academic-presentations

To convert a research paper into a narrated video presentation, you provide the paper and an outline. The Skill uses a four-stage pipeline to generate slide visuals and assemble audio into a coherent video talk.

The best way to generate presentation slides from academic papers is using an automated pipeline that extracts content for scripts and leverages paper figures. This process creates structured decks with talking points for conferences or lectures.

Yes, the presentation generator supports text-to-speech for slide narration using edge-tts or Kokoro. It produces per-slide audio to create accessible talks or demos from your research papers.

Yes, you can use ffmpeg and edge-tts to assemble conference talks from papers. The pipeline combines generated slide visuals and TTS audio into a 15-20 minute narrated video presentation.

Yes, you need to provide your research paper and an outline to generate slides. The script and outline generation stage uses these inputs to structure the presentation deck and talking points.

Using Nanobanana for academic slide generation automates visual creation from deck-style prompts and paper figures. This avoids manual design, enabling rapid conversion of dense research content into accessible talks.