├── .python-version
├── main.png
├── requirements.txt
├── .vscode
    └── settings.json
├── README.md
└── main.py


/.python-version:
--------------------------------------------------------------------------------
1 | 
2 | grad
3 | 


--------------------------------------------------------------------------------
/main.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/salma71/text_speech/HEAD/main.png


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | 
2 | gradio
3 | gTTS==2.2.1
4 | pdfminer.six==20201018
5 | 


--------------------------------------------------------------------------------
/.vscode/settings.json:
--------------------------------------------------------------------------------
1 | {
2 |     "editor.fontSize": 16,
3 |     "python.pythonPath": "./venv/bin/python"
4 | }


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Text to Speech using Gradio
 2 | 
 3 | ![Main image](main.png)
 4 | 
 5 | Convert pdf files into spoken audio using google text to speech package and building a user-friendly ready-made interface using [Gradio package](https://www.gradio.app/). 
 6 | 
 7 | ## Installation
 8 | 
 9 | Fork or clone the repo and run 
10 | 
11 | ```bash
12 | pip install -rrequirements.txt
13 | ```
14 | 
15 | ## Usage
16 | 
17 | Follow a step-by-step guide tutorial in that Medium article!
18 | 
19 | ```
20 | 
21 | ## Contributing
22 | 
23 | Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
24 | 
25 | Please make sure to update tests as appropriate.
26 | 
27 | ## License
28 | 
29 | [MIT](https://choosealicense.com/licenses/mit/)
30 | 


--------------------------------------------------------------------------------
/main.py:
--------------------------------------------------------------------------------
 1 | from gtts import gTTS
 2 | from pdfminer.high_level import extract_text
 3 | import gradio as gr
 4 | import os
 5 | 
 6 | 
 7 | def pdf_to_text(file_obj):
 8 |     text = extract_text(file_obj.name)
 9 |     myobj = gTTS(text=text, lang='en', slow=False) 
10 |     myobj.save("test.wav") 
11 |     return 'test.wav'
12 | 
13 | 
14 | examples = [
15 |     [os.path.abspath("short-pdf.pdf")],
16 |     [os.path.abspath("long-pdf.pdf")]
17 | ]
18 | 
19 | 
20 | iface = gr.Interface(fn = pdf_to_text,
21 |                      inputs = 'file',
22 |                      outputs = 'audio', 
23 |                      verbose = True,
24 |                      title = 'PDF to Audio Application',
25 |                      description = 'A simple application to convert PDF files in audio speech. Upload your own file, or click one of the examples to load them.',
26 |                      article = 
27 |                         '''<div>
28 |                             <p style="text-align: center"> All you need to do is to upload the pdf file and hit submit, then wait for compiling. After that click on Play/Pause for listing to the audio. The audio is saved in a wav format.</p>
29 |                         </div>''',
30 |                      examples=examples
31 |                     )
32 | 
33 | iface.launch()
34 | 


--------------------------------------------------------------------------------