showlab/Paper2Video
Paper2Video converts academic papers with a speaker photo and reference audio into narrated presentation videos.
Not currently ranked — collecting fresh signals.
star history
The system takes a scientific paper, a speaker image, and an audio reference as input and automatically synthesizes a presentation video. It leverages multiple AI components—likely language models for paper comprehension, speech synthesis for audio generation, and video generation for avatar animation. The project includes a trained model and a supporting dataset for training and evaluation.
Frequently asked
- What is showlab/Paper2Video?
- Paper2Video converts academic papers with a speaker photo and reference audio into narrated presentation videos.
- Is Paper2Video open source?
- Yes — showlab/Paper2Video is open source, released under the MIT license.
- What language is Paper2Video written in?
- showlab/Paper2Video is primarily written in Python.
- How popular is Paper2Video?
- showlab/Paper2Video has 2.3k stars on GitHub.
- Where can I find Paper2Video?
- showlab/Paper2Video is on GitHub at https://github.com/showlab/Paper2Video.