Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Transform PDFs into AI podcasts for engaging on-the-go audio content.
| Date | Stars |
|---|---|
| 2026-07-24 | 858 |
| 2026-07-25 | 859 |
| 2026-07-28 | 859 |
| 2026-07-30 | 859 |
| 2026-08-06 | 859 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<h2><img align="center" src="https://github.com/user-attachments/assets/cbe0d62f-c856-4e0b-b3ee-6184b7c4d96f">NVIDIA AI Blueprint: PDF to Podcast</h2>
## Overview
This NVIDIA AI blueprint shows developers how to build an application that transforms PDFs into engaging audio content. Built on NVIDIA NIM, this blueprint is flexible, and can run securely on a private network, delivering actionable insight without sharing sensitive data.
<img width="1021" alt="Architecture Diagram" src="docs/architecture-diagram.png"/>
The blueprint accepts a Target PDF and optionally multiple Context PDFs. The Target PDF will be the main source of information for the generated transcript while Context PDFs will be used as additional reference for the agent to use. The user can also optionally specify a guide prompt that will give a focus for the agent generated transcript (i.e. “Focus on the key drivers for NVIDIA’s Q3 earnings report”).
For more information about the PDF, Agent and TTS service flows, please refer to the mermaid [diagram](docs/README.md)
| :exclamation: Important |
| :-----------------------|
| Users running this blueprint with [NVIDIA AI Workbench](https://www.nvidia.com/en-us/deep-learning-ai/solutions/data-science/workbench/) should skip to the quickstart section [here](https://github.com/NVIDIA-AI-Blueprints/pdf-to-podcast/tree/main/workbench#quickstart)! |
## Software Components
- NVIDIA NIM microservices
- Response generation (Inference)
- [NIM for meta/llama-3.1-8b-instruct](https://build.nvidia.com/meta/llama-3_1-8b-instruct)
- [NIM for meta/llama-3.1-70b-instruct](https://build.nvidia.com/meta/llama-3_1-70b-instruct)
- [NIM for nvidia/llama-3.3-nemotron-super-49b-v1.5](https://build.nvidia.com/nvidia/llama-3_3-nemotron-super-49b-v1_5)
- Document ingest and extraction - [Docling](https://github.com/DS4SD/docling)
- Text-to-speech - [ElevenLabs](https://elevenlabs.io/)
- Redis - [Redis](https://redis.io/)
- Storage - [MinIO](https://minio.io/)
> **Note:** Since NVIDIA blueprints are adaptable to your specific business use case and/or infrastructure, the above software components are configurable. For example, to decrease the amount of GPU memory required, you can leverage a smaller Llama 3.1-8B NIM and disable GPU usage for Docling in docker-compose.yaml.
Docker Compose scripts are provided which spin up the microservices on a single node. The Blueprint contains sample use-case PDFs but Developers can build upon this blueprint, by using their own PDFs based upon their specific use case.
## Hardware Requirements
Below are the hardware requirements, these are dependent on how you choose to deploy the blueprint. There are 2 ways to deploy this blueprint:
1. Default - Use NVIDIA API catalog NIM endpoints
- Can run on any non-gpu accelerated machine/VM
- 8 CPU cores
- 64 GB RAM
- 100GB disk space
- A public IP address is also required
2. Locally host NVIDIA NIM
- [Meta Llama 3.1 8B Instruct Support Matrix](https://docs.nvidia.com/nim/large-language-models/latest/support-matrix.html#llama-3-1-8b-instruct)
- [Meta Llama 3.1 70B Instruct Support Matrix](https://docs.nvidia.com/nim/large-language-models/latest/support-matrix.html#llama-3-1-70b-instruct)
- [Meta Llama 3.1 405B Instruct Support Matrix](https://docs.nvidia.com/nim/large-language-models/latest/support-matrix.html#llama-3-1-405b-instruct)
> **Note:** To run the blueprint at scale and for faster preprocessing of PDFs, it is recommended to use GPU for running the PDF ingest/extraction pipeline.
## Prerequisites
- NVIDIA AI Enterprise developer licence required to local host NVIDIA NIM.
- API catalog keys:
- NVIDIA [API catalog](https://build.nvidia.com/) or [NGC](https://org.ngc.nvidia.com/setup/personal-keys)
- [ElevenLabs](https://elevenlabs.io/docs/api-reference/authentication)
## Quick Start Guide
1. **Docker Compose**
System requirements: Ubuntu 20.04 or 22.04 based machine, with sudo priExcerpt of 10,301 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ba020948e56446f1, topic:tts, readme:text-to-speech
