VoxMinutes v0.1.0
VoxMinutes v0.1.0 — first public MVP release.
Your local meeting assistant: records system audio & mic together, real-time transcription, translation and summaries — all on your device.
Highlights
- Real-time streaming transcription (X-ASR / SenseVoice)
- Dual-channel recording: system playback + microphone
- Live translation: OPUS-MT (fast) or Hy-MT2 (13 target languages)
- Local AI meeting summaries (Qwen / Gemma GGUF, on-device)
- History, search, inline editing, TXT / SRT / Markdown export
- Model manager: multi-source downloads (GitHub / hf-mirror / ModelScope) with resume, or import local archives / GGUF
- First-launch onboarding wizard, UI in English / 中文 / 한국어 / 日本語
Install notes
- No models are bundled. On first launch the onboarding wizard guides you to download or import models. Mainland China works out of the box (automatic mirror fallback).
- Windows may show a SmartScreen warning ("Windows protected your PC") because the installer is not code-signed — click More info → Run anyway.
- Requirements: Windows 10/11 x64. All models run on CPU; 8 GB RAM recommended (16 GB if using a local summary model).
中文说明：安装包不内置模型，首次启动会弹出新手指引帮你下载/导入模型（国内网络可直连镜像）。出现蓝色 SmartScreen 提示时点"更多信息 → 仍要运行"即可。