Cadenza-voice
Local-first voice input for macOS (随言). Hold a shortcut, speak, and the text is typed at your cursor. Recognition runs on your Mac with SenseVoice, FireRedASR2 or Parakeet; cloud services are optional, with your own keys and consent. No account, no telemetry. 本地优先的 macOS 语音输入，开源 MIT。
- asr
- dictation
- local-first
- macos
- menu-bar-app
- offline
- open-source
- privacy
- sherpa-onnx
- speech-recognition
- speech-to-text
- swift
- swiftui
- voice-input
- Stars
- 21
- Forks
- 2
- + today
- +1
- Created
- 10d
Ranking data as of October 16, 2026 (UTC).
Star History
Today, hour by hour
Overview
Local-first voice input for macOS (随言). Hold a shortcut, speak, and the text is typed at your cursor. Recognition runs on your Mac with SenseVoice, FireRedASR2 or Parakeet; cloud services are optional, with your own keys and consent. No account, no telemetry. 本地优先的 macOS 语音输入，开源 MIT。 It ranks #1834 on GitTiger, gaining +1 star on October 16, 2026 (UTC).
The project is written in Swift and has 2 forks. It was created 10d ago.
git clone https://github.com/DragonKingIO/Cadenza-voice.git
cd Cadenza-voice
# see README for setup