(text=extracted_text, lang='en', slow=False)
audio_output_path = "document_audio.wav"
tts.save(audio_output_path)
return audio_output_path, extracted_text, pdf_output_path
except Exception as e:
return None, f"An error occurred: {str(e)}", None
# Gradio interface
iface = gr.Interface(
fn=docx_to_pdf,
inputs=gr.File(label="Upload .docx File"),
outputs=[gr.Audio(label="Generated Audio"), gr.Textbox(label="Extracted Text"), gr.File(label="Generated PDF")]
)
if __name__ == "__main__":
iface.launch()