#37 · Primary category: Speech & Audio
CapsWriter-Offline
PC voice input tool with offline recognition, high accuracy, low latency, hotwords, and LLM polishing; hold CapsLock or mouse side button X2 to speak, release to auto-insert.
Project last updated:08/26/26
GitHub Stars
6.7K
Forks
613
Contributors
2
License
MIT
Why we included this project
CapsWriter-Offline is a Windows voice input tool for people who type a lot of Chinese and would rather just talk. You hold CapsLock or a mouse side button to dictate, and when you release, the recognized text is typed into whatever app has focus. Recognition runs entirely on local ASR models, so it works on machines with no internet and on locked-down office PCs, and latency is low enough that it feels like typing. Beyond plain dictation it can transcribe files to SRT, TXT, or JSON, convert spoken numbers into proper digit formats, and apply hot words and regex rules so jargon and names come out right, and an optional LLM layer can polish or reformat the text before it is committed. If you want a private, fast voice input pipeline on Windows that you can tune yourself, this is a good place to start.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production