NVIDIA-AI-Blueprints/pdf-to-podcast
Transform PDFs into AI podcasts for engaging on-the-go audio content.
Leverages NVIDIA NIM microservices with Docling for PDF extraction and ElevenLabs for TTS, orchestrating multi-stage agentic workflows to generate dialogue-driven podcast transcripts with optional context documents and custom focus prompts. Deployable either via NVIDIA API catalog (CPU-only) or self-hosted NIM with configurable LLM models (8B to 405B), with Redis and MinIO handling state and artifact storage across containerized microservices.
803 stars.
Stars
803
Forks
206
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 30, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/NVIDIA-AI-Blueprints/pdf-to-podcast"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
danthelion/doc2audiobook
Convert text documents to high fidelity audio(books).
tjunttila/pdf2video
A tool for making videos from PDF presentations.
chaonan99/ppt_presenter
Convert ppt to video with audio track, using text to speech synthesis
eminemahjoub/pdf-voice-reader
"PDF Reader: A Python application for seamless PDF viewing with enhanced text-to-speech capabilities."
hutchresearch/latex2speech
TeX2Speech is an application that turns LaTeX documents into spoken audio.