MakeAudiobookAudiobook Workbench

Create an audiobook in five clear steps.

Add a source, review the extracted text and estimate, then render a sample or full audiobook. Paid AI work stays behind explicit confirmation.

  1. 1Add source
  2. 2Extract text
  3. 3Confirm cleanup
  4. 4Prepare narration
  5. 5Render audiobook

Step 1

Add the book source

TXTPDFEPUB

Step 2

Pick a narrator

Marin is selected by default. You can preview it now or change voices before rendering.

OpenAI.fm samples

Selected narrator

Marin

Preview generation is on-demand so the app does not spend API credit automatically.

Change narrator voice
Extraction is free and gives you the exact text-based estimate before any paid AI cleanup or audio render step.
Cost guardrails: extraction is local and free. Paid AI cleanup and audio render steps require confirmation against the current text-based estimate.

Build notes

What this build does right now

MVP+

TXT

Plain text and markdown sources

PDF

Digital PDFs with embedded text

EPUB

Reflowable ebooks with chapter HTML

Extracted text is stored as a reusable artifact. Cleanup results are cached by normalized source and model, narration assembly is local and reusable, and full audiobook packaging now runs as a background job with a merged `m4b` output and podcast RSS feed.

Pipeline output

Run extraction to start the pipeline

Run extraction to inspect normalized text and parser warnings. Once the source looks right, cleanup, assemble, and render a tiny audio sample.