# google-gemma/gemma-translator

Repository: https://github.com/google-gemma/gemma-translator
Canonical: https://ross.abutalabs.com/products/gemma-translator
Language: JavaScript
License: Apache-2.0
License Family: permissive
Last push: 2026-08-14T15:47:25+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 35, longevity 2
- inputs: {"age_days": 30, "days_push": 19, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1337, forks 175 (observed 2026-08-28T04:04:25.459744+00:00)

## What it is
An on-device, fully offline voice translator application powered by Gemma 4 via LiteRT-LM, with a React web frontend optimized for small handheld displays and a Python API server. It is designed to run as a kiosk appliance on a Raspberry Pi 5 with microphone input and speaker output.

## Use cases
- run a fully offline voice translator on a raspberry pi
- translate speech between languages without internet
- build a handheld kiosk translation device with a small display
- run gemma locally on-device with litert-lm
- deploy an LLM-powered appliance with systemd on a pi
- voice-to-voice translation with local text-to-speech

## When to choose
- you need translation with no internet connectivity or privacy concerns
- you have a Raspberry Pi 5 with 8GB RAM and want a dedicated translation appliance
- you want a small-screen optimized retro-terminal UI for a handheld device

## When to avoid
- you need high-quality cloud translation across many languages
- you lack the required hardware (Pi 5 8GB, mic, speaker, display)
- you want a mobile or Windows-native app

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, speech-recognition, tts, http-server, web-framework
- domain: artificial-intelligence, large-language-models, speech-processing, embedded-systems, iot
- platform: python, self-hosted
- tags: offline-translation, gemma, litert-lm, raspberry-pi, voice-translator, kiosk, on-device-inference, linux, macos, nodejs, web-server

## Member repositories
- google-gemma/gemma-translator (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:25.459744+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 2026-08-30T04:44:02.840538+00:00, confidence not recorded.
  - readme: https://github.com/google-gemma/gemma-translator (fetched 2026-08-28T04:04:25.459744+00:00, sha 08f41a3e4356)
- Data as of 2026-08-30T08:39:29.467469+00:00.