Document-to-podcast: a Blueprint by Mozilla.ai for generating podcasts from documents using local AI

This blueprint demonstrate how you can use open-source models & tools to convert input documents into a podcast featuring two speakers. It is designed to work on most local setups, meaning no external API calls or GPU access is required. This makes it more accessible and privacy-friendly by keeping everything local.

📘 To explore this project further and discover other Blueprints, visit the Blueprints Hub.

Example Results

• Introducing Blueprints

blueprints.mp4

• Attention is All You Need

attention-is-all-you-need.mp4

---

👉 📖 For more detailed guidance on using this project, please visit our Docs.

👉 🔨 Built with

• Python 3.10+ (use Python 3.12 for Apple M1/2/3 chips)
• Llama-cpp
• Streamlit (UI demo)

👉 🧠 Check the Supported Models.

Quick-start

Get started right away using one of the options below:

Google Colab	HuggingFace Spaces	GitHub Codespaces

You can also install and use the blueprint locally:

Command Line Interface

pip install document-to-podcast

document-to-podcast \
--input_file "example_data/Mozilla-Trustworthy_AI.pdf" \
--output_folder "example_data"
--text_to_text_model "Qwen/Qwen2.5-1.5B-Instruct-GGUF/qwen2.5-1.5b-instruct-q8_0.gguf"

Graphical Interface App

git clone https://github.com/mozilla-ai/document-to-podcast.git
cd document-to-podcast
pip install -e .

python -m streamlit run demo/app.py

System requirements

• OS: Windows, macOS, or Linux
• Python 3.10+ / 3.12+ for Apple M chips
• Minimum RAM: 8 GB
• Disk space: 20 GB minimum

Troubleshooting

If you are having issues / bugs, check our Troubleshooting section, before opening a new issue.

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.

Contributing

Contributions are welcome! To get started, you can check out the CONTRIBUTING.md file.