File size: 1,881 Bytes
b8b16cf 02f8934 b8b16cf 02f8934 b8b16cf 02f8934 b8b16cf 02f8934 b8b16cf 02f8934 b8b16cf 02f8934 b8b16cf 02f8934 b8b16cf 02f8934 b8b16cf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
import gradio as gr
from gtts import gTTS
import pdfplumber
import os
def extract_text_from_pdf(pdf_file):
"""
Extract text from a PDF file using pdfplumber.
Args:
pdf_file: Uploaded PDF file.
Returns:
str: Extracted text from the PDF.
"""
try:
with pdfplumber.open(pdf_file) as pdf:
text = ""
for page in pdf.pages:
text += page.extract_text() or ""
return text if text else "No text could be extracted from the PDF."
except Exception as e:
return f"Error extracting text: {str(e)}"
def text_to_speech(pdf_file, lang="en"):
"""
Convert text from a PDF to speech using gTTS and return the audio file path.
Args:
pdf_file: Uploaded PDF file.
lang (str): Language code (default is 'en' for English).
Returns:
str: Path to the generated audio file or error message.
"""
try:
# Extract text from PDF
text = extract_text_from_pdf(pdf_file)
if "Error" in text:
return text
# Create gTTS object
tts = gTTS(text=text, lang=lang, slow=False)
# Save the audio file
output_file = "output.mp3"
tts.save(output_file)
return output_file
except Exception as e:
return f"An error occurred: {str(e)}"
# Define Gradio interface
demo = gr.Interface(
fn=text_to_speech,
inputs=[
gr.File(label="Upload a PDF file", file_types=[".pdf"]),
gr.Dropdown(choices=["en", "es", "fr"], label="Select Language", value="en")
],
outputs=gr.Audio(label="Generated Speech"),
title="PDF to Speech with gTTS",
description="Upload a PDF file, select a language, and generate speech from the extracted text."
)
# Launch the app
if __name__ == "__main__":
demo.launch() |