SlideStream documentation

SlideStream turns a Markdown file, a PowerPoint deck or a document into a narrated video presentation, an editable PowerPoint, or both. Narration is what a presenter would say, not the bullets read aloud; the voice runs offline or can be a clone of your own; pictures and a presenter in the corner are optional. It runs on your machine or your own servers.

Get started

pip install "slide-stream[all]"      # everything: AI providers + offline TTS + web UI
slide-stream init                     # a minimal, works-with-no-keys config
slide-stream create deck.md out.mp4   # render a narrated video
slide-stream create deck.md out.pptx  # or an editable PowerPoint

New here? The use cases walk through common jobs; the user guide is the reference.

Find your way

• Use cases: recipes for common jobs.
• User guide: install, configuration, deck format, every command.
• Providers: every voice, picture, LLM, presenter and design option.
• Changelog: what changed in each release.
• Services: the self-hosted engines SlideStream can call, their licences and checks.
• Project: roadmap, user stories, decisions (ADRs), development workflow.

Check your setup

slide-stream doctor <deck> reports any configured provider whose package or API key is missing — with the exact pip install line to fix it.

The full project, source, and issue tracker live on GitHub.