audioarxiv 0.1.2

Turn arXiv papers into audio. audioarxiv lets you fetch the research papers from arXiv and read them aloud.

🎧 audioarxiv

📚 Documentation: https://isaac-cf-wong.github.io/audioarxiv/

Turn arXiv papers into audio. audioarxiv lets you fetch the research papers from arXiv and read them aloud.

---

🚀 Features

• 🔍 Search and retrieve papers using the arXiv API
• 📄 Extract and parse the content from PDF (excluding title/abstract)
• 🗣️ Convert text to speech with natural voice output
• 🧠 Great for passive learning while commuting or doing chores

---

📦 Installation

Install from PyPI:

pip install audioarxiv

Install from Conda:

conda install -c conda-forge audioarxiv

---

🛠 Usage

audioarxiv --id "<arxiv id>"

🎙️ Text-to-Speech Options

You can customize the voice engine using pyttsx3 by specifying the speaking rate, volume, voice, and pause between sentences.

audioarxiv --id "<arxiv id>" --rate <rate> --volume <volume> --voice "<voice>" --pause-seconds <pause-seconds>

• rate: Number of words per minutes. Defaults to 140.
• volume: Volume of the audio. Defaults to 0.9.
• voice: Voice of the audio. Defaults to the pyttsx3 default voice.
• pause-seconds: Number of seconds to pause between sentences.

The settings are saved, so you only need to provide your preferred settings once.

Contributing

Contributions and suggestions are welcome! Whether it's fixing bugs, improving documentation, or adding new features, your help is appreciated.

Please read our Code of Conduct before contributing.

To get started:

• Fork the repository
• Create a new branch for your changes
• Submit a pull request

If you're unsure where to begin, feel free to open an issue or ask for guidance!