# justLV/onju-voice

A hackable AI home assistant platform

Repository: https://github.com/justLV/onju-voice
Canonical: https://ross.abutalabs.com/products/onju-voice
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2026-04-13T06:53:08+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 77, release rhythm 35, longevity 80
- inputs: {"age_days": 1121, "days_push": 142, "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 1711, forks 93 (observed 2026-08-28T04:05:25.648904+00:00)

## What it is
A hackable AI home assistant platform that replaces the internals of a Google Nest Mini with a custom ESP32-S3 PCB, paired with a server that handles speech transcription (Whisper), LLM response generation, and text-to-speech. It includes firmware, server code, and PCB design files, though the project is deprecated in favor of onju-v2.

## Use cases
- build a DIY smart speaker with local Whisper transcription
- voice-control Home Assistant lights with an LLM
- add and retrieve voice notes via a chatbot
- hack a Nest Mini into a custom AI assistant
- run a self-hosted voice assistant server for multiple devices
- experiment with conversational LLM hardware

## When to choose
- you want an open, hackable hardware voice assistant with full source and PCB files
- you want local speech-to-text with Whisper and LLM-generated spoken replies
- you're comfortable with Arduino IDE firmware flashing and running a Python server

## When to avoid
- you need a maintained, production-ready home assistant
- you want a drop-in commercial smart speaker without soldering or PCB ordering
- you need multi-voice character support or complex multi-function calling

## Facets
- artifact type: application
- maturity: abandoned
- function: speech-recognition, tts, llm-inference, chatbot, embedded, audio-processing
- domain: artificial-intelligence, large-language-models, speech-processing, iot, hardware, self-hosted
- platform: embedded, iot, python, windows, self-hosted
- tags: voice-assistant, esp32-s3, whisper, custom-pcb, smart-speaker, home-automation, deprecated, macos, linux

## Member repositories
- justLV/onju-voice (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:25.648904+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 2026-08-30T03:34:59.305292+00:00, confidence not recorded.
  - readme: https://github.com/justLV/onju-voice (fetched 2026-08-28T04:05:25.648904+00:00, sha 71fb913218c1)
- Data as of 2026-08-30T08:39:29.467469+00:00.