# WhiskeyCoder/Qwen3-Audiobook-Converter

Convert PDFs, EPUBs, DOCX, DOC, and TXT files into high-quality audiobooks using **Qwen3 TTS Voice Model** - an open-source voice synthesis system that excels at natural speech generation and voice cloning.

Repository: https://github.com/WhiskeyCoder/Qwen3-Audiobook-Converter
Canonical: https://ross.abutalabs.com/products/qwen3-audiobook-converter
Language: Python
License: MIT
License Family: permissive
Last push: 2026-04-07T14:35:15+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 76, release rhythm 35, longevity 15
- inputs: {"age_days": 221, "days_push": 148, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1081, forks 131 (observed 2026-08-28T04:03:30.845376+00:00)

## What it is
A Python CLI tool that converts documents (PDF, EPUB, DOCX, DOC, TXT) into audiobooks using the Qwen3 TTS voice model running locally via a Gradio interface. It supports pre-built narration voices and voice cloning from reference audio samples, with smart text chunking, caching, and FFmpeg-based audio processing.

## Use cases
- convert pdf books to audiobooks
- turn epub files into spoken audio
- clone a voice for audiobook narration
- batch convert docx documents to mp3 audio
- generate audiobooks with a local tts model
- make text-to-speech audiobooks offline

## When to choose
- You want to convert written documents into audiobook audio files with natural-sounding narration
- You need voice cloning from a reference audio sample with automatic transcription
- You already run or are willing to run the Qwen3 TTS model locally and have FFmpeg installed
- You want a free, open-source alternative to commercial audiobook narration services

## When to avoid
- You need a fully self-contained tool with no external TTS server dependency
- You want cloud-based or API-driven text-to-speech without local GPU/model setup
- You need formats beyond PDF, EPUB, DOCX, DOC, or TXT
- You require a graphical user interface rather than a command-line workflow

## Facets
- artifact type: cli-tool
- maturity: active
- function: tts, audio-processing, pdf, speech-recognition, cli
- domain: pdf, files, media
- platform: python, cli, cross-platform
- tags: audiobook-converter, text-to-speech, voice-cloning, qwen3-tts, epub, docx, document-to-audio, gradio, ffmpeg, audio, natural-language-processing, desktop

## Member repositories
- WhiskeyCoder/Qwen3-Audiobook-Converter (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:30.845376+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:51:19.038646+00:00, confidence not recorded.
  - readme: https://github.com/WhiskeyCoder/Qwen3-Audiobook-Converter (fetched 2026-08-28T04:03:30.845376+00:00, sha 10fc9c848b3c)
- Data as of 2026-08-30T08:39:29.467469+00:00.