vibe

thewh1teagleMIT活跃维护

跨平台桌面端语音转写工具，基于 Whisper 在本地把音视频转成文字，不用上传云端，隐私和离线场景都能用。

Transcribe on your own!

v3.3.0发布于 2026-10-29 19:10 UTC8,058star +33 / 7 天580fork同步于 2026-11-10 23:32 UTC

语音转写 Whisper 本地推理桌面应用跨平台

对比 GitHub 官网 ai cross-platform desktop openai rust

怎么上手

由 README 提炼，执行前请确认

原文

从 https://thewh1teagle.github.io/vibe/ 下载安装包；CLI 用法见 vibe --help

硬件要求按 README 说明

支持 macOS、Windows、Linux，针对 Nvidia/AMD/Intel GPU 优化（Vulkan/CoreML）。README 未说明具体显存要求。

下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼

没人工点评？写下你的经验

本地离线转录音视频的桌面工具，隐私数据不出设备

跨平台桌面端语音转写工具，基于 Whisper 在本地把音视频转成文字，不用上传云端，隐私和离线场景都能用。

核心能力

完全离线转录，数据不离开本机
支持批量转录多个音视频文件
导出 SRT、VTT、TXT、PDF、DOCX 等格式
支持 Whisper、Nemotron 3.5、Parakeet TDT v3 模型
提供 CLI 与带 Swagger 文档的 HTTP API

容易踩的坑

模型需在设置中自行选择或下载；Claude 摘要需 Claude API，本地分析需另装 Ollama；从手机录制需扫码配对

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

用户点评

登录用户的真实使用记录，可按版本和硬件筛选

共 0 条

还没有人点评。第一个说出真实体验的人最有价值。

README 原文

未翻译

在 GitHub 打开

Screenshots

Features 🌟

🌍 Transcribe almost every language
🔒 Ultimate privacy: fully offline transcription, no data ever leaves your device
🎨 User friendly design
🎙️ Transcribe audio / video
🎶 Option to transcribe audio from popular websites (YouTube, Vimeo, Facebook, Twitter and more!)
📂 Batch transcribe multiple files!
📝 Support SRT, VTT, TXT, HTML, PDF, JSON, DOCX formats
👀 Realtime preview
🤖 Supports Whisper, Nemotron 3.5, and Parakeet TDT v3 models
✨ Summarize transcripts: Get quick, multilingual summaries using the Claude API
🧠 Ollama support: Do local AI analysis and batch summaries with Ollama
🌐 Translate to English from any language
🖨️ Print transcript directly to any printer
🔄 Automatic updates
💻 Optimized for GPU (macOS, Windows, Linux)
🎮 Optimized for Nvidia / AMD / Intel GPUs! (Vulkan/CoreML)
🔧 Total Freedom: Customize Models Easily via Settings
⚙️ Model arguments for advanced users
⏳ Transcribe system audio
🎤 Transcribe from microphone
🖥️ CLI support: Use Vibe directly from the command line interface! (see --help)
👥 Speaker diarization
🎬 Stable timestamps mode for subtitle/movie-grade timing (VAD-backed, slower)
📱 Record from your phone: scan a QR code once, then your computer does the transcribing and sends the text straight back — works on iOS and Android with nothing to install from an app store
📥 Integrate custom models from your own site: Use vibe://download/?url=<model url>
📹 Choose caption length optimized for videos / reels
⚡ HTTP API with Swagger docs and agent skills

Supported platforms 🖥️

MacOS Windows Linux

Contribute 🤝

Developers

Get started with local development here.

Ideas, bug reports and translation fixes are welcome — please open an issue. Pull requests are limited to a few collaborators. See CONTRIBUTE.md.

Community

Roadmap 🛣️

You can see the roadmap in Vibe-Roadmap

Add translation 🌐

See the translation guide.

Docs 📄

see Vibe Docs

I want to know more!

Medium post

Issue report

You can open new issue and it's recommend to check DEBUG.md first.

Privacy Policy 🔒

Your privacy is important to us. Please review our Privacy Policy to understand how we handle your data.

Credits

Thanks for tauri.app for making the best apps framework I ever seen

Thanks for github.com/whisper.cpp for outstanding interface for the AI model.

Thanks for openai.com for their amazing Whisper model

Thanks for github.com for their support in open source projects, providing infastructure completely free.

And for all the amazing open source frameworks and libraries which this project uses...

vibe

怎么上手

项目说明