paper2video

Convert research paper text and figures into narrated videos with Python scripts.

2.2k|124|Updated Apr 27, 2026
One-click install
npx skills add https://github.com/microsoft/ResearchStudio --skill paper2video
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: paper2video
Source: https://github.com/microsoft/ResearchStudio/tree/main/ResearchStudio-Reel/skills/paper2video
Command: npx skills add https://github.com/microsoft/ResearchStudio --skill paper2video

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires paper2assets, paper2poster, paper2blog, ppt-master, python, libreoffice, poppler, ffmpeg, ffprobe, playwright, chromium, edge-tts, azure-tts, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the process of converting research paper content into a narrated video, saving time and effort in producing high-quality research presentations.

Core Features & Use Cases

  • Paper to Video Conversion: Automatically generates a narrated video from the text, figures, and other elements of a research paper.
  • Narration Customization: Allows customization of narration script and voice.
  • Visual Cues: Adds visual cues to the video to highlight key sections.
  • Use Case: Imagine you have a research paper. Use this Skill to automatically generate a narrated video that summarizes the paper's key points, complete with visual cues.

Quick Start

Use the paper2video skill with the paper file 'research_paper.pdf'.

Frequently Asked Questions about paper2video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a research paper PDF into a narrated video?

To convert a research paper PDF into a narrated video, you can use tools that extract text and figures, generate a narration script, and synthesize audio. This Skill automates that exact PDF to video conversion process using Python scripts and text-to-speech libraries.

Can I customize the narration script and voice for research communication videos?

Yes, you can customize the narration script and voice for research communication videos. The process allows script adjustments and utilizes Edge TTS or Azure TTS to synthesize the audio track for your paper content.

What dependencies are needed to automate paper to video conversion?

Automating paper to video conversion requires Python, LibreOffice, Poppler, FFmpeg, FFprobe, Playwright, Chromium, and text-to-speech engines like Edge TTS. These tools handle PDF processing, browser rendering, and audio synthesis.

Does generating a video from a research paper automatically add visual cues?

Yes, generating a video from a research paper automatically adds visual cues to highlight key sections. The workflow extracts paper figures and text, then overlays these visual cues during the video production phase.

What is the best way to create a video presentation from an academic paper?

The best way to create a video presentation from an academic paper is to automate extraction of text and figures, then synthesize narration. This Skill uses paper2poster and ppt-master to structure slides before rendering the final video.

Why does PDF to video conversion fail without FFmpeg and Poppler?

PDF to video conversion fails without FFmpeg and Poppler because Poppler extracts text and figures from the research paper, while FFmpeg and FFprobe handle audio and video merging. Both are essential dependencies for the processing pipeline.