Spaces:
Running
Running
| import gradio as gr | |
| from docx import Document # For .docx handling | |
| from fpdf import FPDF # Python-native PDF generation | |
| from gtts import gTTS | |
| # 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) | |
| # Generate the PDF using fpdf | |
| pdf = FPDF() | |
| pdf.add_page() | |
| pdf.set_font("Arial", size=12) | |
| pdf.multi_cell(190, 10, txt=extracted_text) | |
| pdf_output_path = "document_output.pdf" | |
| pdf.output(pdf_output_path) | |
| # 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() | |