All projects

16 / 20 · Local-first audiobook studio

BookVoice

A Windows desktop application for converting long-form documents into locally generated narration and shaping the result in a multitrack editor.

Ask about this project
Role
Desktop application development
Platform
Windows desktop application
Built with
Electron, Python, Local TTS
BookVoice local-first audiobook studio desktop interface

The story

  1. 01

    The challenge

    Turning a long document into an audiobook usually means moving between text cleanup, speech generation and audio editing tools. The goal was a private workflow that handles all three on one computer.

  2. 02

    Our approach

    We split generation by chapter, so long jobs can show progress, recover partial work and be revised. An Electron interface coordinates a local Python speech worker and a three-track editor for narration, ambience and effects.

  3. 03

    What it delivers

    BookVoice takes a document through local narration and audio arrangement to an exportable MP3. After the first model download, the core workflow runs without an account or a hosted backend.

What we built

  1. 01Import PDF, TXT, Markdown or pasted text
  2. 02Normalize text and detect editable chapter structures
  3. 03Generate narration locally with Piper or Kokoro
  4. 04Install the selected Python runtime, engine and voice model only when needed
  5. 05Process chapters in sequence with progress, cancellation and partial recovery
  6. 06Preview and save individual chapters or a combined MP3 audiobook
  7. 07Arrange narration, ambience and effects across three timeline tracks
  8. 08Move, trim, split, fade, loop and adjust clip volume
  9. 09Narration-aware ducking, resampling and peak normalization
  10. 10Waveform previews, a draggable playhead and timeline zoom
  11. 11Reusable .bookvoice editor projects with undo and redo history
  12. 12Freesound search with preview caching, license metadata and attribution export

Technology

Desktop
Electron, Vite, ES2022 JavaScript, HTML and CSS
Processing
A persistent local Python worker using JSON over stdin and stdout
Speech
Piper and Kokoro local text-to-speech engines
Documents
PDF.js plus TXT, Markdown and pasted-text import
Audio
NumPy, SoundFile, waveform analysis, offline mixing and MP3 export
Distribution
Electron Builder and a guided Windows NSIS installer

Keep scrolling
to see more

About us

Next page