# xiaochong/hi-kid

HiKid - Your AI English Pal. A desktop app built with React and TypeScript, targeting children in non-English-speaking countries who want to practice English speaking and listening.

Repository: https://github.com/xiaochong/hi-kid
Canonical: https://ross.abutalabs.com/products/hi-kid
Homepage: https://xiaochong.github.io/hi-kid
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, english-learning, kids-education, local-ai, offline-ai, speaking-practice, voice-chat
Last push: 2026-04-24T16:25:53+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 79, release rhythm 48, longevity 9
- inputs: {"age_days": 136, "days_push": 131, "days_rel": 133, "gap_med": null, "n_releases_24m": 1}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1043, forks 127 (observed 2026-08-28T04:03:21.113335+00:00)

## What it is
HiKid is a free, open-source Electron desktop app that lets children in non-English-speaking countries practice English speaking and listening through voice conversations with a local AI. It runs a fully offline pipeline (SoX recording, local ASR, local LLM via Ollama, local TTS) so no data ever leaves the machine.

## Use cases
- help my kid practice english speaking offline
- voice chat app for children learning english
- private ai tutor that runs locally without internet
- speech recognition and tts practice tool for kids
- offline english listening and conversation practice
- ai english companion for non-english-speaking children

## When to choose
- you want a privacy-safe, fully offline English practice companion for kids
- you're on macOS and want a cartoon-style, voice-first learning app with no API keys
- you prefer local models (Ollama, local ASR/TTS) over cloud services

## When to avoid
- you need Windows or Linux support today (only macOS is available)
- you want cloud-grade LLM quality or typed/written exercises rather than voice chat
- your machine can't run local ASR, TTS, and LLM models comfortably

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, tts, llm-inference, chatbot, audio-processing
- domain: education, large-language-models, speech-processing, privacy
- platform: cross-platform
- tags: english-learning, kids-education, offline-ai, local-ai, voice-chat, ollama, speaking-practice, privacy-first, natural-language-processing, macos, desktop, electron

## Member repositories
- xiaochong/hi-kid (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:21.113335+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 2026-08-30T07:02:33.142945+00:00, confidence not recorded.
  - readme: https://github.com/xiaochong/hi-kid (fetched 2026-08-28T04:03:21.113335+00:00, sha df70a6bebb7e)
  - homepage: https://xiaochong.github.io/hi-kid (fetched 2026-08-29T13:03:31.161731+00:00, sha 289a65744123)
- Data as of 2026-08-30T08:39:29.467469+00:00.