# yetone/voice-input-src

Repository: https://github.com/yetone/voice-input-src
Canonical: https://ross.abutalabs.com/products/voice-input-src
License: MIT
License Family: permissive
Last push: 2026-04-25T04:18:31+00:00

## Health v2 (maintenance only)
Score: 50/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 79, release rhythm 35, longevity 11
- inputs: {"age_days": 157, "days_push": 130, "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 2409, forks 241 (observed 2026-08-28T04:06:44.316526+00:00)

## What it is
A macOS menu-bar voice input app (Swift, macOS 14+) that lets users hold the Fn key to record and release to inject streaming-transcribed text into the focused input field. It uses Apple Speech Recognition with an optional OpenAI-compatible LLM refinement step to fix recognition errors in mixed Chinese-English speech.

## Use cases
- hold a key to dictate text anywhere on macOS
- voice input with Chinese speech recognition out of the box
- fix homophone errors in transcribed Chinese-English speech with an LLM
- switch dictation language between Chinese, English, Japanese, and Korean
- see a live waveform while recording voice notes

## When to choose
- you want hands-free dictation injected into any focused macOS app
- you primarily dictate in Chinese or other CJK languages
- you want streaming transcription without cloud vendor lock-in, with optional LLM cleanup

## When to avoid
- you need Windows or Linux support
- you want full transcription of audio files rather than live dictation
- you cannot grant macOS accessibility/input-monitoring permissions

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, llm-inference, gui
- domain: speech-processing, apple-ecosystem, developer-tools, desktop-applications
- platform: -
- tags: voice-input, dictation, menu-bar-app, transcription, text-injection, hold-to-talk, waveform-animation, openai-compatible-api, natural-language-processing, macos, desktop, swift

## Member repositories
- yetone/voice-input-src (main) score 50

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:44.316526+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 2026-08-30T02:34:01.973537+00:00, confidence not recorded.
  - readme: https://github.com/yetone/voice-input-src (fetched 2026-08-28T04:06:44.316526+00:00, sha b3c57523a0a1)
- Data as of 2026-08-30T08:39:29.467469+00:00.