Ross ROSS = Recommend OSS · open-source software intelligence for agents

HaujetZhao/CapsWriter-Offline

PC 端语音输入工具,离线识别,高准确率、低延迟,支持热词、LLM润色。按住CapsLock或鼠标侧键X2说话,松开自动上屏。 observed · 2026-08-28

github.com/HaujetZhao/CapsWriter-Offline · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

92/100

  • Activity 99
  • Release rhythm 86
  • Longevity 85
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.

  • gap_med: 9.0
  • age_days: 1193
  • days_rel: 95
  • days_push: 7
  • n_releases_24m: 7

Full methodology

Adoption not part of the score

6691 stars · 612 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

CapsWriter-Offline is a fully offline voice input tool for Windows that transcribes speech to text when you hold CapsLock or mouse side button X2 and release it. It supports hotword replacement, regex rules, LLM-based polishing, and audio/video file transcription to subtitles and text.

Use cases

  • dictate text offline by holding CapsLock
  • transcribe audio and video files to srt subtitles
  • replace misrecognized rare words with hotwords
  • polish dictated text with an LLM
  • convert spoken Chinese numbers to digits
  • keep a daily archive of voice notes

When to choose

  • you need private, fully offline speech-to-text on Windows 10/11
  • you want low-latency push-to-talk dictation anywhere on the system
  • you need custom hotword or regex replacement for domain terms
  • you want to transcribe media files into subtitles and timestamps

When to avoid

  • you are on macOS or Linux, which are not supported
  • you need cloud-based multilingual ASR with broad language coverage
  • you cannot download separate ASR model packages
  • you need a GUI-first dictation product rather than config-file customization

Facets

application · maturity active

speech-recognition audio-processing llm-inference ocr speech-processing developer-tools windows windows python voice-input offline-asr dictation hotwords push-to-talk subtitle-transcription paraformer sensevoice natural-language-processing desktop

1 source

Member repositories

RepositoryRoleHealth v2
HaujetZhao/CapsWriter-Offlinemain92

For agents

markdown · JSON · MCP: product_card(name="HaujetZhao/CapsWriter-Offline")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem