Welcome to audioarxiv’s documentation!

audioarxiv

audioarxiv is a Python package designed to make staying up to date with the latest research more accessible and convenient. It allows you to fetch research papers directly from arXiv and converts them into speech, so you can listen to them on the go—whether you’re commuting, working out, or simply prefer auditory learning. With support for customizable text-to-speech settings and a streamlined interface, audioarxiv offers researchers, students, and enthusiasts a hands-free way to engage with scientific literature.

Please note: the package is still in its early stages of development, and some features may be limited or not fully mature yet.

Contents

• Installation
• User Guide
• Release Notes

API:

audio	Handles text-to-speech conversion using various engines to read research papers aloud.
preprocess	Processes and cleans the extracted text from papers, including sentence segmentation, symbol handling, and formatting for better audio output.
resources	Fetches research papers and metadata from arXiv using the arXiv API.

Indices and tables

• Index

• Module Index

• Search Page