Narration OS

WHAT IS NARRATION OS?

• NarrationOS turns any book or any text into a performed audiobook, generated entirely on your own machine. Drop in a file, pick a voice, and get back a finished narration you can listen to, master, and keep. No subscription, no uploads, no cloud, COMPLETELY OFFLINE. Your books, performed. Built by a solo developer, Narration OS runs the whole pipeline locally on your GPU, powered by Resemble AI's Chatterbox voice model.

BRING ANY BOOK

•  Import EPUB, PDF, DOCX, RTF, TXT, Markdown, and HTML, automatically split into chapters.
• No file? Paste any text, give it a title, and narrate it in seconds.
• Scanned PDFs are handled with built-in OCR.

YOUR OWN VOICE

• Clone a voice from a short 10 to 30 second recording, then use it across every book.
• Cloning is consent-gated: you confirm your right to the voice, and a receipt is signed locally with your own key.
• Preview any voice before you commit it to a book.

SHAPE THE PERFORMANCE

• The Narration Editor lets you fine-tune a chapter before you render: set book-wide name pronunciations and audition individual lines.
• Detect sound effects and laughter so they are voiced as real sounds instead of spelled out.
• Every change is previewed in the text before you commit. Nothing touches the audio until you press Render.

LISTEN YOUR WAY

• A karaoke reader highlights each word as it is read. Click any line to jump there.
• Switch to a cinematic teleprompter layout for a focused, immersive read.
• Bookmarks, adjustable speed, a sleep timer, and full keyboard control.

FINISH AND OWN IT

• Master your audiobook with target loudness, a clarity EQ, and a de-esser.
• Export to MP3, WAV, or chaptered M4B. Real files on your drive that you keep forever.

RUNS ON YOUR HARDWARE

• Best on NVIDIA (CUDA) GPUs, the primary and most-tested path. AMD (RDNA3/4, ROCm) and Intel Arc (XPU) are also fully GPU-accelerated. CPU-only works too, just slower.
• The AI runtime is bundled, so no internet is needed after install.

A NOTE FROM THE DEVELOPER

NarrationOS is a solo project and uses open source AI tools, so I would rather be upfront than oversell it. Although it has some rough edges, it already does the thing I built it for: it let me finally listen to the books I wanted, in the voices I wanted. I will keep improving it.

WHAT IS INCLUDED

• NarrationOS 1.0.0, the full app. Not a demo, not a trial. Every feature is unlocked from the first launch, and all future version updates for this app are included in this purchase at no extra cost.
• No bundled voices, and that's on purpose. NarrationOS doesn't ship with stock narrator voices. You clone your own. Record a short sample, and the app builds a voice from it. This keeps you in full control of the voice you publish with. You'll create your first voice as part of the guided setup.
• A sample book: The Lighthouse Keeper. An original short story, written for NarrationOS and included with the app. It's already in your library the first time you open it, so there's nothing to import. It has named characters and real dialogue on purpose, which gives the guided tour something to work with: hear your cloned voice, set name pronunciations, detect sound effects and laughs, let the app attribute lines to speakers, and take a chapter through the Narration Editor to a finished render.