# nazdridoy/kokoro-tts

A CLI text-to-speech tool using the Kokoro model, supporting multiple languages, voices (with blending), and various input formats including EPUB books and PDF documents.

Repository: https://github.com/nazdridoy/kokoro-tts
Canonical: https://ross.abutalabs.com/products/kokoro-tts
Homepage: https://huggingface.co/hexgrad/Kokoro-82M
Language: Python
License: MIT
License Family: permissive
Topics: kokoro, kokoro-tts, python, tts, audiobook, podcast, epub, pdf
Last push: 2026-08-22T22:24:48+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 42
- inputs: {"age_days": 596, "days_push": 11, "days_rel": 11, "gap_med": 26.0, "n_releases_24m": 11}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1816, forks 174 (observed 2026-08-28T04:05:40.088352+00:00)

## What it is
A Python CLI text-to-speech tool built on the Kokoro-82M model that converts text, EPUB, PDF, and TXT inputs into natural-sounding speech with multiple languages, voices, and voice blending. It supports WAV/MP3 output, streaming playback, chapter splitting/merging, adjustable speed, and GPU acceleration.

## Use cases
- convert epub book to audiobook
- generate speech audio from a pdf document
- text to speech from the command line
- create mp3 narration of text files
- blend multiple tts voices with custom weights
- run offline text-to-speech with gpu acceleration
- split generated audio into chapters

## When to choose
- you want a lightweight, fast, Apache-licensed TTS model runnable locally
- you need to convert ebooks or PDFs into audio files
- you prefer a terminal workflow with piping and stdin support
- you want voice blending and multi-language support without cloud APIs

## When to avoid
- you need a graphical interface (GUI is still a TODO)
- you run Python 3.13+ (only 3.11-3.12 supported)
- you need real-time streaming synthesis at scale in production services
- you need languages or voices beyond what Kokoro-82M provides

## Facets
- artifact type: cli-tool
- maturity: active
- function: tts, cli, audio-processing, pdf, gpu-computing
- domain: speech-processing, artificial-intelligence, pdf
- platform: cli, python, cross-platform
- tags: text-to-speech, kokoro, epub, audiobook-generation, voice-blending, offline, audio, command-line, gpu

## Member repositories
- nazdridoy/kokoro-tts (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:40.088352+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 2026-08-30T03:20:36.463567+00:00, confidence not recorded.
  - readme: https://github.com/nazdridoy/kokoro-tts (fetched 2026-08-28T04:05:40.088352+00:00, sha 7416feae6370)
  - homepage: https://huggingface.co/hexgrad/Kokoro-82M (fetched 2026-08-29T10:59:48.208746+00:00, sha f9bbe8638b72)
  - site_page: https://huggingface.co/docs (fetched 2026-08-29T10:59:48.217998+00:00, sha bdec26667b98)
  - site_page: https://huggingface.co/docs/inference-providers (fetched 2026-08-29T10:59:48.221982+00:00, sha 8a5d0f819473)
  - site_page: https://huggingface.co/docs/hub/model-cards (fetched 2026-08-29T10:59:48.223923+00:00, sha 60ded09a56b0)
  - registry_pypi: https://pypi.org/pypi/kokoro-tts/json (fetched 2026-08-29T10:59:48.227941+00:00, sha 8442a87d45b7)
  - site_page: https://huggingface.co/pricing (fetched 2026-08-29T10:59:48.219978+00:00, sha de6b7a178be5)
  - site_page: https://huggingface.co/huggingface (fetched 2026-08-29T10:59:48.225878+00:00, sha a64a0fe552e5)
- Data as of 2026-08-30T08:39:29.467469+00:00.