# showlab/Paper2Video

Automatic Video Generation from Scientific Papers

Repository: https://github.com/showlab/Paper2Video
Canonical: https://ross.abutalabs.com/products/paper2video
Homepage: https://showlab.github.io/Paper2Video/
Language: Python
License: MIT
License Family: permissive
Last push: 2026-03-05T09:05:41+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 70, release rhythm 35, longevity 23
- inputs: {"age_days": 334, "days_push": 181, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2368, forks 326 (observed 2026-08-28T04:06:41.674834+00:00)

## What it is
Paper2Video is a Python pipeline that automatically generates academic presentation videos from scientific papers, taking a paper PDF, a speaker image, and a reference audio sample as input. It coordinates slide creation, subtitles, speech synthesis, and a talking-head presenter, and also provides a benchmark dataset for evaluating generated presentation videos.

## Use cases
- turn an arxiv paper into a presentation video
- automatically generate slides and narration from a pdf paper
- create a talking-head video presenting my research paper
- make academic presentation videos without recording
- evaluate ai-generated presentation videos
- generate conference-style video summaries of papers

## When to choose
- you want to automate producing presentation videos from research papers
- you need aligned slides, subtitles, speech, and talking-head output
- you are researching multimodal video generation or evaluation of presentations

## When to avoid
- you need polished, human-quality video editing with fine creative control
- you lack GPU resources or LLM API access for inference
- you want generic text-to-video generation unrelated to academic papers

## Facets
- artifact type: library
- maturity: active
- function: video-processing, llm-inference, tts, agent-framework, machine-learning
- domain: artificial-intelligence, large-language-models, education
- platform: python, cross-platform
- tags: paper2video, presentation-generation, talking-head, slides-generation, academic-communication, multimodal, video, natural-language-processing, gpu

## Member repositories
- showlab/Paper2Video (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:41.674834+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:35:56.875412+00:00, confidence not recorded.
  - readme: https://github.com/showlab/Paper2Video (fetched 2026-08-28T04:06:41.674834+00:00, sha dba76f15800d)
  - homepage: https://showlab.github.io/Paper2Video/ (fetched 2026-08-29T10:16:21.736907+00:00, sha 0cd78941550d)
- Data as of 2026-08-30T08:39:29.467469+00:00.