Skip to content
SPECIFICTION
Get listed

Mozilla Document-to-Podcast

github.com

WindowsmacOSLinuxSelf-hosted
Visit github.com
Spec score 7.4 #15 of 23 in AI Podcast Generators

What it is

Mozilla Document-to-Podcast is an open-source Mozilla.ai blueprint that turns documents into two-speaker podcasts. Its workflow extracts and cleans text, uses a language model to create a conversational script, then generates speech audio. The CLI accepts PDF, HTML, TXT, DOCX and Markdown files, and saves podcast.txt and podcast.wav in the selected output folder. Users can customize prompts, speakers, voice profiles and model settings, and select text models that load with llama.cpp; Kokoro-82M is supported out of the box for text-to-speech. The project offers a command-line interface and a Streamlit demo app, with installation through PyPI or an editable clone. It is designed for local processing without external API calls or GPU access. The stated requirements include Windows, macOS or Linux, Python 3.10 or later (3.12 or later for Apple M chips), at least 8 GB RAM and 20 GB disk space. When cleaned text exceeds the model's context-based character limit, the CLI may use only part of the input.

Spec sheet

Purpose
Document-to-Podcast is a Mozilla.ai Blueprint for turning input documents into podcasts featuring two speakers.Read 7 Oct 2026 · github.com
Privacy
The project describes local processing without external API calls as a way to keep processing local and make it more privacy-friendly.Read 4 Oct 2026 · github.com
Support
The README directs users with issues to the troubleshooting documentation before opening a new issue, and the docs invite questions on Discord.Read 7 Oct 2026 · github.com
License
The project is licensed under Apache 2.0.Read 7 Oct 2026 · github.com
Cloud setup options
The getting-started guide lists Google Colab, GitHub Codespaces, and local installation as setup options.Read 7 Oct 2026 · mozilla-ai.github.io
Customization
Users can customize the script prompt, speakers, voice profiles, and model settings.Read 4 Oct 2026 · mozilla-ai.github.io
Document formats
The documented pipeline accepts PDF, HTML, TXT, DOCX, and Markdown files.Read 7 Oct 2026 · mozilla-ai.github.io
Input formats
The CLI accepts PDF, HTML, TXT, DOCX, and Markdown files.Read 4 Oct 2026 · mozilla-ai.github.io
Installation
The project can be installed from PyPI with pip or cloned and installed in editable mode.Read 4 Oct 2026 · mozilla-ai.github.io
Interfaces
The project offers a command-line interface and a Streamlit graphical demo app.Read 7 Oct 2026 · github.com
Local processing
The project is designed to run on local setups without external API calls or GPU access, keeping processing local.Read 7 Oct 2026 · github.com
Model choice
Users can select a text-to-text model loadable by llama.cpp and can use the supported Kokoro-82M text-to-speech model out of the box.Read 7 Oct 2026 · mozilla-ai.github.io
Model support
Users can select text-to-text models loadable by llama.cpp and supported text-to-speech loaders; Kokoro-82M is listed as currently supported out of the box.Read 4 Oct 2026 · mozilla-ai.github.io
Output files
The CLI writes a podcast script as podcast.txt and audio as podcast.wav in the specified output folder.Read 7 Oct 2026 · mozilla-ai.github.io
Pipeline
The documented workflow extracts and cleans document text, generates a conversational script with a language model, then creates audio with text-to-speech.Read 4 Oct 2026 · mozilla-ai.github.io
Speaker voices
Each speaker can have a distinct voice profile, and speaker names, roles, descriptions, and voice profiles are customizable.Read 7 Oct 2026 · mozilla-ai.github.io
Supported operating systems
The stated system requirements list Windows, macOS, and Linux, Python 3.10 or later (3.12 or later for Apple M chips), at least 8 GB RAM, and at least 20 GB disk space.Read 4 Oct 2026 · github.com
System requirements
The README lists Windows, macOS, or Linux, Python 3.10 or later (3.12 or later for Apple M chips), at least 8 GB RAM, and 20 GB disk space.Read 7 Oct 2026 · github.com
Target audience
The project describes Blueprints as tools for developers to integrate AI capabilities into their projects using open-source models and tools.Read 7 Oct 2026 · mozilla-ai.github.io
Usage limit
The CLI may use only a subset of the input when cleaned text exceeds the text model's context-based character limit.Read 4 Oct 2026 · mozilla-ai.github.io
Workflow
The pipeline extracts and cleans document text, generates a conversational script with a language model, then creates audio with text-to-speech.Read 7 Oct 2026 · mozilla-ai.github.io

Strong points and limits

Strong points

  • Accepts PDF, HTML, TXT, DOCX and Markdown.
  • Designed for local processing without external API calls.
  • Exports a script and WAV audio file.
  • Offers both CLI and Streamlit demo interfaces.
  • Licensed under Apache 2.0.

Limits

  • Requires at least 8 GB RAM and 20 GB disk space.
  • May use only part of text beyond the model limit.
  • Apple M chips require Python 3.12 or later.

Who it suits

This blueprint suits developers who want to add document-to-audio generation using open-source models and tools. It also fits users who want local processing and can meet its system requirements.

Verdict

The project gives users control over models, voices and scripts while keeping processing local by design. Check the system requirements and text-length limitation before choosing it for large documents.

Where Specifiction places it

Alternatives to Mozilla Document-to-PodcastAll alternatives →