UNESCO PDF-to-Podcast

6.7easy start · #15of 23
in AI Podcast Generators

Well documentedyes
Runs where you workyes

Runs on Linux, Mac, self-hosted, Windows.

UNESCO PDF-to-Podcast is ranked #15 of 23 in AI podcast generators on The Geeks Club. It runs on Linux, macOS, Self-hosted, Windows.

Compared on AI podcast generators

Free plan: No
Host dialogue: Yes
Source imports: PDF documents
Voice cloning: Yes
Audio export: wav

Best UNESCO PDF-to-Podcast alternatives

See all 20

Jellypod Lesson 17.7 Podhoc Lesson 27.4 302 AI Podcast Generator Lesson 37.3 Podycy Lesson 47.3 AudioPod AI Lesson 57.2 Paper2Pod Lesson 67.1

The record

Purpose: The project converts scientific PDFs into podcast-style audio conversations using AI.
PDF processing: Its pipeline extracts structured PDF content, generates a conversational script, and synthesizes podcast audio.
Models and tools: The pipeline uses Docling for PDF extraction, Ollama with Granite4 for script generation, and VibeVoice for audio synthesis.
Audience options: Scripts can be tailored for experts, the general public, young people, or novices.
Languages: The project supports script generation in UNESCO’s six official languages: English, French, Chinese, Spanish, Arabic, and Russian.
Voice availability: English and Chinese have included native voices; French, Spanish, Arabic, and Russian fall back to English voices unless users add their own samples.
Podcast controls: Users can set a target duration and select between two and four speakers.
Installation: The project requires Python 3.9 or later, Poetry, and Ollama, and recommends a GPU while allowing a CPU fallback.
Local setup: The README provides installation instructions for macOS and Linux.
Notable limits: The README says the project currently handles one PDF at a time, long PDFs may need chunking, and audio generation needs significant GPU memory, especially with the 7B model.
Support: The project points users to GitHub Issues, Discussions, and wiki documentation for support.
License: The repository’s LICENSE file identifies the project license as MIT.
Maker profile: The UNESCO GitHub profile describes its code repository as an open-source hub for education, science, culture, and sustainable development.
Pipeline: Its pipeline extracts PDF content, generates a conversational script, and synthesizes podcast audio.

Where it ranks on The Geeks Club

Best AI Podcast Generators in 2026#15 of 23

Is UNESCO PDF-to-Podcast yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote UNESCO PDF-to-Podcast

Sources

github.com/unesco/pdf-to-podcast· checked 4 Oct 2026
github.com/unesco/pdf-to-podcast/blob/main/LICENSE· checked 4 Oct 2026
github.com/unesco· checked 4 Oct 2026
github.com/unesco/pdf-to-podcast/blob/main/pyproje· checked 4 Oct 2026