# hgneng/ekho

Chinese text-to-speech engine

Repository: https://github.com/hgneng/ekho
Canonical: https://ross.abutalabs.com/products/ekho
Language: Lex
License: GPL-2.0
License Family: copyleft
Topics: tts, chinese, cantonese, tibetan
Last push: 2026-09-02T00:48:00+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 8, longevity 100
- inputs: {"age_days": 3794, "days_push": 1, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1211, forks 266 (observed 2026-09-03T02:15:12.689492+00:00)

## What it is
Ekho is an open-source Chinese text-to-speech engine supporting Mandarin, Cantonese, and Tibetan, part of the eGuideDog accessibility project. It converts written Chinese text into spoken audio using recorded voice data and can be extended with custom voices.

## Use cases
- convert Chinese text to speech
- Cantonese text-to-speech synthesis
- Tibetan TTS engine
- screen reader speech for visually impaired Chinese users
- create a custom TTS voice
- offline Chinese speech synthesis

## When to choose
- you need offline Chinese, Cantonese, or Tibetan speech synthesis
- you want a free GPL-licensed TTS for accessibility applications
- you need to build custom voice data for Chinese TTS

## When to avoid
- you need natural-sounding neural TTS voices
- you need non-Chinese language support
- you need a managed cloud TTS API

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, audio-processing
- domain: speech-processing, accessibility
- platform: cross-platform, cli
- tags: chinese-tts, cantonese, tibetan, eguidedog, offline-tts, natural-language-processing, localization, linux

## Member repositories
- hgneng/ekho (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:12.689492+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 2026-08-30T06:17:59.650662+00:00, confidence not recorded.
  - readme: https://github.com/hgneng/ekho (fetched 2026-09-03T02:15:12.689492+00:00, sha ae7b3cd30879)
- Data as of 2026-08-30T08:39:29.467469+00:00.