Orator takes your markdown documents and produces narrated, camera-ready videos — in your own voice. Entirely on your machine. No cloud APIs, no subscription, no recording studio.
Orator reads your document, narrates it in your cloned voice, renders professional slides from the same source, and composites everything into a finished MP4.
Your .md or .qmd file is split into sections. Prose becomes narration text. Code blocks, tables, and callouts get spoken descriptions.
Each section is synthesized in your cloned voice using a 10-second reference clip. Zero-shot — no training data, no cloud upload.
Professional slides are generated from the same source document. Syntax-highlighted code, styled tables, accessible color palette.
Audio and slides are stitched into a final 1080p MP4 with GPU-accelerated encoding. Each slide displays for exactly the duration of its narration.
Lecture videos, tutorial walkthroughs, and training modules from the lesson notes you already have.
Video docs, API walkthroughs, and changelog videos from the markdown you already write.
Onboarding videos and compliance training from existing SOPs. No proprietary content leaves the machine.
Video abstracts, conference pre-recordings, and release note walkthroughs from structured documents.
Your voice. Your content. Your machine.
Every competitor in the narrated video space is cloud-only and subscription-based. Orator runs entirely on your hardware. Your documents and your voice model never leave your computer. For teams subject to data residency, HIPAA, or internal security policies, this isn’t a feature — it’s a requirement.
Orator is currently in development. Join the waitlist to be notified at launch.
Join the waitlist and we’ll notify you the moment Orator is ready. No drip campaigns. No newsletters. One email: it’s ready.
We’ll be in touch when Orator launches.
Open source software
Orator is a commercial product built on open source software. We gratefully acknowledge the following projects and their contributors.