metadata

title: PDF2Audio
app_file: app.py
sdk: gradio
sdk_version: 4.44.0

PDF to Audio Converter

This code can be used to convert PDFs into audio podcasts, lectures, summaries, and more. It uses OpenAI's GPT models for text generation and text-to-speech conversion. You can also edit a draft transcript (multiple times) and provide specific comments, or overall directives on how it could be adapted or improved.

Features

Upload multiple PDF files
Choose from different instruction templates (podcast, lecture, summary, etc.)
Customize text generation and audio models
Select different voices for speakers
Iterate on the draft via specific or general commments, and/or edits to the transcript and specific feedback to the model for improvements

Use in Colab

Local Installation

Follow these steps to set up PDF2Audio on your local machine using Conda:

Clone the repository:

git clone https://github.com/lamm-mit/PDF2Audio.git
cd PDF2Audio

Install Miniconda (if you haven't already):
- Download the installer from Miniconda website
- Follow the installation instructions for your operating system
- Verify the installation:
```
conda --version
```
Create a new Conda environment:
```
conda create -n pdf2audio python=3.9
```
Activate the Conda environment:
```
conda activate pdf2audio
```
Install the required dependencies:
```
pip install -r requirements.txt
```
Set up your OpenAI API key: Create a .env file in the project root directory and add your OpenAI API key:
```
OPENAI_API_KEY=your_api_key_here
```

Running the App

To run the PDF2Audio app:

Ensure you're in the project directory and your Conda environment is activated:
```
conda activate pdf2audio
```
Run the Python script that launches the Gradio interface:
```
python app.py
```
Open your web browser and go to the URL provided in the terminal (typically http://127.0.0.1:7860).
Use the Gradio interface to upload a PDF file and convert it to audio.

How to Use

Upload one or more PDF files
Select the desired instruction template
Customize the instructions if needed
Click "Generate Audio" to create your audio content

Access via 🤗 Hugging Face Spaces

lamm-mit/PDF2Audio

Example result

Note

This app requires an OpenAI API key to function.

Credits

This project was inspired by and based on the code available at https://github.com/knowsuchagency/pdf-to-podcast and https://github.com/knowsuchagency/promptic.

@article{ghafarollahi2024sciagentsautomatingscientificdiscovery,
    title={SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning}, 
    author={Alireza Ghafarollahi and Markus J. Buehler},
    year={2024},
    eprint={2409.05556},
    archivePrefix={arXiv},
    primaryClass={cs.AI},
    url={https://arxiv.org/abs/2409.05556}, 
}
@article{buehler2024graphreasoning,
    title={Accelerating Scientific Discovery with Generative Knowledge Extraction, Graph-Based Representation, and Multimodal Intelligent Graph Reasoning},
    author={Markus J. Buehler},
    journal={Machine Learning: Science and Technology},
    year={2024},
    url={http://iopscience.iop.org/article/10.1088/2632-2153/ad7228},
}