Paper2Video
AI turns academic papers into "talk videos" — slides, subtitles, voiceover, presenter
AI automatically turns academic papers into "talk videos" (PPT + subtitles + voiceover + virtual presenter).
AI video generation, digital humans, and video restoration.
Key features
- Generates presentation videos from LaTeX papers automatically
- PaperTalker agent integrates slides, subtitles, cursor grounding, speech, talking head
- Paper2Video benchmark with metrics for evaluating presentation quality
- Fast mode without talking head; full mode with Hallo2
Good for
- Turning academic papers into video presentations
- Researchers sharing talks without recording
Stack & tags
Pythonpaper-to-videopresentationagenttalking-headttsopen-sourceresearch
Quick start
python pipeline_light.py --model_name_t gpt-4.1 --paper_latex_root /path/to/latex_proj --ref_img /path/to/ref_img.png --ref_audio /path/to/ref_audio.wavFrom the project README on GitHub.
Similar open-source projects
Hyperframes
★ 55,468Write HTML. Render video. Built for agents — HeyGen's open-source video framework
Hypit
★ 18,649Clone any viral video with AI agents — swap the face, the words, the B-roll, ship 100 variants