Whisper Studio

Whisper Studio

Whisper Studio is an independent desktop interface for OpenAI Whisper.
complete with apps for macOS, Windows, Linux

A cross-platform desktop application for AI-powered audio and video transcription using [OpenAI Whisper](https://github.com/openai/whisper). Built with Electron, React, TypeScript, and Vite.

Whisper Studio runs entirely on your machine — no cloud services, no data leaves your device. Transcribe audio or video files, edit the resulting transcript, and export to SRT, VTT, TXT, TSV, or JSON.

Features

• Transcribe audio and video files locally using OpenAI Whisper
• GPU (CUDA) and CPU compute modes
• Real-time transcription progress and live log output
• Interactive transcript editor with search and replace
• Export to SRT, VTT, TXT, TSV, and JSON
• Model manager — download and delete Whisper models in-app
• Prerequisite checker for Python, FFmpeg, CUDA, and pip packages
• Dark / light theme

Getting Started

npm install
npm run dev

Release Targets

Electron Builder is configured for:

• macOS: dmg, zip
• Windows: nsis, portable
• Linux: AppImage, deb

Code signing, notarization, update feeds, and platform-specific icons should be added before publishing production releases.