# espeak-ng/espeak-ng

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

Repository: https://github.com/espeak-ng/espeak-ng
Canonical: https://ross.abutalabs.com/products/espeak-ng
Language: C
License: GPL-3.0
License Family: copyleft
Topics: espeak-ng, espeak, android, text-to-speech, speech-synthesis
Last push: 2026-08-19T12:23:56+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 8, longevity 100
- inputs: {"age_days": 3921, "days_push": 14, "days_rel": 629, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6763, forks 1279 (observed 2026-08-28T04:09:48.367933+00:00)

## What it is
eSpeak NG is a compact open-source text-to-speech synthesizer supporting over 100 languages and accents, using formant synthesis for small size and high-speed speech. It is available as a command-line tool, a shared library, and a SAPI5 version for Windows screen readers.

## Use cases
- convert text to spoken audio from the command line
- add text-to-speech to an accessibility screen reader
- generate WAV files of spoken text in many languages
- embed a lightweight TTS engine in an Android app
- use TTS as a front-end for MBROLA voices
- translate text into phoneme codes for another synthesis engine

## When to choose
- you need a tiny, fast TTS engine covering 100+ languages
- you need offline speech synthesis with no cloud dependency
- you want a library or CLI that integrates easily into other programs
- you need SSML/HTML text input support

## When to avoid
- you need natural, human-quality voices rather than robotic formant speech
- you need neural TTS quality for consumer-facing products
- you need complete SSML support

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, cli, audio-processing
- domain: speech-processing, accessibility, cross-platform
- platform: windows, bsd, cli, cross-platform
- tags: text-to-speech, formant-synthesis, multilingual, screen-reader, mbrola, ssml, c, natural-language-processing, linux, android, macos

## Member repositories
- espeak-ng/espeak-ng (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:48.367933+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 2026-08-29T17:42:33.665601+00:00, confidence not recorded.
  - readme: https://github.com/espeak-ng/espeak-ng (fetched 2026-08-28T04:09:48.367933+00:00, sha d6b11d6bca77)
- Data as of 2026-08-30T08:39:29.467469+00:00.