NVIDIA PDF to Podcast

NVIDIA PDF to Podcast transforms your documents into dynamic, customizable AI podcasts. Ready to experience the power of AI? Start your journey here!

Platform: Replicate

PDF to PodcastDocument-to-AudioAI Content ConversionVoice Synthesis

239 runs

CPU

License Check Required

🚀Function Overview

Converts PDF documents into customizable podcast-style audio content with configurable hosts, voices, and duration.

Key Features

PDF to audio podcast conversion
Customizable host and guest profiles with names
Voice selection for speaker roles
Adjustable podcast duration
Optional topic guidance for content focus
Monologue/dialogue mode switching

Use Cases

•Generating educational content from textbooks/reports
•Creating audio summaries of research papers
•Producing business briefings from documents
•Converting news articles into podcast formats

⚙️Input Parameters

pdf

string

PDF files to convert to podcast

host_name

string

Name of the podcast host

guest_name

string

Name of the podcast guest

host_voice

string

Voice for the podcast host

guest_voice

string

Voice for the podcast guest

duration_minutes

integer

Target podcast duration in minutes

podcast_topic

string

Optional topic guidance for the podcast

monologue

boolean

Generate a monologue instead of a dialogue

💡Usage Examples

Example 1

Input Parameters

{
  "pdf": "https://replicate.delivery/pbxt/N3SR4T7rDV9e6GoIixducuK5cyrFSCkZyKw7yPSOazEHYv7d/2505.00024v2.pdf",
  "host_name": "Adam",
  "monologue": false,
  "guest_name": "Bella",
  "host_voice": "Patient_Man",
  "guest_voice": "Wise_Woman",
  "podcast_topic": "",
  "duration_minutes": 5
}

Output Results

https://replicate.delivery/xezq/q98CJLgHej2e0060Ku8KfHsYGKQnW6A7TIWstzEe9dcdfb6lC/podcast.mp3

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: CPU
Run Count: 239
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

AI podcast conversionDocument-to-audioCustomizable voicesAdjustable durationEducational contentResearch paper summariesBusiness briefingsNews article podcasts

Related Models

Chatterbox TTS

Chatterbox is a state-of-the-art zeroshot TTS

Piper Persian Text-to-Speech

A fast, local neural text to speech system that sounds great and is optimized for the Raspberry Pi 4. Piper is used in a variety of projects.

Minimax Voice Cloning

Clone voices to use with Minimax's speech-02-hd and speech-02-turbo