# santinic/audiblez

Generate audiobooks from e-books

Repository: https://github.com/santinic/audiblez
Canonical: https://ross.abutalabs.com/products/audiblez
Language: Python
License: MIT
License Family: permissive
Topics: audiobooks, epub, kokoro, python, tts
Last push: 2026-02-27T19:06:57+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 69, release rhythm 35, longevity 42
- inputs: {"age_days": 596, "days_push": 187, "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 8460, forks 747 (observed 2026-08-28T04:10:21.284975+00:00)

## What it is
Audiblez is a Python CLI tool (with an optional GUI) that converts .epub e-books into .m4b audiobooks using the Kokoro-82M text-to-speech model. It supports multiple languages, voice selection, and GPU acceleration via CUDA.

## Use cases
- convert epub books to audiobooks
- generate m4b audiobook files from e-books
- text to speech for long documents
- create audiobooks with natural sounding voices
- batch convert e-book chapters to audio
- run tts locally on cpu or cuda gpu

## When to choose
- you want offline, local text-to-speech without cloud services
- you need multi-language audiobook generation with voice selection
- you have a GPU and want fast conversion of full books

## When to avoid
- you need commercial-grade studio narration or fine-grained prosody control
- you only have a CPU and need very fast conversion of large books
- your source files are not epub format

## Facets
- artifact type: cli-tool
- maturity: active
- function: tts, audio-processing, cli, gui
- domain: speech-processing, files
- platform: python, cli, cross-platform, windows
- tags: audiobooks, epub, kokoro, text-to-speech, m4b, speech-synthesis, audio, natural-language-processing, linux, macos, gpu

## Member repositories
- santinic/audiblez (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:21.284975+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 2026-08-29T17:27:12.415064+00:00, confidence not recorded.
  - readme: https://github.com/santinic/audiblez (fetched 2026-08-28T04:10:21.284975+00:00, sha 48dfadb1d640)
  - registry_pypi: https://pypi.org/pypi/audiblez/json (fetched 2026-08-29T08:26:57.930659+00:00, sha 443373c5acce)
- Data as of 2026-08-30T08:39:29.467469+00:00.